Best InternLM Internvl2.5 78B Alternatives & Competitors in 2026

OpenAI Sep 29, 2026 flagship reasoning & coding model (superseding GPT-6 Sol) with $2/$10 base pricing and $0.10/1M (95% off) official cached input.

Audit: ⚠️ 272K Context Cliff: Standard $2.00/$10.00 (Cache $0.10) applies up to ≤272K tokens. Prompts exceeding >272K tokens jump to $4.00 input / $15.00 output per 1M tokens.

OpenAI Sep 3, 2026 ultra-frontier deep reasoning flagship ($10/$50 per 1M) with $1.00/1M (90% off) official cached input.

Audit: Internal reasoning tokens are billed at the $50/1M output rate. Always pin system prompts to utilize the $1.00/1M (90% off) cached input rate.

OpenAI Sep 22, 2026 high-throughput compact model priced 100x cheaper than GPT-6 Astra ($0.10/$0.50, Official Cache Read $0.01/1M).

Audit: <=272K: $0.10/$0.50 ($0.01 cache, $0.125 write); >272K full-request cliff: $0.20/$0.75 ($0.02 cache).

Anthropic Sep 22, 2026 flagship coding & autonomous agent model ($4/$20 per 1M, 20% cheaper than Opus 5 ($5/$25 -> $4/$20)) with $0.20/1M (95% off) cache read.

Audit: Adaptive thinking billed at $20/1M output rate ($8/$40 in 2x Fast mode; US-only +10%).

Anthropic Sep 1, 2026 heavy research & synthesis architecture ($10/$50 per 1M) featuring an industry-leading 97.5% cache read discount ($0.25/1M).

Audit: Un-cached multi-turn research loops burn $10/$50 rapidly; enable Prompt Caching immediately to lock in the $0.25/1M (97.5% off) read rate.

Anthropic Sep 28, 2026 production coding workhorse ($2/$10 per 1M). Official cache read cut 50% from $0.20 to $0.10/1M effective Oct 7, 2026.

Audit: Extended thinking tokens bill at Sonnet 5.5 standard $10/1M output rate; cache read cut 50% to $0.10/1M on Oct 7.

Anthropic Oct 7, 2026 ultra-fast model: $0.10/$0.50 (Cache $0.01/1M) for prompts ≤100K tokens; jumps 5x to $0.50/$2.50 (Cache $0.05) for >100K tokens.

Audit: <=100K: $0.10/$0.50 ($0.01 cache); >100K (including cached tokens) jumps 5x to $0.50/$2.50 ($0.05 cache) for the full request.

Google Oct 1, 2026 multimodal flagship currently at $2/$10 (Cache $0.10/1M) Time-Limited Intro Price through Nov 30, 2026; increases to $4/$20 (Cache $0.20) on Dec 1, 2026.

Audit: ⚠️ Time-Limited Intro Pricing Alert: The $2.00/$10.00 (Cache $0.10) rate expires on 2026-11-30! Starting 2026-12-01, standard pricing doubles to $4.00/$20.00 (Cache $0.20).

Google Gemini 3.8 Flash high-speed multimodal model ($0.75/$3.75 intro thru 2026-12-31, Official Cache Read $0.075/1M [90% off], reprices to $1.50/$7.50 in 2027).

Audit: ⚠️ Intro Rate Expiration: Official $0.75/$3.75 (Cache $0.075/1M) introductory pricing ends 2026-12-31, increasing to $1.50/$7.50 in Jan 2027.

DeepSeek-V4 Pro (0813) 1.6T MoE flagship: Off-Peak $0.66/$1.98 ($0.022/1M KV cache hit, 96.7% off); Weekday UTC Peak (01-04 & 06-10) 2x at $1.32/$3.96 ($0.044 cache).

Audit: Off-Peak: $0.66/$1.98 ($0.022 cache); Weekday UTC Peak (01-04 & 06-10): $1.32/$3.96 ($0.044 cache). Chinese statutory holidays count as all-day Off-Peak.

DeepSeek-V4.1-Flash-1017 high-speed coding & triage model: Off-Peak $0.15/$0.60 ($0.003/1M KV cache hit, 98% off); Peak $0.30/$1.20 ($0.006 cache).

Audit: Off-Peak: $0.15/$0.60 ($0.003 cache); Weekday UTC Peak: $0.30/$1.20 ($0.006 cache). Search/Fetch API ($0.75/1K) begins billing 2026-10-31T16:00:00Z (Nov 1 00:00 Beijing).

OpenAI GPT-5.6 Terra router catalog tier ($2.00/$12.00 per 1M, 400K flat context window, $0.20 cache read).

Audit: Flat context pricing ($2.00/$12.00, Cache $0.20/1M); consider migrating to GPT-6.1 Sol ($2.00/$10.00, Cache $0.10/1M) for 95% cache savings.

OpenAI Daybreak Program specialized defensive cybersecurity & vulnerability auditing model ($12.50/$75.00 per 1M, restricted authorization).

Audit: Requires OpenAI Daybreak Program enterprise security clearance. High $12.50/$75.00 token rate; enable $1.25/1M prompt caching for codebase scans.

Flagship GPT-5 series general model with configurable reasoning_effort from none to xhigh.

Audit: Official gpt-5.5-chat-latest cached input rate is $0.50/1M (90% off $5.00 input). Migrate to GPT-6.1 Sol ($2/$10, Cache $0.10) to cut spend by 50%.

OpenAI GPT-5.4 nano high-throughput classification & routing model ($0.20/$1.25 per 1M, Official Cache Read $0.02/1M [90% Off], 128K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

OpenAI specialized code generation & repository refactoring model ($1.75/$14.00 per 1M, Official Cache Read $0.175/1M).

Audit: High $14.00/1M output rate; pin repository context in prefix cache ($0.175/1M read, 90% off) or migrate to GPT-6.1 Sol ($2/$10, Cache $0.10).

xAI frontier reasoning & coding model (500K context): <200K at $2/$6 ($0.50 cache); >=200K at $4/$12 ($1.00 cache). No batch discount.

Audit: <200K: $2.00/$6.00 ($0.50 cache); >=200K (including cached tokens) full-request 2x cliff: $4.00/$12.00 ($1.00 cache). Not eligible for Batch discount (0%); Priority 2x; US endpoint +10%.

OpenAI prior-generation Sol tier ($4.00/$20.00 <=272K, $0.40 cache read; >272K cliff $8/$30; promo active until 2026-11-21).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Google 2M context multimodal model (<=200K: $2.00/$12.00, $0.20 cache; >200K cliff: $4.00/$18.00, 180K soft-block).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Alibaba Bailian 0-1M flat context window model (CNY 0.80/2.70 = $0.1124/$0.3792 USD @ FX 7.12, $0.0225 cache read, 0% batch discount).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Alibaba Bailian stepped tier model (50% Batch off; <=32K CNY 0.20/0.80, 32K-256K CNY 0.60/2.40, >256K CNY 1.20/4.80; 230.4K soft-cap -> qwen3.8-flash).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Mistral AI frontier multilingual & reasoning model ($1.50/$4.50 per 1M, $0.15 cache read [90% off], 256K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Mistral specialized low-latency code generation model ($0.20/$0.60 per 1M, $0.04 cache read [80% off], 256K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Cohere enterprise RAG & agentic reasoning model ($2.50/$10.00 per 1M, $0.25 cache read [90% off], 256K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Moonshot AI 1-Trillion parameter MoE model ($0.55/$2.20 per 1M, $0.055 cache read [90% off], 256K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Zhipu AI flagship bilingual reasoning model ($0.70/$2.80 per 1M, $0.07 cache read [90% off], 128K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

MiniMax 4-Million token ultra-long context model ($0.80/$3.20 per 1M, $0.08 cache read [90% off], 4M context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

AWS Bedrock flagship multimodal model ($2.50/$12.50 per 1M, $0.25 cache read [90% off], 2M context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

xAI Grok 4.3 high-speed reasoning model: $1.25/$2.50 (Cache $0.20/1M) short context; jumps to $2.50/$5.00 (Cache $0.40/1M) on long context.

Audit: <200K: $1.25/$2.50 ($0.20 cache); >=200K full-request 2x cliff: $2.50/$5.00 ($0.40 cache). Batch discount is 20%; Priority tier 2x; US endpoint +10%.

