Best inclusionAI: Ling 3.1 Flash Alternatives & Competitors in 2026

OpenAI October 2026 flagship reasoning & coding model delivering near-Astra intelligence at 1/5th the cost.

Audit: Context Cliff Alert: Prompts exceeding 272K tokens double in price from $2/$10 to $4/$15 per 1M tokens.

OpenAI most powerful computer-use and autonomous multi-agent flagship model built for zero-failure enterprise tasks.

Audit: Billed at $10/$50 (<272K) and jumps to $20/$75 (>272K). Reserve strictly for hard computer-use orchestration.

OpenAI ultra-affordable reasoning and logic model with 1M+ token context window for high-volume production pipelines.

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

Ranked #1 on Artificial Analysis Intelligence Index (Score 58). Cuts Opus 5 pricing by 20% and features 0.05x ($0.20/1M) cache reads.

Audit: Adaptive thinking is always on; high effort generates ~119K thinking tokens/task. Fast mode costs $8/$40; inference_geo:"us" adds +10%.

Anthropic specialized frontier model for demanding scientific reasoning, OfficeQA leadership, and long-horizon agentic work.

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

Released Sept 28, 2026 at half of Opus 5.5 price with 0.05x ($0.10/1M) cache reads for high-speed SWE agents.

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

Ultra-fast classification, extraction, and routing model with $0.01/1M cache reads under 100K prompt tokens.

Audit: Severe Context Cliff: Prompts over 100,000 tokens jump 500% from $0.10/$0.50 to $0.50/$2.50 per 1M tokens!

Google DeepMind Oct 2026 frontier release featuring a 1,000,000 (1M) output token limit, 95% cache discount ($0.10/1M), and #1 Vals Index & DeepSWE (77.9%).

Audit: Introductory $2/$10 API rate is locked until Nov 30, 2026, after which standard uncached rates rise to $4/$20.

High-frequency multimodal, TTS, and live streaming model optimized for low-latency production workloads.

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

1.6-Trillion parameter (49B active) MoE architecture with Fine-Grained Sparse Attention and $0.07/1M disk KV cache hits.

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

284B parameter (13B active) high-speed sparse-attention model with thinking integrated directly into tool calls.

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

Balanced enterprise general-purpose model in the GPT-5.6 family with 1M context window.

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

Specialized offensive/defensive cybersecurity and zero-day vulnerability auditing model.

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

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

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

Ultra-fast classification, tagging, and high-volume FAQ model replacing legacy GPT-4o mini.

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

Dedicated agentic software engineering model tuned for multi-hour terminal and IDE sessions.

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

xAI October 2026 frontier reasoning model with live X/Web grounding and sub-200ms latency.

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

Meta open-weight multimodal MoE model supporting 10M+ extended context on dedicated clusters.

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

Open-weight reinforcement-learning reasoning model for formal math, finance, and theorem synthesis.

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

Single API routing across 400+ live models (GPT-6.1 Sol, Opus 5.5, Gemini 4 Argon) with automatic price arbitrage.

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

This model always redirects to the latest model in the Pareto family.

Audit: Auto-discovered via live global telemetry registry.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Audit: Auto-discovered via live global telemetry registry.

LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that ca

Audit: Auto-discovered via live global telemetry registry.

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Goo

Audit: Auto-discovered via live global telemetry registry.

Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Goo

Audit: Auto-discovered via live global telemetry registry.

Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source,

Audit: Auto-discovered via live global telemetry registry.

Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `prov

Audit: Auto-discovered via live global telemetry registry.

Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and retu

Audit: Auto-discovered via live global telemetry registry.

Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in softwar

Audit: Auto-discovered via live global telemetry registry.

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger

Audit: Auto-discovered via live global telemetry registry.

Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger

Audit: Auto-discovered via live global telemetry registry.

Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product reconte

Audit: Auto-discovered via live global telemetry registry.

Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with u

Audit: Auto-discovered via live global telemetry registry.

Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

Audit: Auto-discovered via live global telemetry registry.

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on c

Audit: Auto-discovered via live global telemetry registry.

GPT-6.1 Sol Pro is the same underlying model as [GPT-6.1 Sol](https://openrouter.ai/openai/gpt-6.1-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on c

Audit: Auto-discovered via live global telemetry registry.

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy pro

Audit: Auto-discovered via live global telemetry registry.

GPT-6.1 Sol is an upgrade to GPT-6 Sol from OpenAI, positioned below the flagship GPT-6 Astra in the GPT-6 series. It is suited for agentic coding, computer use, document-heavy pro

Audit: Auto-discovered via live global telemetry registry.

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fix

Audit: Auto-discovered via live global telemetry registry.

Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fix

Audit: Auto-discovered via live global telemetry registry.

Perceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optional structured annota

Audit: Auto-discovered via live global telemetry registry.

Ember-1 is a specialized reasoning model from Fireworks Research, built on [Kimi K3](https://openrouter.ai/moonshotai/kimi-k3). It is designed to make every token go further: it pr

Audit: Auto-discovered via live global telemetry registry.

GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It support

Audit: Auto-discovered via live global telemetry registry.

Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

Audit: Auto-discovered via live global telemetry registry.

Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses...

Audit: Auto-discovered via live global telemetry registry.

Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple special

Audit: Auto-discovered via live global telemetry registry.

Solar Mini 4 is Upstage's compact, cost-efficient language model, a 35B-parameter mixture-of-experts with 3B active parameters and a 524K context window. It is built for agentic us

Audit: Auto-discovered via live global telemetry registry.

Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool s

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on comp

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Luna Pro is the same underlying model as [GPT-6 Luna](https://openrouter.ai/openai/gpt-6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses on comp

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classi

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Luna is the fast, cost-efficient model in OpenAI's GPT-6 series, positioned below GPT-6 Sol. It is suited for high-volume and latency-sensitive workloads such as chat, classi

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Sol Pro is the same underlying model as [GPT-6 Sol](https://openrouter.ai/openai/gpt-6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding pr

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Sol is the cost-efficient high-end model in OpenAI's GPT-6 series, positioned below the flagship GPT-6 Astra and above the fast GPT-6 Luna tier. It is suited for demanding pr

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step chan

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step chan

Audit: Auto-discovered via live global telemetry registry.

MiMo-V2.6-Pro-UltraSpeed is the fast speed edition of Xiaomi's flagship foundation model, MiMo-V2.6-Pro. Built from the same 1T MiMo-V2.6-Pro checkpoint, it matches the original mo

Audit: Auto-discovered via live global telemetry registry.

MiMo-V2.6-Flash is an open-source foundation model developed by Xiaomi. Built on a Mixture-of-Experts architecture with 309B total parameters and 15B activated per token, it employ

Audit: Auto-discovered via live global telemetry registry.

MiMo-V2.6-Pro is the flagship foundation model developed by Xiaomi. Built at a scale of over 1T parameters, it is designed to push the ceiling of capability for the most demanding.

Audit: Auto-discovered via live global telemetry registry.

Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, veri

Audit: Auto-discovered via live global telemetry registry.

Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for aud

Audit: Auto-discovered via live global telemetry registry.

Bonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding with a 262K-token cont

Audit: Auto-discovered via live global telemetry registry.

GLM-5.3-FlashX is the high-speed variant of Z.ai's GLM-5.3-Flash, a native multimodal model delivering inference speeds of up to 200 tokens/s. Built on the same hybrid sparse and l

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the DeepSeek Pro family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the DeepSeek Flash family.

Audit: Auto-discovered via live global telemetry registry.

Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must

Audit: Auto-discovered via live global telemetry registry.

Schematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. Extraction instruction

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the GPT Astra family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the GPT Sol family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the GPT Terra family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the GPT Luna family.

Audit: Auto-discovered via live global telemetry registry.

Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language mode

Audit: Auto-discovered via live global telemetry registry.

Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model train

Audit: Auto-discovered via live global telemetry registry.

Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception an

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters o

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters o

Audit: Auto-discovered via live global telemetry registry.

Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces and refines multiple t

Audit: Auto-discovered via live global telemetry registry.

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, imple

Audit: Auto-discovered via live global telemetry registry.

Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, imple

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creatio

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Astra is OpenAI's flagship model for demanding end-to-end work. It is suited for advanced analysis, software engineering, deep research, scientific work, and document creatio

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on c

Audit: Auto-discovered via live global telemetry registry.

GPT-6 Astra Pro is the same underlying model as [GPT-6 Astra](https://openrouter.ai/openai/gpt-6-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on c

Audit: Auto-discovered via live global telemetry registry.

Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. It is a 2.4-trillion-parameter mixture-of-experts model that accepts text, image, and video input a

Audit: Auto-discovered via live global telemetry registry.

Muse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic, multi-agent, and codi

Audit: Auto-discovered via live global telemetry registry.

Muse Spark 1.3 is a multimodal reasoning model from Meta for long-running agentic, multi-agent, and coding workflows. It is designed to keep track of information across extended ta

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.

Audit: Auto-discovered via live global telemetry registry.

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, fro

Audit: Auto-discovered via live global telemetry registry.

Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, fro

Audit: Auto-discovered via live global telemetry registry.

Granite 4.2 8B is a dense reasoning model from IBM. It is suited for mathematics, code generation, multilingual dialogue, and agentic workflows that need multi-step reasoning. It s

Audit: Auto-discovered via live global telemetry registry.

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and pro

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the GLM Flash family.

Audit: Auto-discovered via live global telemetry registry.

Qwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase analysis, desktop int

Audit: Auto-discovered via live global telemetry registry.

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains

Audit: Auto-discovered via live global telemetry registry.

GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains

Audit: Auto-discovered via live global telemetry registry.

Muse Spark 1.2 contributor tier is a reasoning model from Meta designed for developers who want to start building at an even lower cost. It’s meaningfully cheaper than Muse Spark..

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of [DeepSeek V4 Flash 0731](https://openrouter.ai/deepseek/deepseek-v4-flash-0731) from DeepSeek, adding imag

Audit: Auto-discovered via live global telemetry registry.

Hy-MT2-1.8B is a compact 1.8B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for struc

Audit: Auto-discovered via live global telemetry registry.