Meta Llama 4 Scout 109B open-weight MoE model ($0.11/$0.34 per 1M, $0.022/1M cache read [80% off], 10M token context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

DeepSeek-R1 (deepseek-reasoner) open-weight reinforcement-learning reasoning model ($0.55/$2.19 per 1M, $0.14/1M disk KV cache hit, 128K context window).

Audit: Enable Prompt Context Caching & Batch API to reduce repeated system prompt input token burn by 50%-97.5%.

Alibaba Qwen Qwen3 235B A22B (qwen/qwen3-235b-a22b): OpenRouter gateway-synced model at $0.22/1M input, $0.88/1M output, $0.022/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.22/$0.88 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 32B (qwen/qwen3-32b): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 30B A3B (qwen/qwen3-30b-a3b): OpenRouter gateway-synced model at $0.06/1M input, $0.22/1M output, $0.006/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.06/$0.22 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 14B (qwen/qwen3-14b): OpenRouter gateway-synced model at $0.05/1M input, $0.18/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.18 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 8B (qwen/qwen3-8b): OpenRouter gateway-synced model at $0.03/1M input, $0.1/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 4B (qwen/qwen3-4b): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 1.7B (qwen/qwen3-1.7b): OpenRouter gateway-synced model at $0.015/1M input, $0.04/1M output, $0.0015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.015/$0.04 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 0.6B (qwen/qwen3-0.6b): OpenRouter gateway-synced model at $0.01/1M input, $0.02/1M output, $0.001/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.01/$0.02 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwq 32B (qwen/qwq-32b): OpenRouter gateway-synced model at $0.12/1M input, $0.35/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.35 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwq 32B Preview (qwen/qwq-32b-preview): OpenRouter gateway-synced model at $0.12/1M input, $0.35/1M output, $0.012/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.12/$0.35 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Coder 32B Instruct (qwen/qwen-2.5-coder-32b-instruct): OpenRouter gateway-synced model at $0.07/1M input, $0.16/1M output, $0.007/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.07/$0.16 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Coder 14B Instruct (qwen/qwen-2.5-coder-14b-instruct): OpenRouter gateway-synced model at $0.05/1M input, $0.12/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.12 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Coder 7B Instruct (qwen/qwen-2.5-coder-7b-instruct): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 72B Instruct (qwen/qwen-2.5-72b-instruct): OpenRouter gateway-synced model at $0.12/1M input, $0.39/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.39 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 32B Instruct (qwen/qwen-2.5-32b-instruct): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 14B Instruct (qwen/qwen-2.5-14b-instruct): OpenRouter gateway-synced model at $0.05/1M input, $0.15/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 7B Instruct (qwen/qwen-2.5-7b-instruct): OpenRouter gateway-synced model at $0.025/1M input, $0.05/1M output, $0.0025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.025/$0.05 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Vl 72B Instruct (qwen/qwen-2.5-vl-72b-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Vl 32B Instruct (qwen/qwen-2.5-vl-32b-instruct): OpenRouter gateway-synced model at $0.09/1M input, $0.27/1M output, $0.009/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.09/$0.27 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Vl 7B Instruct (qwen/qwen-2.5-vl-7b-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.1/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Math 72B Instruct (qwen/qwen-2.5-math-72b-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Math 7B Instruct (qwen/qwen-2.5-math-7b-instruct): OpenRouter gateway-synced model at $0.03/1M input, $0.08/1M output, $0.003/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.03/$0.08 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen Plus (qwen/qwen-plus): OpenRouter gateway-synced model at $0.4/1M input, $1.2/1M output, $0.04/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.4/$1.2 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen Turbo (qwen/qwen-turbo): OpenRouter gateway-synced model at $0.05/1M input, $0.2/1M output, $0.005/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.05/$0.2 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen Max (qwen/qwen-max): OpenRouter gateway-synced model at $1.6/1M input, $4.8/1M output, $0.16/1M cached input (256K context window).

Audit: Gateway-synced rate ($1.6/$4.8 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen Vl Max (qwen/qwen-vl-max): OpenRouter gateway-synced model at $0.8/1M input, $2.4/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$2.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen Vl Plus (qwen/qwen-vl-plus): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2 72B Instruct (qwen/qwen-2-72b-instruct): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2 7B Instruct (qwen/qwen-2-7b-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.05/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.05 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2 Vl 72B Instruct (qwen/qwen-2-vl-72b-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2 Vl 7B Instruct (qwen/qwen-2-vl-7b-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.1/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.1 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 1.5 110B Chat (qwen/qwen-1.5-110b-chat): OpenRouter gateway-synced model at $0.18/1M input, $0.54/1M output, $0.018/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.18/$0.54 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 1.5 72B Chat (qwen/qwen-1.5-72b-chat): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 1.5 32B Chat (qwen/qwen-1.5-32b-chat): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 1.5 14B Chat (qwen/qwen-1.5-14b-chat): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 1.5 7B Chat (qwen/qwen-1.5-7b-chat): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 Coder 480B A35B Instruct (qwen/qwen3-coder-480b-a35b-instruct): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 Coder 30B A3B Instruct (qwen/qwen3-coder-30b-a3b-instruct): OpenRouter gateway-synced model at $0.07/1M input, $0.21/1M output, $0.007/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.07/$0.21 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 235B A22B Thinking 2507 (qwen/qwen3-235b-a22b-thinking-2507): OpenRouter gateway-synced model at $0.25/1M input, $0.95/1M output, $0.025/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.25/$0.95 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 235B A22B Instruct 2507 (qwen/qwen3-235b-a22b-instruct-2507): OpenRouter gateway-synced model at $0.22/1M input, $0.88/1M output, $0.022/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.22/$0.88 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen3 30B A3B Instruct 2507 (qwen/qwen3-30b-a3b-instruct-2507): OpenRouter gateway-synced model at $0.06/1M input, $0.22/1M output, $0.006/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.06/$0.22 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 Coder 3B Instruct (qwen/qwen-2.5-coder-3b-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.04/1M output, $0.002/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.02/$0.04 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 3B Instruct (qwen/qwen-2.5-3b-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.04/1M output, $0.002/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.02/$0.04 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 1.5B Instruct (qwen/qwen-2.5-1.5b-instruct): OpenRouter gateway-synced model at $0.01/1M input, $0.02/1M output, $0.001/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.01/$0.02 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Alibaba Qwen Qwen 2.5 0.5B Instruct (qwen/qwen-2.5-0.5b-instruct): OpenRouter gateway-synced model at $0.01/1M input, $0.02/1M output, $0.001/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.01/$0.02 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Chat V3 0324 (deepseek/deepseek-chat-v3-0324): OpenRouter gateway-synced model at $0.2/1M input, $0.77/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.77 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Chat (deepseek/deepseek-chat): OpenRouter gateway-synced model at $0.2/1M input, $0.77/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.77 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 0528 (deepseek/deepseek-r1-0528): OpenRouter gateway-synced model at $0.5/1M input, $2.15/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$2.15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Distill Llama 70B (deepseek/deepseek-r1-distill-llama-70b): OpenRouter gateway-synced model at $0.23/1M input, $0.69/1M output, $0.023/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.23/$0.69 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Distill Qwen 32B (deepseek/deepseek-r1-distill-qwen-32b): OpenRouter gateway-synced model at $0.12/1M input, $0.35/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.35 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Distill Qwen 14B (deepseek/deepseek-r1-distill-qwen-14b): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Distill Llama 8B (deepseek/deepseek-r1-distill-llama-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Distill Qwen 7B (deepseek/deepseek-r1-distill-qwen-7b): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Distill Qwen 1.5B (deepseek/deepseek-r1-distill-qwen-1.5b): OpenRouter gateway-synced model at $0.015/1M input, $0.03/1M output, $0.0015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.015/$0.03 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Prover V2 (deepseek/deepseek-prover-v2): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek V2.5 (deepseek/deepseek-v2.5): OpenRouter gateway-synced model at $0.14/1M input, $0.28/1M output, $0.014/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.14/$0.28 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Coder V2 Instruct (deepseek/deepseek-coder-v2-instruct): OpenRouter gateway-synced model at $0.14/1M input, $0.28/1M output, $0.014/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.14/$0.28 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Coder V2 Lite Instruct (deepseek/deepseek-coder-v2-lite-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Vl2 (deepseek/deepseek-vl2): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Vl2 Small (deepseek/deepseek-vl2-small): OpenRouter gateway-synced model at $0.06/1M input, $0.18/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.18 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Vl2 Tiny (deepseek/deepseek-vl2-tiny): OpenRouter gateway-synced model at $0.03/1M input, $0.09/1M output, $0.003/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.03/$0.09 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Math 7B Instruct (deepseek/deepseek-math-7b-instruct): OpenRouter gateway-synced model at $0.03/1M input, $0.09/1M output, $0.003/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.03/$0.09 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Llm 67B Chat (deepseek/deepseek-llm-67b-chat): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek Coder 33B Instruct (deepseek/deepseek-coder-33b-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

DeepSeek Deepseek R1 Zero (deepseek/deepseek-r1-zero): OpenRouter gateway-synced model at $0.5/1M input, $2/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.3 70B Instruct (meta-llama/llama-3.3-70b-instruct): OpenRouter gateway-synced model at $0.12/1M input, $0.3/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.2 90B Vision Instruct (meta-llama/llama-3.2-90b-vision-instruct): OpenRouter gateway-synced model at $0.35/1M input, $0.4/1M output, $0.035/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.35/$0.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.2 11B Vision Instruct (meta-llama/llama-3.2-11b-vision-instruct): OpenRouter gateway-synced model at $0.05/1M input, $0.05/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.05 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.2 3B Instruct (meta-llama/llama-3.2-3b-instruct): OpenRouter gateway-synced model at $0.015/1M input, $0.025/1M output, $0.0015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.015/$0.025 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.2 1B Instruct (meta-llama/llama-3.2-1b-instruct): OpenRouter gateway-synced model at $0.01/1M input, $0.015/1M output, $0.001/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.01/$0.015 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.1 405B Instruct (meta-llama/llama-3.1-405b-instruct): OpenRouter gateway-synced model at $0.8/1M input, $0.8/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$0.8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.1 405B (meta-llama/llama-3.1-405b): OpenRouter gateway-synced model at $0.8/1M input, $0.8/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$0.8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.1 70B Instruct (meta-llama/llama-3.1-70b-instruct): OpenRouter gateway-synced model at $0.23/1M input, $0.4/1M output, $0.023/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.23/$0.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.1 8B Instruct (meta-llama/llama-3.1-8b-instruct): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3 70B Instruct (meta-llama/llama-3-70b-instruct): OpenRouter gateway-synced model at $0.3/1M input, $0.6/1M output, $0.03/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.3/$0.6 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3 8B Instruct (meta-llama/llama-3-8b-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama Guard 4 12B (meta-llama/llama-guard-4-12b): OpenRouter gateway-synced model at $0.03/1M input, $0.03/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.03 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama Guard 3 8B (meta-llama/llama-guard-3-8b): OpenRouter gateway-synced model at $0.02/1M input, $0.02/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.02 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama Guard 2 8B (meta-llama/llama-guard-2-8b): OpenRouter gateway-synced model at $0.02/1M input, $0.02/1M output, $0.002/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.02/$0.02 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Codellama 70B Instruct (meta-llama/codellama-70b-instruct): OpenRouter gateway-synced model at $0.25/1M input, $0.5/1M output, $0.025/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.25/$0.5 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Codellama 34B Instruct (meta-llama/codellama-34b-instruct): OpenRouter gateway-synced model at $0.12/1M input, $0.24/1M output, $0.012/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.12/$0.24 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Codellama 13B Instruct (meta-llama/codellama-13b-instruct): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Codellama 7B Instruct (meta-llama/codellama-7b-instruct): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 2 70B Chat (meta-llama/llama-2-70b-chat): OpenRouter gateway-synced model at $0.35/1M input, $0.7/1M output, $0.035/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.35/$0.7 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 2 13B Chat (meta-llama/llama-2-13b-chat): OpenRouter gateway-synced model at $0.1/1M input, $0.2/1M output, $0.01/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.1/$0.2 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.1 70B Instruct Fp8 (meta-llama/llama-3.1-70b-instruct-fp8): OpenRouter gateway-synced model at $0.2/1M input, $0.35/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.35 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.1 405B Instruct Fp8 (meta-llama/llama-3.1-405b-instruct-fp8): OpenRouter gateway-synced model at $0.7/1M input, $0.7/1M output, $0.07/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.7/$0.7 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Meta Llama Llama 3.3 70B Instruct Fp8 (meta-llama/llama-3.3-70b-instruct-fp8): OpenRouter gateway-synced model at $0.1/1M input, $0.25/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.25 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.5 Pro (google/gemini-2.5-pro): OpenRouter gateway-synced model at $1.25/1M input, $10/1M output, $0.125/1M cached input (2000K context window).

Audit: Gateway-synced rate ($1.25/$10 per 1M, flat 2000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.5 Flash (google/gemini-2.5-flash): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.5 Flash Lite (google/gemini-2.5-flash-lite): OpenRouter gateway-synced model at $0.075/1M input, $0.3/1M output, $0.0075/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.075/$0.3 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.0 Flash 001 (google/gemini-2.0-flash-001): OpenRouter gateway-synced model at $0.1/1M input, $0.4/1M output, $0.01/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.1/$0.4 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.0 Flash Lite 001 (google/gemini-2.0-flash-lite-001): OpenRouter gateway-synced model at $0.075/1M input, $0.3/1M output, $0.0075/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.075/$0.3 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.0 Pro Exp 02 05 (google/gemini-2.0-pro-exp-02-05): OpenRouter gateway-synced model at $1.25/1M input, $5/1M output, $0.125/1M cached input (2000K context window).

Audit: Gateway-synced rate ($1.25/$5 per 1M, flat 2000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 1.5 Pro (google/gemini-1.5-pro): OpenRouter gateway-synced model at $1.25/1M input, $5/1M output, $0.125/1M cached input (2000K context window).

Audit: Gateway-synced rate ($1.25/$5 per 1M, flat 2000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 1.5 Flash (google/gemini-1.5-flash): OpenRouter gateway-synced model at $0.075/1M input, $0.3/1M output, $0.0075/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.075/$0.3 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 1.5 Flash 8B (google/gemini-1.5-flash-8b): OpenRouter gateway-synced model at $0.0375/1M input, $0.15/1M output, $0.0037/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.0375/$0.15 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 3 27B It (google/gemma-3-27b-it): OpenRouter gateway-synced model at $0.1/1M input, $0.2/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 3 12B It (google/gemma-3-12b-it): OpenRouter gateway-synced model at $0.05/1M input, $0.1/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 3 4B It (google/gemma-3-4b-it): OpenRouter gateway-synced model at $0.02/1M input, $0.04/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.04 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 3 1B It (google/gemma-3-1b-it): OpenRouter gateway-synced model at $0.01/1M input, $0.02/1M output, $0.001/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.01/$0.02 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 2 27B It (google/gemma-2-27b-it): OpenRouter gateway-synced model at $0.1/1M input, $0.2/1M output, $0.01/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.1/$0.2 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 2 9B It (google/gemma-2-9b-it): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 2 2B It (google/gemma-2-2b-it): OpenRouter gateway-synced model at $0.01/1M input, $0.02/1M output, $0.001/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.01/$0.02 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Codegemma 7B It (google/codegemma-7b-it): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Paligemma 2 28B It (google/paligemma-2-28b-it): OpenRouter gateway-synced model at $0.12/1M input, $0.24/1M output, $0.012/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.12/$0.24 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Paligemma 2 10B It (google/paligemma-2-10b-it): OpenRouter gateway-synced model at $0.05/1M input, $0.1/1M output, $0.005/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.05/$0.1 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Medgemma 27B It (google/medgemma-27b-it): OpenRouter gateway-synced model at $0.15/1M input, $0.3/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Shieldgemma 2 27B It (google/shieldgemma-2-27b-it): OpenRouter gateway-synced model at $0.08/1M input, $0.16/1M output, $0.008/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.08/$0.16 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Txgemma 27B Chat (google/txgemma-27b-chat): OpenRouter gateway-synced model at $0.12/1M input, $0.24/1M output, $0.012/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.12/$0.24 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.5 Pro Preview 05 06 (google/gemini-2.5-pro-preview-05-06): OpenRouter gateway-synced model at $1.25/1M input, $10/1M output, $0.125/1M cached input (2000K context window).