Hy-MT2-30B-A3B is Tencent's flagship translation model in the Hy-MT2 family. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest GLM model from Z.ai.

Audit: Auto-discovered via live global telemetry registry.

Hy-MT2-7B is a 7B-parameter translation model from Tencent. It supports 33 language pairs and five Chinese dialect and minority-language pairs, with workflows for structured, delim

Audit: Auto-discovered via live global telemetry registry.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context w

Audit: Auto-discovered via live global telemetry registry.

GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. It supports text input and output with a 1M-token context w

Audit: Auto-discovered via live global telemetry registry.

Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks

Audit: Auto-discovered via live global telemetry registry.

Dots3-Note Preview is an open-weight mixture-of-experts model from Dots Studio, with 16B active parameters out of 280B total. It is the lightest model in the Dots 3 family and is..

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performanc

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. It is designed for tasks that require responsive performanc

Audit: Auto-discovered via live global telemetry registry.

Seed 2.1 Turbo is a multimodal model from ByteDance Seed for coding and long-horizon agent workflows. It is suited for end-to-end software delivery, multi-step task execution, and

Audit: Auto-discovered via live global telemetry registry.

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out

Audit: Auto-discovered via live global telemetry registry.

Seed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-agent workflows in tool

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.

Audit: Auto-discovered via live global telemetry registry.

Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).

Audit: Auto-discovered via live global telemetry registry.

LFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises against using it for ag

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and sp

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and sp

Audit: Auto-discovered via live global telemetry registry.

Sakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts. It is suited for Ja

Audit: Auto-discovered via live global telemetry registry.

Solar Pro 4 is Upstage's cost-efficient large language model, featuring a 524K context window. It is built for long-horizon tasks and agentic workflows, with strong capabilities in

Audit: Auto-discovered via live global telemetry registry.

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware. It i

Audit: Auto-discovered via live global telemetry registry.

Muse Spark 1.2 is a reasoning model from Meta, designed for complex agentic tasks. It accepts text, images, video, and PDF documents, returns text, and offers a 1M-token context wi

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the DeepSeek V4 Flash family.

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoni

Audit: Auto-discovered via live global telemetry registry.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more

Audit: Auto-discovered via live global telemetry registry.

Inkling Small is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 12B active parameters out of 276B total. It is positioned as the smaller, more

Audit: Auto-discovered via live global telemetry registry.

Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recog

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and

Audit: Auto-discovered via live global telemetry registry.

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and pr

Audit: Auto-discovered via live global telemetry registry.

Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Term

Audit: Auto-discovered via live global telemetry registry.

Laguna S 2.1 is the latest coding agent model from [Poolside](<https://poolside.ai/>). Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Term

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessar

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.6 Flash is a high-efficiency model from Google for coding, agentic workflows, and web and app development. It is designed to produce polished outputs with fewer unnecessar

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent w

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent w

Audit: Auto-discovered via live global telemetry registry.

LongCat 2.0 is a sparse mixture-of-experts language model from Meituan, with 48B active parameters out of 1.6T total. It is suited for coding, repository-level changes, long-horizo

Audit: Auto-discovered via live global telemetry registry.

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning

Audit: Auto-discovered via live global telemetry registry.

Inkling is an open-weight multimodal mixture-of-experts model from Thinking Machines Lab, with 41B active parameters out of 975B total. It is designed for general-purpose reasoning

Audit: Auto-discovered via live global telemetry registry.

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is par

Audit: Auto-discovered via live global telemetry registry.

Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is par

Audit: Auto-discovered via live global telemetry registry.

Muse Spark 1.1 is a multimodal reasoning model from Meta, built for agentic tasks. It accepts text, images, video, and PDF documents and returns text, with a 1M-token context windo

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses o

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Luna Pro is the same underlying model as [GPT-5.6 Luna](https://openrouter.ai/openai/gpt-5.6-luna), served with `reasoning.mode` set to `pro` for higher-quality responses o

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series. It is suited for high-volume, latency-sensitive tasks such as chat, classification, and lightweight agentic

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality response

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Terra Pro is the same underlying model as [GPT-5.6 Terra](https://openrouter.ai/openai/gpt-5.6-terra), served with `reasoning.mode` set to `pro` for higher-quality response

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Terra is a balanced model in OpenAI's GPT-5.6 series, positioned between the flagship Sol tier and the cost-efficient Luna tier. It is suited for everyday coding, reasoning

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on c

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Sol Pro is the same underlying model as [GPT-5.6 Sol](https://openrouter.ai/openai/gpt-5.6-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on c

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and mult

Audit: Auto-discovered via live global telemetry registry.

GPT-5.6 Sol is the flagship model in OpenAI's GPT-5.6 series. It is suited for complex reasoning, coding, and agentic workflows, and is particularly strong at command-line and mult

Audit: Auto-discovered via live global telemetry registry.

Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest Grok model from xAI.

Audit: Auto-discovered via live global telemetry registry.

Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multip

Audit: Auto-discovered via live global telemetry registry.

Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple special

Audit: Auto-discovered via live global telemetry registry.

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It

Audit: Auto-discovered via live global telemetry registry.