Audit: Gateway-synced rate ($1.25/$10 per 1M, flat 2000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemini 2.5 Flash Preview 05 20 (google/gemini-2.5-flash-preview-05-20): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Google Gemma 7B It (google/gemma-7b-it): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Large 2411 (mistralai/mistral-large-2411): OpenRouter gateway-synced model at $2/1M input, $6/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Large 2407 (mistralai/mistral-large-2407): OpenRouter gateway-synced model at $2/1M input, $6/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Medium 3 (mistralai/mistral-medium-3): OpenRouter gateway-synced model at $0.4/1M input, $2/1M output, $0.04/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.4/$2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Small 3.1 24B Instruct (mistralai/mistral-small-3.1-24b-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Small 24B Instruct 2501 (mistralai/mistral-small-24b-instruct-2501): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Small 2409 (mistralai/mistral-small-2409): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Pixtral Large 2411 (mistralai/pixtral-large-2411): OpenRouter gateway-synced model at $2/1M input, $6/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Pixtral 12B (mistralai/pixtral-12b): OpenRouter gateway-synced model at $0.1/1M input, $0.1/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Codestral 2501 (mistralai/codestral-2501): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Codestral 2405 (mistralai/codestral-2405): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Codestral Mamba (mistralai/codestral-mamba): OpenRouter gateway-synced model at $0.1/1M input, $0.1/1M output, $0.01/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.1/$0.1 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Ministral 8B (mistralai/ministral-8b): OpenRouter gateway-synced model at $0.1/1M input, $0.1/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Ministral 3B (mistralai/ministral-3b): OpenRouter gateway-synced model at $0.04/1M input, $0.04/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.04 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Saba (mistralai/mistral-saba): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Nemo (mistralai/mistral-nemo): OpenRouter gateway-synced model at $0.04/1M input, $0.04/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.04 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mixtral 8X22B Instruct (mistralai/mixtral-8x22b-instruct): OpenRouter gateway-synced model at $0.65/1M input, $0.65/1M output, $0.065/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.65/$0.65 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mixtral 8X7B Instruct (mistralai/mixtral-8x7b-instruct): OpenRouter gateway-synced model at $0.24/1M input, $0.24/1M output, $0.024/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.24/$0.24 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral 7B Instruct V0.3 (mistralai/mistral-7b-instruct-v0.3): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mathstral 7B V0.1 (mistralai/mathstral-7b-v0.1): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Devstral Small (mistralai/devstral-small): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Magistral Medium 2506 (mistralai/magistral-medium-2506): OpenRouter gateway-synced model at $2/1M input, $5/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Magistral Small 2506 (mistralai/magistral-small-2506): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Small 3.2 24B Instruct (mistralai/mistral-small-3.2-24b-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Medium 2312 (mistralai/mistral-medium-2312): OpenRouter gateway-synced model at $0.8/1M input, $2.4/1M output, $0.08/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.8/$2.4 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Mistral AI Mistral Tiny (mistralai/mistral-tiny): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude Opus 4 (anthropic/claude-opus-4): OpenRouter gateway-synced model at $15/1M input, $75/1M output, $1.5/1M cached input (200K context window).

Audit: Gateway-synced rate ($15/$75 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude Sonnet 4 (anthropic/claude-sonnet-4): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3.7 Sonnet (anthropic/claude-3.7-sonnet): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3.7 Sonnet Thinking (anthropic/claude-3.7-sonnet-thinking): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3.5 Sonnet (anthropic/claude-3.5-sonnet): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3.5 Sonnet 20240620 (anthropic/claude-3.5-sonnet-20240620): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3.5 Haiku (anthropic/claude-3.5-haiku): OpenRouter gateway-synced model at $0.8/1M input, $4/1M output, $0.08/1M cached input (200K context window).

Audit: Gateway-synced rate ($0.8/$4 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3.5 Haiku 20241022 (anthropic/claude-3.5-haiku-20241022): OpenRouter gateway-synced model at $0.8/1M input, $4/1M output, $0.08/1M cached input (200K context window).

Audit: Gateway-synced rate ($0.8/$4 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3 Opus (anthropic/claude-3-opus): OpenRouter gateway-synced model at $15/1M input, $75/1M output, $1.5/1M cached input (200K context window).

Audit: Gateway-synced rate ($15/$75 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3 Sonnet (anthropic/claude-3-sonnet): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 3 Haiku (anthropic/claude-3-haiku): OpenRouter gateway-synced model at $0.25/1M input, $1.25/1M output, $0.025/1M cached input (200K context window).

Audit: Gateway-synced rate ($0.25/$1.25 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthropic Claude 2.1 (anthropic/claude-2.1): OpenRouter gateway-synced model at $8/1M input, $24/1M output, $0.8/1M cached input (200K context window).

Audit: Gateway-synced rate ($8/$24 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4.5 Preview (openai/gpt-4.5-preview): OpenRouter gateway-synced model at $75/1M input, $150/1M output, $7.5/1M cached input (128K context window).

Audit: Gateway-synced rate ($75/$150 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4.1 (openai/gpt-4.1): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (1000K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4.1 Mini (openai/gpt-4.1-mini): OpenRouter gateway-synced model at $0.4/1M input, $1.6/1M output, $0.04/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.4/$1.6 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4.1 Nano (openai/gpt-4.1-nano): OpenRouter gateway-synced model at $0.1/1M input, $0.4/1M output, $0.01/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.1/$0.4 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O 2024 11 20 (openai/gpt-4o-2024-11-20): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O 2024 08 06 (openai/gpt-4o-2024-08-06): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O 2024 05 13 (openai/gpt-4o-2024-05-13): OpenRouter gateway-synced model at $5/1M input, $15/1M output, $0.5/1M cached input (128K context window).

Audit: Gateway-synced rate ($5/$15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O Mini 2024 07 18 (openai/gpt-4o-mini-2024-07-18): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O Audio Preview (openai/gpt-4o-audio-preview): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O Search Preview (openai/gpt-4o-search-preview): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O Mini Search Preview (openai/gpt-4o-mini-search-preview): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O4 Mini (openai/o4-mini): OpenRouter gateway-synced model at $1.1/1M input, $4.4/1M output, $0.11/1M cached input (200K context window).

Audit: Gateway-synced rate ($1.1/$4.4 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O4 Mini High (openai/o4-mini-high): OpenRouter gateway-synced model at $1.1/1M input, $4.4/1M output, $0.11/1M cached input (200K context window).

Audit: Gateway-synced rate ($1.1/$4.4 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O3 (openai/o3): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (200K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O3 Pro (openai/o3-pro): OpenRouter gateway-synced model at $20/1M input, $80/1M output, $2/1M cached input (200K context window).

Audit: Gateway-synced rate ($20/$80 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O3 Mini (openai/o3-mini): OpenRouter gateway-synced model at $1.1/1M input, $4.4/1M output, $0.11/1M cached input (200K context window).

Audit: Gateway-synced rate ($1.1/$4.4 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O3 Mini High (openai/o3-mini-high): OpenRouter gateway-synced model at $1.1/1M input, $4.4/1M output, $0.11/1M cached input (200K context window).

Audit: Gateway-synced rate ($1.1/$4.4 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O1 (openai/o1): OpenRouter gateway-synced model at $15/1M input, $60/1M output, $1.5/1M cached input (200K context window).

Audit: Gateway-synced rate ($15/$60 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O1 Pro (openai/o1-pro): OpenRouter gateway-synced model at $150/1M input, $600/1M output, $15/1M cached input (200K context window).

Audit: Gateway-synced rate ($150/$600 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI O1 Mini (openai/o1-mini): OpenRouter gateway-synced model at $1.1/1M input, $4.4/1M output, $0.11/1M cached input (128K context window).

Audit: Gateway-synced rate ($1.1/$4.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4 Turbo (openai/gpt-4-turbo): OpenRouter gateway-synced model at $10/1M input, $30/1M output, $1/1M cached input (128K context window).

Audit: Gateway-synced rate ($10/$30 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4 Turbo Preview (openai/gpt-4-turbo-preview): OpenRouter gateway-synced model at $10/1M input, $30/1M output, $1/1M cached input (128K context window).