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026

Audit: Auto-discovered via live global telemetry registry.

Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from [Poolside](https://poolside.ai/) and a step forward from their Laguna XS.2 model (released in April 2026

Audit: Auto-discovered via live global telemetry registry.

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reaso

Audit: Auto-discovered via live global telemetry registry.

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reaso

Audit: Auto-discovered via live global telemetry registry.

Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) is Google's fastest, most cost-efficient Gemini image model, built for high-velocity developer pipelines and rapid-fire visual expl

Audit: Auto-discovered via live global telemetry registry.

Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model t

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Flash Image, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed. It combi

Audit: Auto-discovered via live global telemetry registry.

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reas

Audit: Auto-discovered via live global telemetry registry.

North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized

Audit: Auto-discovered via live global telemetry registry.

GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level

Audit: Auto-discovered via live global telemetry registry.

MoonshotAI: Kimi K2.7 Code is a coding-focused model in Moonshot AI's Kimi K2 family, built to complete end-to-end programming tasks reliably over long contexts. It uses a native m

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Claude Fable family.

Audit: Auto-discovered via live global telemetry registry.

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning sup

Audit: Auto-discovered via live global telemetry registry.

Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning sup

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses fr

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3.5 Content Safety is a compact 4B-parameter multimodal guardrail model from NVIDIA, fine-tuned from Google Gemma-3-4B. It moderates both inputs to and responses fr

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba m

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba m

Audit: Auto-discovered via live global telemetry registry.

Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensiv

Audit: Auto-discovered via live global telemetry registry.

MiniMax-M3 is a multimodal foundation model from MiniMax. It supports text, image, and video inputs with text output, a 1M-token context window, and is suited for long-horizon agen

Audit: Auto-discovered via live global telemetry registry.

Step 3.7 Flash is StepFun's latest high-efficiency multimodal Mixture-of-Experts model. It pairs a 196B-parameter language backbone with a vision encoder for native image and video

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M

Audit: Auto-discovered via live global telemetry registry.

Qwen3.7-Max is the flagship model in Alibaba's Qwen3.7 series. It supports text input and output and is designed for agent-centric workloads, with particular strengths in coding, o

Audit: Auto-discovered via live global telemetry registry.

Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficie

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficie

Audit: Auto-discovered via live global telemetry registry.

Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired with natural language q

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and i

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Flash Lite is Google’s GA high-efficiency multimodal model optimized for low-latency, high-volume workloads. It supports text, image, video, audio, and PDF inputs, and i

Audit: Auto-discovered via live global telemetry registry.

GPT Chat Latest points to OpenAI's stable API alias `chat-latest` that always resolves to the latest Instant chat model used in ChatGPT. As OpenAI rolls out new Instant model updat

Audit: Auto-discovered via live global telemetry registry.

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications r

Audit: Auto-discovered via live global telemetry registry.

Grok 4.3 is a reasoning model from SpaceXAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications r

Audit: Auto-discovered via live global telemetry registry.

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, a

Audit: Auto-discovered via live global telemetry registry.

Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, a

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron™ 3 Nano Omni is a 30B-A3B open multimodal model designed to function as a perception and context sub-agent in enterprise agent systems. It accepts text, image, vide

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Claude Haiku family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the GPT Mini family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Gemini Pro family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Kimi family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Gemini Flash family.

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Claude Sonnet family.

Audit: Auto-discovered via live global telemetry registry.

Qwen3.5 Plus (April 2026) is a large-scale multimodal language model from Alibaba. It accepts text, image, and video input and produces text output, with a 1M token context window.

Audit: Auto-discovered via live global telemetry registry.

Qwen3.6 Flash is a fast, efficient language model from Alibaba's Qwen 3.6 series. It supports text, image, and video input with a 1M token context window. Tiered pricing kicks in..

Audit: Auto-discovered via live global telemetry registry.

Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of

Audit: Auto-discovered via live global telemetry registry.

Qwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities — accepting text, image

Audit: Auto-discovered via live global telemetry registry.

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K

Audit: Auto-discovered via live global telemetry registry.

GPT-5.5 Pro is OpenAI’s high-capability model optimized for deep reasoning and accuracy on complex, high-stakes workloads. It features a 1M+ token context window (922K input, 128K

Audit: Auto-discovered via live global telemetry registry.

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on ha

Audit: Auto-discovered via live global telemetry registry.

GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved token efficiency on ha

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designe

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. I

Audit: Auto-discovered via live global telemetry registry.

Hy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning levels across disabled,

Audit: Auto-discovered via live global telemetry registry.

MiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks, with top rankings on

Audit: Auto-discovered via live global telemetry registry.

MiMo-V2.5 is a native omnimodal model by Xiaomi. It delivers Pro-level agentic performance at roughly half the inference cost, while surpassing MiMo-V2-Omni in multimodal perceptio

Audit: Auto-discovered via live global telemetry registry.

[GPT-5.4](https://openrouter.ai/openai/gpt-5.4) Image 2 combines OpenAI's GPT-5.4 model with state-of-the-art image generation capabilities from GPT Image 2. It enables rich multim

Audit: Auto-discovered via live global telemetry registry.