Audit: Gateway-synced rate ($10/$30 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4 0613 (openai/gpt-4-0613): OpenRouter gateway-synced model at $30/1M input, $60/1M output, $3/1M cached input (32K context window).

Audit: Gateway-synced rate ($30/$60 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 3.5 Turbo 0125 (openai/gpt-3.5-turbo-0125): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (16K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 16K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 3.5 Turbo 16K (openai/gpt-3.5-turbo-16k): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (16K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 16K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Codex Mini (openai/codex-mini): OpenRouter gateway-synced model at $1.5/1M input, $6/1M output, $0.15/1M cached input (200K context window).

Audit: Gateway-synced rate ($1.5/$6 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O (openai/gpt-4o): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenAI Gpt 4O Mini (openai/gpt-4o-mini): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command A (cohere/command-a): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (256K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R Plus 08 2024 (cohere/command-r-plus-08-2024): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R Plus 04 2024 (cohere/command-r-plus-04-2024): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (128K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R 08 2024 (cohere/command-r-08-2024): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R 03 2024 (cohere/command-r-03-2024): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R7B 12 2024 (cohere/command-r7b-12-2024): OpenRouter gateway-synced model at $0.0375/1M input, $0.15/1M output, $0.0037/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.0375/$0.15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Aya Expanse 32B (cohere/aya-expanse-32b): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Aya Expanse 8B (cohere/aya-expanse-8b): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Aya Vision 32B (cohere/aya-vision-32b): OpenRouter gateway-synced model at $0.6/1M input, $1.8/1M output, $0.06/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.6/$1.8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Aya Vision 8B (cohere/aya-vision-8b): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R Plus (cohere/command-r-plus): OpenRouter gateway-synced model at $2.5/1M input, $10/1M output, $0.25/1M cached input (128K context window).

Audit: Gateway-synced rate ($2.5/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Cohere Command R (cohere/command-r): OpenRouter gateway-synced model at $0.15/1M input, $0.6/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Llama 3.1 Nemotron 70B Instruct (nvidia/llama-3.1-nemotron-70b-instruct): OpenRouter gateway-synced model at $0.12/1M input, $0.3/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Llama 3.3 Nemotron Super 49B V1 (nvidia/llama-3.3-nemotron-super-49b-v1): OpenRouter gateway-synced model at $0.1/1M input, $0.4/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Llama 3.1 Nemotron Ultra 253B V1 (nvidia/llama-3.1-nemotron-ultra-253b-v1): OpenRouter gateway-synced model at $0.6/1M input, $1.8/1M output, $0.06/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.6/$1.8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Llama 3.1 Nemotron Nano 8B V1 (nvidia/llama-3.1-nemotron-nano-8b-v1): OpenRouter gateway-synced model at $0.03/1M input, $0.09/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.09 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Nemotron 4 340B Instruct (nvidia/nemotron-4-340b-instruct): OpenRouter gateway-synced model at $1.2/1M input, $1.2/1M output, $0.12/1M cached input (64K context window).

Audit: Gateway-synced rate ($1.2/$1.2 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Nemotron 3 8B Chat 4K (nvidia/nemotron-3-8b-chat-4k): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Nemotron Mini 4B Instruct (nvidia/nemotron-mini-4b-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.04/1M output, $0.002/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.02/$0.04 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Nvlm D 72B (nvidia/nvlm-d-72b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Cosmos Nemotron 34B (nvidia/cosmos-nemotron-34b): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NVIDIA Llama 3.1 Nemotron 51B Instruct (nvidia/llama-3.1-nemotron-51b-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.4/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 4 (microsoft/phi-4): OpenRouter gateway-synced model at $0.07/1M input, $0.14/1M output, $0.007/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.07/$0.14 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 4 Multimodal Instruct (microsoft/phi-4-multimodal-instruct): OpenRouter gateway-synced model at $0.05/1M input, $0.1/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 4 Mini Instruct (microsoft/phi-4-mini-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.05/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.05 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 4 Reasoning Plus (microsoft/phi-4-reasoning-plus): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 4 Mini Reasoning (microsoft/phi-4-mini-reasoning): OpenRouter gateway-synced model at $0.03/1M input, $0.09/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.09 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 3.5 Mini 128K Instruct (microsoft/phi-3.5-mini-128k-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 3.5 Moe 128K Instruct (microsoft/phi-3.5-moe-128k-instruct): OpenRouter gateway-synced model at $0.12/1M input, $0.24/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.24 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 3.5 Vision 128K Instruct (microsoft/phi-3.5-vision-128k-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.2/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 3 Medium 128K Instruct (microsoft/phi-3-medium-128k-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.2/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Phi 3 Mini 128K Instruct (microsoft/phi-3-mini-128k-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Wizardlm 2 8X22B (microsoft/wizardlm-2-8x22b): OpenRouter gateway-synced model at $0.5/1M input, $0.5/1M output, $0.05/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.5/$0.5 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Wizardlm 2 7B (microsoft/wizardlm-2-7b): OpenRouter gateway-synced model at $0.05/1M input, $0.05/1M output, $0.005/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.05/$0.05 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Mai Ds R1 (microsoft/mai-ds-r1): OpenRouter gateway-synced model at $0.45/1M input, $1.8/1M output, $0.045/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.45/$1.8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Microsoft Orca 2 13B (microsoft/orca-2-13b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Sonar Reasoning Pro (perplexity/sonar-reasoning-pro): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Sonar Reasoning (perplexity/sonar-reasoning): OpenRouter gateway-synced model at $1/1M input, $5/1M output, $0.1/1M cached input (128K context window).

Audit: Gateway-synced rate ($1/$5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Sonar Pro (perplexity/sonar-pro): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (200K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 200K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Sonar (perplexity/sonar): OpenRouter gateway-synced model at $1/1M input, $1/1M output, $0.1/1M cached input (128K context window).

Audit: Gateway-synced rate ($1/$1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Sonar Deep Research (perplexity/sonar-deep-research): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity R1 1776 (perplexity/r1-1776): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Llama 3.1 Sonar Large 128K Online (perplexity/llama-3.1-sonar-large-128k-online): OpenRouter gateway-synced model at $1/1M input, $1/1M output, $0.1/1M cached input (128K context window).

Audit: Gateway-synced rate ($1/$1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Llama 3.1 Sonar Small 128K Online (perplexity/llama-3.1-sonar-small-128k-online): OpenRouter gateway-synced model at $0.2/1M input, $0.2/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Perplexity Llama 3.1 Sonar Huge 128K Online (perplexity/llama-3.1-sonar-huge-128k-online): OpenRouter gateway-synced model at $5/1M input, $5/1M output, $0.5/1M cached input (128K context window).

Audit: Gateway-synced rate ($5/$5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 3 Beta (x-ai/grok-3-beta): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (128K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 3 Mini Beta (x-ai/grok-3-mini-beta): OpenRouter gateway-synced model at $0.3/1M input, $0.5/1M output, $0.03/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.3/$0.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 3 Fast Beta (x-ai/grok-3-fast-beta): OpenRouter gateway-synced model at $5/1M input, $25/1M output, $0.5/1M cached input (128K context window).

Audit: Gateway-synced rate ($5/$25 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 3 Mini Fast Beta (x-ai/grok-3-mini-fast-beta): OpenRouter gateway-synced model at $0.6/1M input, $4/1M output, $0.06/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.6/$4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 2 1212 (x-ai/grok-2-1212): OpenRouter gateway-synced model at $2/1M input, $10/1M output, $0.2/1M cached input (128K context window).

Audit: Gateway-synced rate ($2/$10 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 2 Vision 1212 (x-ai/grok-2-vision-1212): OpenRouter gateway-synced model at $2/1M input, $10/1M output, $0.2/1M cached input (32K context window).

Audit: Gateway-synced rate ($2/$10 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok Vision Beta (x-ai/grok-vision-beta): OpenRouter gateway-synced model at $5/1M input, $15/1M output, $0.5/1M cached input (32K context window).

Audit: Gateway-synced rate ($5/$15 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok Beta (x-ai/grok-beta): OpenRouter gateway-synced model at $5/1M input, $15/1M output, $0.5/1M cached input (128K context window).