This model always redirects to the latest model in the Claude Opus family.

Audit: Auto-discovered via live global telemetry registry.

Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. It handles complex end

Audit: Auto-discovered via live global telemetry registry.

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stron

Audit: Auto-discovered via live global telemetry registry.

Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stron

Audit: Auto-discovered via live global telemetry registry.

GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around minute-level interaction

Audit: Auto-discovered via live global telemetry registry.

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — deli

Audit: Auto-discovered via live global telemetry registry.

Gemma 4 26B A4B IT is an instruction-tuned Mixture-of-Experts (MoE) model from Google DeepMind. Despite 25.2B total parameters, only 3.8B activate per token during inference — deli

Audit: Auto-discovered via live global telemetry registry.

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking

Audit: Auto-discovered via live global telemetry registry.

Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking

Audit: Auto-discovered via live global telemetry registry.

Qwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance infe

Audit: Auto-discovered via live global telemetry registry.

GLM-5V-Turbo is Z.ai’s first native multimodal agent foundation model, built for vision-based coding and agent-driven tasks. It natively handles image, video, and text inputs, exce

Audit: Auto-discovered via live global telemetry registry.

Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launc

Audit: Auto-discovered via live global telemetry registry.

Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordina

Audit: Auto-discovered via live global telemetry registry.

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict

Audit: Auto-discovered via live global telemetry registry.

Full-length songs are priced at $0.08 per song. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate high-quality

Audit: Auto-discovered via live global telemetry registry.

30 second duration clips are priced at $0.04 per clip. Lyria 3 is Google's family of music generation models, available through the Gemini API. With Lyria 3, you can generate...

Audit: Auto-discovered via live global telemetry registry.

Reka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimized specifically to del

Audit: Auto-discovered via live global telemetry registry.

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participate in its own evoluti

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 nano is the most lightweight and cost-efficient variant of the GPT-5.4 family, optimized for speed-critical and high-volume tasks. It supports text and image inputs and is

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong perfor

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 mini brings the core capabilities of GPT-5.4 to a faster, more efficient model optimized for high-throughput workloads. It supports text and image inputs with strong perfor

Audit: Auto-discovered via live global telemetry registry.

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoni

Audit: Auto-discovered via live global telemetry registry.

Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoni

Audit: Auto-discovered via live global telemetry registry.

GLM-5 Turbo is a new model from Z.ai designed for fast inference and strong performance in agent-driven environments such as OpenClaw scenarios. It is deeply optimized for real-wor

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. B

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-agent applications. B

Audit: Auto-discovered via live global telemetry registry.

Seed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latency, making it a practi

Audit: Auto-discovered via live global telemetry registry.

Qwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-parameter architectur

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 Pro is OpenAI's most advanced model, building on GPT-5.4's unified architecture with enhanced reasoning capabilities for complex, high-stakes tasks. It features a 1M+ token

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for.

Audit: Auto-discovered via live global telemetry registry.

GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system. It features a 1M+ token context window (922K input, 128K output) with support for.

Audit: Auto-discovered via live global telemetry registry.

Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple token

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases. It outperforms Gemini 2.5 Flash Lite on overall quality and approaches Gemini 2

Audit: Auto-discovered via live global telemetry registry.

Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance compar

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Flash Image Preview, a.k.a. "Nano Banana 2," is Google’s latest state of the art image generation and editing model, delivering Pro-level visual quality at Flash speed.

Audit: Auto-discovered via live global telemetry registry.

The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model,

Audit: Auto-discovered via live global telemetry registry.

The Qwen3.5 27B native vision-language Dense model incorporates a linear attention mechanism, delivering fast response times while balancing inference speed and performance. Its ov

Audit: Auto-discovered via live global telemetry registry.

The Qwen3.5 122B-A10B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving

Audit: Auto-discovered via live global telemetry registry.

The Qwen3.5 native vision-language Flash models are built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving hi

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-part

Audit: Auto-discovered via live global telemetry registry.

GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional k

Audit: Auto-discovered via live global telemetry registry.

Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, ma

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage acro

Audit: Auto-discovered via live global telemetry registry.

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage acro

Audit: Auto-discovered via live global telemetry registry.

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex c

Audit: Auto-discovered via live global telemetry registry.

Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex c

Audit: Auto-discovered via live global telemetry registry.

The Qwen3.5 native vision-language series Plus models are built on a hybrid architecture that integrates linear attention mechanisms with sparse mixture-of-experts models, achievin

Audit: Auto-discovered via live global telemetry registry.

The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, ach

Audit: Auto-discovered via live global telemetry registry.

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity. Trained in a diverse range of complex real-world digital working environments, M2.5 builds upon th

Audit: Auto-discovered via live global telemetry registry.

GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows. Built for expert developers, it delivers production-gr

Audit: Auto-discovered via live global telemetry registry.

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, maki

Audit: Auto-discovered via live global telemetry registry.

Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, maki

Audit: Auto-discovered via live global telemetry registry.

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only

Audit: Auto-discovered via live global telemetry registry.

The simplest way to get free inference. openrouter/free is a router that selects free models at random from the models available on OpenRouter. The router smartly filters for model

Audit: Auto-discovered via live global telemetry registry.

Step 3.5 Flash is StepFun's most capable open-source foundation model. Built on a sparse Mixture of Experts (MoE) architecture, it selectively activates only 11B of its 196B parame

Audit: Auto-discovered via live global telemetry registry.

Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm. Built on Kimi K2 with continued p

Audit: Auto-discovered via live global telemetry registry.

Solar Pro 3 is Upstage's powerful Mixture-of-Experts (MoE) language model. With 102B total parameters and 12B active parameters per forward pass, it delivers exceptional performanc

Audit: Auto-discovered via live global telemetry registry.

MiniMax M2-her is a dialogue-first large language model built for immersive roleplay, character-driven chat, and expressive multi-turn conversations. Designed to stay consistent in

Audit: Auto-discovered via live global telemetry registry.

Palmyra X5 is Writer's most advanced model, purpose-built for building and scaling AI agents across the enterprise. It delivers industry-leading speed and efficiency on context win

Audit: Auto-discovered via live global telemetry registry.

The gpt-audio model is OpenAI's first generally available audio model. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice con

Audit: Auto-discovered via live global telemetry registry.

A cost-efficient version of GPT Audio. The new snapshot features an upgraded decoder for more natural sounding voices and maintains better voice consistency. Input is priced at $0.

Audit: Auto-discovered via live global telemetry registry.

As a 30B-class SOTA model, GLM-4.7-Flash offers a new option that balances performance and efficiency. It is further optimized for agentic coding use cases, strengthening coding ca

Audit: Auto-discovered via live global telemetry registry.

GPT-5.2-Codex is an upgraded version of GPT-5.1-Codex optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, in

Audit: Auto-discovered via live global telemetry registry.

Seed 1.6 Flash is an ultra-fast multimodal deep thinking model by ByteDance Seed, supporting both text and visual understanding. It features a 256k context window and can generate

Audit: Auto-discovered via live global telemetry registry.

Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.

Audit: Auto-discovered via live global telemetry registry.

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated par

Audit: Auto-discovered via live global telemetry registry.

GLM-4.7 is Z.ai’s latest flagship model, featuring upgrades in two key areas: enhanced programming capabilities and more stable multi-step reasoning/execution. It demonstrates sign

Audit: Auto-discovered via live global telemetry registry.

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and t

Audit: Auto-discovered via live global telemetry registry.

Gemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance. It delivers near Pro level reasoning and t

Audit: Auto-discovered via live global telemetry registry.

NVIDIA Nemotron 3 Nano 30B A3B is a small language MoE model with highest compute efficiency and accuracy for developers to build specialized agentic AI systems. The model is fully

Audit: Auto-discovered via live global telemetry registry.

GPT-5.2 Chat (AKA Instant) is the fast, lightweight member of the 5.2 family, optimized for low-latency chat while retaining strong general intelligence. It uses adaptive reasoning

Audit: Auto-discovered via live global telemetry registry.

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that requi

Audit: Auto-discovered via live global telemetry registry.

GPT-5.2 Pro is OpenAI’s most advanced model, offering major improvements in agentic coding and long context performance over GPT-5 Pro. It is optimized for complex tasks that requi

Audit: Auto-discovered via live global telemetry registry.

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate co

Audit: Auto-discovered via live global telemetry registry.

GPT-5.2 is the latest frontier-grade model in the GPT-5 series, offering stronger agentic and long context perfomance compared to GPT-5.1. It uses adaptive reasoning to allocate co

Audit: Auto-discovered via live global telemetry registry.

Devstral 2 is a state-of-the-art open-source model by Mistral AI specializing in agentic coding. It is a 123B-parameter dense transformer model supporting a 256K context window. De

Audit: Auto-discovered via live global telemetry registry.

The relace-search model uses 4-12 `view_file` and `grep` tools in parallel to explore a codebase and return relevant files to the user request. In contrast to RAG, relace-search pe

Audit: Auto-discovered via live global telemetry registry.

GLM-4.6V is a large multimodal model designed for high-fidelity visual understanding and long-context reasoning across images, documents, and mixed media. It supports up to 128K to

Audit: Auto-discovered via live global telemetry registry.

GPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks. It is based on an updated version of the 5.1 reasonin

Audit: Auto-discovered via live global telemetry registry.

Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilit

Audit: Auto-discovered via live global telemetry registry.

The largest model in the Ministral 3 family, Ministral 3 14B offers frontier capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. A powerful and

Audit: Auto-discovered via live global telemetry registry.

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Audit: Auto-discovered via live global telemetry registry.

A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.

Audit: Auto-discovered via live global telemetry registry.

The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.

Audit: Auto-discovered via live global telemetry registry.

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apa

Audit: Auto-discovered via live global telemetry registry.

Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total), and released under the Apa

Audit: Auto-discovered via live global telemetry registry.

DeepSeek-V3.2 is a large language model designed to harmonize high computational efficiency with strong reasoning and agentic tool-use performance. It introduces DeepSeek Sparse At

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal ca

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal ca

Audit: Auto-discovered via live global telemetry registry.