Audit: Gateway-synced rate ($5/$15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 3 (x-ai/grok-3): OpenRouter gateway-synced model at $3/1M input, $15/1M output, $0.3/1M cached input (128K context window).

Audit: Gateway-synced rate ($3/$15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

xAI Grok 3 Mini (x-ai/grok-3-mini): OpenRouter gateway-synced model at $0.3/1M input, $0.5/1M output, $0.03/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.3/$0.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Nova Pro V1 (amazon/nova-pro-v1): OpenRouter gateway-synced model at $0.8/1M input, $3.2/1M output, $0.08/1M cached input (300K context window).

Audit: Gateway-synced rate ($0.8/$3.2 per 1M, flat 300K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Nova Lite V1 (amazon/nova-lite-v1): OpenRouter gateway-synced model at $0.06/1M input, $0.24/1M output, $0.006/1M cached input (300K context window).

Audit: Gateway-synced rate ($0.06/$0.24 per 1M, flat 300K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Nova Micro V1 (amazon/nova-micro-v1): OpenRouter gateway-synced model at $0.035/1M input, $0.14/1M output, $0.0035/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.035/$0.14 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Nova Premier V1 (amazon/nova-premier-v1): OpenRouter gateway-synced model at $2.5/1M input, $12.5/1M output, $0.25/1M cached input (1000K context window).

Audit: Gateway-synced rate ($2.5/$12.5 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Titan Text Premier V1 (amazon/titan-text-premier-v1): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Titan Text Express V1 (amazon/titan-text-express-v1): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Amazon Titan Text Lite V1 (amazon/titan-text-lite-v1): OpenRouter gateway-synced model at $0.15/1M input, $0.2/1M output, $0.015/1M cached input (16K context window).

Audit: Gateway-synced rate ($0.15/$0.2 per 1M, flat 16K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Kimi K2 Instruct (moonshotai/kimi-k2-instruct): OpenRouter gateway-synced model at $0.6/1M input, $2.5/1M output, $0.06/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.6/$2.5 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Kimi K1.5 Long Thinking (moonshotai/kimi-k1.5-long-thinking): OpenRouter gateway-synced model at $0.8/1M input, $3.2/1M output, $0.08/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.8/$3.2 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Kimi Vl A3B Thinking (moonshotai/kimi-vl-a3b-thinking): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Kimi Vl A3B Instruct (moonshotai/kimi-vl-a3b-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Moonshot V1 128K (moonshotai/moonshot-v1-128k): OpenRouter gateway-synced model at $0.8/1M input, $2.4/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$2.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Moonshot V1 32K (moonshotai/moonshot-v1-32k): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Moonshot V1 8K (moonshotai/moonshot-v1-8k): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (8K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 8K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Moonshot Moonlight 16B A3B Instruct (moonshotai/moonlight-16b-a3b-instruct): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 Plus (zhipuai/glm-4-plus): OpenRouter gateway-synced model at $0.7/1M input, $2.1/1M output, $0.07/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.7/$2.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 Air 250414 (zhipuai/glm-4-air-250414): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 Long (zhipuai/glm-4-long): OpenRouter gateway-synced model at $0.14/1M input, $0.42/1M output, $0.014/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.14/$0.42 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 Flash 250414 (zhipuai/glm-4-flash-250414): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4V Plus (zhipuai/glm-4v-plus): OpenRouter gateway-synced model at $0.8/1M input, $2.4/1M output, $0.08/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.8/$2.4 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm Z1 32B 0414 (zhipuai/glm-z1-32b-0414): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm Z1 Rumination 32B (zhipuai/glm-z1-rumination-32b): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm Z1 9B 0414 (zhipuai/glm-z1-9b-0414): OpenRouter gateway-synced model at $0.05/1M input, $0.15/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 32B 0414 (zhipuai/glm-4-32b-0414): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 9B 0414 (zhipuai/glm-4-9b-0414): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Codegeex 4 9B (zhipuai/codegeex-4-9b): OpenRouter gateway-synced model at $0.03/1M input, $0.09/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.09 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 0520 (zhipuai/glm-4-0520): OpenRouter gateway-synced model at $0.7/1M input, $2.1/1M output, $0.07/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.7/$2.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 Air (zhipuai/glm-4-air): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Zhipu Glm 4 Flash (zhipuai/glm-4-flash): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Minimax 01 (minimax/minimax-01): OpenRouter gateway-synced model at $0.2/1M input, $1.1/1M output, $0.02/1M cached input (4000K context window).

Audit: Gateway-synced rate ($0.2/$1.1 per 1M, flat 4000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Minimax Vl 01 (minimax/minimax-vl-01): OpenRouter gateway-synced model at $0.25/1M input, $1.25/1M output, $0.025/1M cached input (1000K context window).

Audit: Gateway-synced rate ($0.25/$1.25 per 1M, flat 1000K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Abab6.5S Chat (minimax/abab6.5s-chat): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (245K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 245K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Abab6.5G Chat (minimax/abab6.5g-chat): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Abab6.5T Chat (minimax/abab6.5t-chat): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Abab7 Chat Preview (minimax/abab7-chat-preview): OpenRouter gateway-synced model at $1/1M input, $3/1M output, $0.1/1M cached input (256K context window).

Audit: Gateway-synced rate ($1/$3 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Minimax M1 80K (minimax/minimax-m1-80k): OpenRouter gateway-synced model at $0.3/1M input, $1.2/1M output, $0.03/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.3/$1.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

MiniMax Abab6 Chat (minimax/abab6-chat): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Hermes 3 Llama 3.1 405B (nousresearch/hermes-3-llama-3.1-405b): OpenRouter gateway-synced model at $0.8/1M input, $0.8/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$0.8 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Hermes 3 Llama 3.1 70B (nousresearch/hermes-3-llama-3.1-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.4/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Hermes 3 Llama 3.1 8B (nousresearch/hermes-3-llama-3.1-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Deephermes 3 Llama 3 8B Preview (nousresearch/deephermes-3-llama-3-8b-preview): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Deephermes 3 Mistral 24B Preview (nousresearch/deephermes-3-mistral-24b-preview): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Hermes 2 Pro Llama 3 8B (nousresearch/hermes-2-pro-llama-3-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Nous Capybara 34B (nousresearch/nous-capybara-34b): OpenRouter gateway-synced model at $0.2/1M input, $0.4/1M output, $0.02/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.2/$0.4 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Nous Nous Hermes 2 Mixtral 8X7B Dpo (nousresearch/nous-hermes-2-mixtral-8x7b-dpo): OpenRouter gateway-synced model at $0.24/1M input, $0.24/1M output, $0.024/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.24/$0.24 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AI21 Jamba 1.6 Large (ai21/jamba-1.6-large): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (256K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AI21 Jamba 1.6 Mini (ai21/jamba-1.6-mini): OpenRouter gateway-synced model at $0.2/1M input, $0.4/1M output, $0.02/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.2/$0.4 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AI21 Jamba 1.5 Large (ai21/jamba-1.5-large): OpenRouter gateway-synced model at $2/1M input, $8/1M output, $0.2/1M cached input (256K context window).

Audit: Gateway-synced rate ($2/$8 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AI21 Jamba 1.5 Mini (ai21/jamba-1.5-mini): OpenRouter gateway-synced model at $0.2/1M input, $0.4/1M output, $0.02/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.2/$0.4 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AI21 Jamba Instruct (ai21/jamba-instruct): OpenRouter gateway-synced model at $0.5/1M input, $0.7/1M output, $0.05/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.5/$0.7 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Inflection Inflection 3 Pi (inflection/inflection-3-pi): OpenRouter gateway-synced model at $0.8/1M input, $3.2/1M output, $0.08/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.8/$3.2 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Inflection Inflection 3 Productivity (inflection/inflection-3-productivity): OpenRouter gateway-synced model at $0.8/1M input, $3.2/1M output, $0.08/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.8/$3.2 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Inflection Inflection 2.5 (inflection/inflection-2.5): OpenRouter gateway-synced model at $0.8/1M input, $3.2/1M output, $0.08/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.8/$3.2 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Liquid Lfm 7B (liquid/lfm-7b): OpenRouter gateway-synced model at $0.04/1M input, $0.04/1M output, $0.004/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.04/$0.04 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Liquid Lfm 3B (liquid/lfm-3b): OpenRouter gateway-synced model at $0.02/1M input, $0.02/1M output, $0.002/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.02/$0.02 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Liquid Lfm 40B (liquid/lfm-40b): OpenRouter gateway-synced model at $0.15/1M input, $0.15/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.15 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Liquid Lfm 2.5 24B A2B (liquid/lfm-2.5-24b-a2b): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Olmo 2 32B Instruct (allenai/olmo-2-32b-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.3/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.3 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Olmo 2 13B Instruct (allenai/olmo-2-13b-instruct): OpenRouter gateway-synced model at $0.08/1M input, $0.16/1M output, $0.008/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.08/$0.16 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Olmo 2 7B Instruct (allenai/olmo-2-7b-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Molmo 72B 0924 (allenai/molmo-72b-0924): OpenRouter gateway-synced model at $0.3/1M input, $0.6/1M output, $0.03/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.3/$0.6 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Molmo 7B D 0924 (allenai/molmo-7b-d-0924): OpenRouter gateway-synced model at $0.05/1M input, $0.1/1M output, $0.005/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.05/$0.1 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Tulu 3 405B (allenai/tulu-3-405b): OpenRouter gateway-synced model at $0.8/1M input, $1.6/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$1.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Tulu 3 70B (allenai/tulu-3-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.5/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

AllenAI Tulu 3 8B (allenai/tulu-3-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi Large (01-ai/yi-large): OpenRouter gateway-synced model at $0.8/1M input, $0.8/1M output, $0.08/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.8/$0.8 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi Large Turbo (01-ai/yi-large-turbo): OpenRouter gateway-synced model at $0.18/1M input, $0.18/1M output, $0.018/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.18/$0.18 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi Lightning (01-ai/yi-lightning): OpenRouter gateway-synced model at $0.14/1M input, $0.14/1M output, $0.014/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.14/$0.14 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi Coder 9B Chat (01-ai/yi-coder-9b-chat): OpenRouter gateway-synced model at $0.05/1M input, $0.1/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.1 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi 1.5 34B Chat (01-ai/yi-1.5-34b-chat): OpenRouter gateway-synced model at $0.15/1M input, $0.3/1M output, $0.015/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.15/$0.3 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi 1.5 9B Chat (01-ai/yi-1.5-9b-chat): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

01.AI Yi Vision (01-ai/yi-vision): OpenRouter gateway-synced model at $0.3/1M input, $0.6/1M output, $0.03/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.3/$0.6 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Upstage Solar Pro 2 (upstage/solar-pro-2): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Upstage Solar Pro (upstage/solar-pro): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Upstage Solar Mini (upstage/solar-mini): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Upstage Solar 10.7B Instruct V1 (upstage/solar-10.7b-instruct-v1): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Databricks Dbrx Instruct (databricks/dbrx-instruct): OpenRouter gateway-synced model at $0.6/1M input, $1.8/1M output, $0.06/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.6/$1.8 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Databricks Dolly V2 12B (databricks/dolly-v2-12b): OpenRouter gateway-synced model at $0.1/1M input, $0.2/1M output, $0.01/1M cached input (16K context window).

Audit: Gateway-synced rate ($0.1/$0.2 per 1M, flat 16K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Snowflake Arctic Instruct (snowflake/arctic-instruct): OpenRouter gateway-synced model at $0.24/1M input, $0.72/1M output, $0.024/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.24/$0.72 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Snowflake Llama 3.1 Swiftkv 70B (snowflake/llama-3.1-swiftkv-70b): OpenRouter gateway-synced model at $0.2/1M input, $0.4/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite 3.2 8B Instruct (ibm-granite/granite-3.2-8b-instruct): OpenRouter gateway-synced model at $0.05/1M input, $0.15/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite 3.2 2B Instruct (ibm-granite/granite-3.2-2b-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite 3.1 8B Instruct (ibm-granite/granite-3.1-8b-instruct): OpenRouter gateway-synced model at $0.05/1M input, $0.15/1M output, $0.005/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.05/$0.15 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite 3.1 2B Instruct (ibm-granite/granite-3.1-2b-instruct): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite Code 34B Instruct (ibm-granite/granite-code-34b-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite Code 20B Instruct (ibm-granite/granite-code-20b-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite Code 8B Instruct (ibm-granite/granite-code-8b-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

IBM Granite Granite Vision 3.2 2B (ibm-granite/granite-vision-3.2-2b): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Baichuan Baichuan4 Turbo (baichuan/baichuan4-turbo): OpenRouter gateway-synced model at $0.4/1M input, $1.2/1M output, $0.04/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.4/$1.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Baichuan Baichuan4 Air (baichuan/baichuan4-air): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Baichuan Baichuan4 (baichuan/baichuan4): OpenRouter gateway-synced model at $0.8/1M input, $2.4/1M output, $0.08/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.8/$2.4 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Baichuan Baichuan3 Turbo 128K (baichuan/baichuan3-turbo-128k): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Baichuan Baichuan2 13B Chat (baichuan/baichuan2-13b-chat): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

InternLM Internlm3 8B Instruct (internlm/internlm3-8b-instruct): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

InternLM Internlm2.5 20B Chat (internlm/internlm2.5-20b-chat): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

InternLM Internlm2.5 7B Chat (internlm/internlm2.5-7b-chat): OpenRouter gateway-synced model at $0.03/1M input, $0.09/1M output, $0.003/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.03/$0.09 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

InternLM Internvl2.5 38B (internlm/internvl2.5-38b): OpenRouter gateway-synced model at $0.18/1M input, $0.54/1M output, $0.018/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.18/$0.54 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

InternLM Internvl2.5 8B (internlm/internvl2.5-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.12/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

StepFun Step 2 16K (stepfun/step-2-16k): OpenRouter gateway-synced model at $0.6/1M input, $1.8/1M output, $0.06/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.6/$1.8 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

StepFun Step 2 Mini (stepfun/step-2-mini): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

StepFun Step 1V 8K (stepfun/step-1v-8k): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

StepFun Step 1 256K (stepfun/step-1-256k): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

StepFun Step 1 32K (stepfun/step-1-32k): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

StepFun Step R1 V Mini (stepfun/step-r1-v-mini): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

ByteDance Doubao 1.5 Pro 256K (bytedance/doubao-1.5-pro-256k): OpenRouter gateway-synced model at $0.4/1M input, $1.6/1M output, $0.04/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.4/$1.6 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

ByteDance Doubao 1.5 Pro 32K (bytedance/doubao-1.5-pro-32k): OpenRouter gateway-synced model at $0.11/1M input, $0.28/1M output, $0.011/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.11/$0.28 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

ByteDance Doubao 1.5 Lite 32K (bytedance/doubao-1.5-lite-32k): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

ByteDance Doubao 1.5 Vision Pro 32K (bytedance/doubao-1.5-vision-pro-32k): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

ByteDance Ui Tars 72B Dpo (bytedance/ui-tars-72b-dpo): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

ByteDance Ui Tars 7B Dpo (bytedance/ui-tars-7b-dpo): OpenRouter gateway-synced model at $0.05/1M input, $0.15/1M output, $0.005/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.05/$0.15 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Tencent Hunyuan Turbos 2025 (tencent/hunyuan-turbos-2025): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Tencent Hunyuan Pro (tencent/hunyuan-pro): OpenRouter gateway-synced model at $0.4/1M input, $1.2/1M output, $0.04/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.4/$1.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Tencent Hunyuan Standard 256K (tencent/hunyuan-standard-256k): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (256K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 256K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Tencent Hunyuan Lite (tencent/hunyuan-lite): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Tencent Hunyuan Code (tencent/hunyuan-code): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Tencent Hunyuan Vision (tencent/hunyuan-vision): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

SenseTime Sensechat 5.5 (sensenova/sensechat-5.5): OpenRouter gateway-synced model at $0.35/1M input, $1.05/1M output, $0.035/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.35/$1.05 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

SenseTime Sensechat 5 128K (sensenova/sensechat-5-128k): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

SenseTime Sensechat Turbo (sensenova/sensechat-turbo): OpenRouter gateway-synced model at $0.06/1M input, $0.18/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.18 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

SenseTime Sensechat Vision (sensenova/sensechat-vision): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

iFlytek Spark 4.0 Ultra (iflytek/spark-4.0-ultra): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

iFlytek Spark Max 32K (iflytek/spark-max-32k): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

iFlytek Spark Pro 128K (iflytek/spark-pro-128k): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

iFlytek Spark Lite (iflytek/spark-lite): OpenRouter gateway-synced model at $0.02/1M input, $0.06/1M output, $0.002/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.02/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Reka AI Reka Core (rekaai/reka-core): OpenRouter gateway-synced model at $1/1M input, $3/1M output, $0.1/1M cached input (128K context window).