Nano Banana Pro is Google’s most advanced image-generation and editing model, built on Gemini 3 Pro. It extends the original Nano Banana with significantly improved multimodal reas

Audit: Auto-discovered via live global telemetry registry.

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style

Audit: Auto-discovered via live global telemetry registry.

GPT-5.1 is the latest frontier-grade model in the GPT-5 series, offering stronger general-purpose reasoning, improved instruction adherence, and a more natural conversational style

Audit: Auto-discovered via live global telemetry registry.

GPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows. It is designed for both interactive development sessions and long, indepe

Audit: Auto-discovered via live global telemetry registry.

GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex

Audit: Auto-discovered via live global telemetry registry.

Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-

Audit: Auto-discovered via live global telemetry registry.

Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models.

Audit: Auto-discovered via live global telemetry registry.

Exclusively available on the OpenRouter API, Sonar Pro's new Pro Search mode is Perplexity's most advanced agentic search system. It is designed for deeper reasoning and analysis.

Audit: Auto-discovered via live global telemetry registry.

Voxtral Small is an enhancement of Mistral Small 3, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech tran

Audit: Auto-discovered via live global telemetry registry.

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety

Audit: Auto-discovered via live global telemetry registry.

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it de

Audit: Auto-discovered via live global telemetry registry.

Granite-4.0-H-Micro is a 3B parameter from the Granite 4 family of models. These models are the latest in a series of models released by IBM. They are fine-tuned for long...

Audit: Auto-discovered via live global telemetry registry.

GPT-5 Image Mini combines OpenAI's advanced language capabilities, powered by [GPT-5 Mini](https://openrouter.ai/openai/gpt-5-mini), with GPT Image 1 Mini for efficient image gener

Audit: Auto-discovered via live global telemetry registry.

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Clau

Audit: Auto-discovered via live global telemetry registry.

Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Clau

Audit: Auto-discovered via live global telemetry registry.

Qwen3-VL-8B-Instruct is a multimodal vision-language model from the Qwen3-VL series, built for high-fidelity understanding and reasoning across text, images, and video. It features

Audit: Auto-discovered via live global telemetry registry.

[GPT-5](https://openrouter.ai/openai/gpt-5) Image combines OpenAI's GPT-5 model with state-of-the-art image generation capabilities. It offers major improvements in reasoning, code

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Flash Image, a.k.a. "Nano Banana," is now generally available. It is a state of the art image generation model with contextual understanding. It is capable of image gene

Audit: Auto-discovered via live global telemetry registry.

Qwen3-VL-30B-A3B-Thinking is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Thinking variant enhances reasoning in STEM

Audit: Auto-discovered via live global telemetry registry.

Qwen3-VL-30B-A3B-Instruct is a multimodal model that unifies strong text generation with visual understanding for images and videos. Its Instruct variant optimizes instruction-foll

Audit: Auto-discovered via live global telemetry registry.

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step

Audit: Auto-discovered via live global telemetry registry.

GPT-5 Pro is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step

Audit: Auto-discovered via live global telemetry registry.

Compared with GLM-4.5, this generation brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to

Audit: Auto-discovered via live global telemetry registry.

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchm

Audit: Auto-discovered via live global telemetry registry.

Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchm

Audit: Auto-discovered via live global telemetry registry.

DeepSeek-V3.2-Exp is an experimental large language model released by DeepSeek as an intermediate step between V3.1 and future architectures. It introduces DeepSeek Sparse Attentio

Audit: Auto-discovered via live global telemetry registry.

Uncensored and creative writing model based on Mistral Small 3.2 24B with good recall, prompt adherence, and intelligence.

Audit: Auto-discovered via live global telemetry registry.

Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your fil

Audit: Auto-discovered via live global telemetry registry.

Qwen3-VL-235B-A22B Instruct is an open-weight multimodal model that unifies strong text generation with visual understanding across images and video. The Instruct model targets gen

Audit: Auto-discovered via live global telemetry registry.

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, inc

Audit: Auto-discovered via live global telemetry registry.

Qwen3 Coder Flash is Alibaba's fast and cost efficient version of their proprietary Qwen3 Coder Plus. It is a powerful coding agent model specializing in autonomous programming via

Audit: Auto-discovered via live global telemetry registry.

Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems;

Audit: Auto-discovered via live global telemetry registry.

Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks acr

Audit: Auto-discovered via live global telemetry registry.

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trilli

Audit: Auto-discovered via live global telemetry registry.

Hermes 4 is a large-scale reasoning model built on Meta-Llama-3.1-405B and released by Nous Research. It introduces a hybrid reasoning mode, where the model can choose to deliberat

Audit: Auto-discovered via live global telemetry registry.

DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 ba

Audit: Auto-discovered via live global telemetry registry.

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at signifi

Audit: Auto-discovered via live global telemetry registry.

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at signifi

Audit: Auto-discovered via live global telemetry registry.

GLM-4.5V is a vision-language foundation model for multimodal agent applications. Built on a Mixture-of-Experts (MoE) architecture with 106B parameters and 12B activated parameters

Audit: Auto-discovered via live global telemetry registry.