Audit: Gateway-synced rate ($1/$3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Reka AI Reka Flash 3 (rekaai/reka-flash-3): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Reka AI Reka Flash (rekaai/reka-flash): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Reka AI Reka Edge (rekaai/reka-edge): OpenRouter gateway-synced model at $0.08/1M input, $0.24/1M output, $0.008/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.08/$0.24 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Writer Palmyra X 004 (writer/palmyra-x-004): OpenRouter gateway-synced model at $1.5/1M input, $4.5/1M output, $0.15/1M cached input (128K context window).

Audit: Gateway-synced rate ($1.5/$4.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Writer Palmyra Fin 70B 32K (writer/palmyra-fin-70b-32k): OpenRouter gateway-synced model at $0.6/1M input, $1.8/1M output, $0.06/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.6/$1.8 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Writer Palmyra Med 70B 32K (writer/palmyra-med-70b-32k): OpenRouter gateway-synced model at $0.6/1M input, $1.8/1M output, $0.06/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.6/$1.8 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Writer Palmyra Creative (writer/palmyra-creative): OpenRouter gateway-synced model at $0.5/1M input, $1.5/1M output, $0.05/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.5/$1.5 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Essential AI Rnj 1 Instruct (essentialai/rnj-1-instruct): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Essential AI Rnj 1 Base (essentialai/rnj-1-base): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Caller Large (arcee-ai/caller-large): OpenRouter gateway-synced model at $0.3/1M input, $0.9/1M output, $0.03/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.3/$0.9 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Virtuoso Large (arcee-ai/virtuoso-large): OpenRouter gateway-synced model at $0.35/1M input, $1.05/1M output, $0.035/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.35/$1.05 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Virtuoso Medium V2 (arcee-ai/virtuoso-medium-v2): OpenRouter gateway-synced model at $0.18/1M input, $0.54/1M output, $0.018/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.18/$0.54 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Coder Large (arcee-ai/coder-large): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Maestro Reasoning (arcee-ai/maestro-reasoning): OpenRouter gateway-synced model at $0.4/1M input, $1.2/1M output, $0.04/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.4/$1.2 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Spotlight (arcee-ai/spotlight): OpenRouter gateway-synced model at $0.15/1M input, $0.45/1M output, $0.015/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.15/$0.45 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Arcee AI Blitz 70B (arcee-ai/blitz-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Featherless Qwerky 72B (featherless/qwerky-72b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Featherless Qwerky 32B (featherless/qwerky-32b): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Prime Intellect Intellect 2 (primeintellect/intellect-2): OpenRouter gateway-synced model at $0.2/1M input, $0.6/1M output, $0.02/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.2/$0.6 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Prime Intellect Intellect 1 Instruct (primeintellect/intellect-1-instruct): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenChat Openchat 3.6 8B (openchat/openchat-3.6-8b): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

OpenChat Openchat 3.5 0106 (openchat/openchat-3.5-0106): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Teknium Openhermes 2.5 Mistral 7B (teknium/openhermes-2.5-mistral-7b): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Teknium Openhermes 2 Yi 34B (teknium/openhermes-2-yi-34b): OpenRouter gateway-synced model at $0.15/1M input, $0.3/1M output, $0.015/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.15/$0.3 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin3.0 R1 Mistral 24B (cognitivecomputations/dolphin3.0-r1-mistral-24b): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin3.0 Mistral 24B (cognitivecomputations/dolphin3.0-mistral-24b): OpenRouter gateway-synced model at $0.1/1M input, $0.3/1M output, $0.01/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.1/$0.3 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin 2.9.2 Qwen2 72B (cognitivecomputations/dolphin-2.9.2-qwen2-72b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin 2.9 Llama3 70B (cognitivecomputations/dolphin-2.9-llama3-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin 2.9 Llama3 8B (cognitivecomputations/dolphin-2.9-llama3-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin Mixtral 8X22B (cognitivecomputations/dolphin-mixtral-8x22b): OpenRouter gateway-synced model at $0.5/1M input, $0.5/1M output, $0.05/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.5/$0.5 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Dolphin Dolphin Mixtral 8X7B (cognitivecomputations/dolphin-mixtral-8x7b): OpenRouter gateway-synced model at $0.24/1M input, $0.24/1M output, $0.024/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.24/$0.24 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Gryphe Mythomax L2 13B (gryphe/mythomax-l2-13b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Gryphe Mythomist 7B (gryphe/mythomist-7b): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Undi95 Toppy M 7B (undi95/toppy-m-7b): OpenRouter gateway-synced model at $0.03/1M input, $0.06/1M output, $0.003/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.03/$0.06 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Undi95 Remm Slerp L2 13B (undi95/remm-slerp-l2-13b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Sao10K L3.3 Euryale 70B (sao10k/l3.3-euryale-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.5/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Sao10K L3.1 Euryale 70B (sao10k/l3.1-euryale-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.5/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Sao10K L3 Lunaris 8B (sao10k/l3-lunaris-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Sao10K Fimbulvetr 11B V2 (sao10k/fimbulvetr-11b-v2): OpenRouter gateway-synced model at $0.05/1M input, $0.1/1M output, $0.005/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.05/$0.1 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NeverSleep Llama 3.1 Lumimaid 70B (neversleep/llama-3.1-lumimaid-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.5/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.5 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NeverSleep Llama 3.1 Lumimaid 8B (neversleep/llama-3.1-lumimaid-8b): OpenRouter gateway-synced model at $0.04/1M input, $0.08/1M output, $0.004/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.04/$0.08 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

NeverSleep Noromaid 20B (neversleep/noromaid-20b): OpenRouter gateway-synced model at $0.12/1M input, $0.24/1M output, $0.012/1M cached input (32K context window).

Audit: Gateway-synced rate ($0.12/$0.24 per 1M, flat 32K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

TheDrummer Anubis Pro 105B V1 (thedrummer/anubis-pro-105b-v1): OpenRouter gateway-synced model at $0.45/1M input, $0.9/1M output, $0.045/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.45/$0.9 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

TheDrummer Rocinante 12B (thedrummer/rocinante-12b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

TheDrummer Unslopnemo 12B (thedrummer/unslopnemo-12b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

TheDrummer Cydonia 24B V2 (thedrummer/cydonia-24b-v2): OpenRouter gateway-synced model at $0.12/1M input, $0.36/1M output, $0.012/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.12/$0.36 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

TheDrummer Skyfall 36B V2 (thedrummer/skyfall-36b-v2): OpenRouter gateway-synced model at $0.18/1M input, $0.54/1M output, $0.018/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.18/$0.54 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthracite Magnum V4 72B (anthracite-org/magnum-v4-72b): OpenRouter gateway-synced model at $0.28/1M input, $0.56/1M output, $0.028/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.28/$0.56 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthracite Magnum V2 72B (anthracite-org/magnum-v2-72b): OpenRouter gateway-synced model at $0.28/1M input, $0.56/1M output, $0.028/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.28/$0.56 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Anthracite Magnum V4 12B (anthracite-org/magnum-v4-12b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

EVA Eva Qwen 2.5 72B (eva-unit-01/eva-qwen-2.5-72b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

EVA Eva Llama 3.33 70B (eva-unit-01/eva-llama-3.33-70b): OpenRouter gateway-synced model at $0.25/1M input, $0.75/1M output, $0.025/1M cached input (128K context window).

Audit: Gateway-synced rate ($0.25/$0.75 per 1M, flat 128K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.

Infermatic Mn Inferor 12B (infermatic/mn-inferor-12b): OpenRouter gateway-synced model at $0.06/1M input, $0.12/1M output, $0.006/1M cached input (64K context window).

Audit: Gateway-synced rate ($0.06/$0.12 per 1M, flat 64K window). Verify upstream provider cache TTL and regional routing before high-volume batch runs.