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reas

Audit: Auto-discovered via live global telemetry registry.

GPT-5 is OpenAI’s most advanced model, offering major improvements in reasoning, code quality, and user experience. It is optimized for complex tasks that require step-by-step reas

Audit: Auto-discovered via live global telemetry registry.

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but wit

Audit: Auto-discovered via live global telemetry registry.

GPT-5 Mini is a compact version of GPT-5, designed to handle lighter-weight reasoning tasks. It provides the same instruction-following and safety-tuning benefits as GPT-5, but wit

Audit: Auto-discovered via live global telemetry registry.

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasonin

Audit: Auto-discovered via live global telemetry registry.

GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasonin

Audit: Auto-discovered via live global telemetry registry.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. I

Audit: Auto-discovered via live global telemetry registry.

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. I

Audit: Auto-discovered via live global telemetry registry.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per f

Audit: Auto-discovered via live global telemetry registry.

gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per f

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified

Audit: Auto-discovered via live global telemetry registry.

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified

Audit: Auto-discovered via live global telemetry registry.

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correc

Audit: Auto-discovered via live global telemetry registry.

Mistral's cutting-edge language model for coding released end of July 2025. Codestral specializes in low-latency, high-frequency tasks such as fill-in-the-middle (FIM), code correc

Audit: Auto-discovered via live global telemetry registry.

Qwen3-Coder-30B-A3B-Instruct is a 30.5B parameter Mixture-of-Experts (MoE) model with 128 experts (8 active per forward pass), designed for advanced code generation, repository-sca

Audit: Auto-discovered via live global telemetry registry.

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is des

Audit: Auto-discovered via live global telemetry registry.

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of u

Audit: Auto-discovered via live global telemetry registry.

GLM-4.5-Air is the lightweight variant of our latest flagship model family, also purpose-built for agent-centric applications. Like GLM-4.5, it adopts the Mixture-of-Experts (MoE)

Audit: Auto-discovered via live global telemetry registry.

Qwen3-235B-A22B-Thinking-2507 is a high-performance, open-weight Mixture-of-Experts (MoE) language model optimized for complex reasoning tasks. It activates 22B of its 235B paramet

Audit: Auto-discovered via live global telemetry registry.

Qwen3-Coder-480B-A35B-Instruct is a Mixture-of-Experts (MoE) code generation model developed by the Qwen team. It is optimized for agentic coding tasks such as function calling, to

Audit: Auto-discovered via live global telemetry registry.

UI-TARS-1.5 is a multimodal vision-language agent optimized for GUI-based environments, including desktop interfaces, web browsers, mobile systems, and games. Built by ByteDance, i

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token ge

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Flash-Lite is a lightweight reasoning model in the Gemini 2.5 family, optimized for ultra-low latency and cost efficiency. It offers improved throughput, faster token ge

Audit: Auto-discovered via live global telemetry registry.

Qwen3-235B-A22B-Instruct-2507 is a multilingual, instruction-tuned mixture-of-experts language model based on the Qwen3-235B architecture, with 22B active parameters per forward pa

Audit: Auto-discovered via live global telemetry registry.

Kimi K2 Instruct is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. I

Audit: Auto-discovered via live global telemetry registry.

Venice Uncensored Dolphin Mistral 24B Venice Edition is a fine-tuned variant of Mistral-Small-24B-Instruct-2501, developed by dphn.ai in collaboration with Venice.ai. This model is

Audit: Auto-discovered via live global telemetry registry.

Hunyuan-A13B is a 13B active parameter Mixture-of-Experts (MoE) language model developed by Tencent, with a total parameter count of 80B and support for reasoning via Chain-of-Thou

Audit: Auto-discovered via live global telemetry registry.

Morph's high-accuracy apply model for complex code edits. ~4,500 tokens/sec with 98% accuracy for precise code transformations. The model requires the prompt to be in the following

Audit: Auto-discovered via live global telemetry registry.

Morph's fastest apply model for code edits. ~10,500 tokens/sec with 96% accuracy for rapid code transformations. The model requires the prompt to be in the following format: <instr

Audit: Auto-discovered via live global telemetry registry.

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling. Compare

Audit: Auto-discovered via live global telemetry registry.

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference. It leverages a hybrid Mixture-of-Experts (MoE) architecture pa

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinki

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Flash is Google's state-of-the-art workhorse model, specifically designed for advanced reasoning, coding, mathematics, and scientific tasks. It includes built-in "thinki

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

Audit: Auto-discovered via live global telemetry registry.

The o-series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o3-pro model uses more compute to think harder and pro

Audit: Auto-discovered via live global telemetry registry.

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to

Audit: Auto-discovered via live global telemetry registry.

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 67

Audit: Auto-discovered via live global telemetry registry.

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Ac

Audit: Auto-discovered via live global telemetry registry.

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-

Audit: Auto-discovered via live global telemetry registry.

Llama Guard 4 is a Llama 4 Scout-derived multimodal pretrained model, fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content

Audit: Auto-discovered via live global telemetry registry.

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, an

Audit: Auto-discovered via live global telemetry registry.

Qwen3-14B is a dense 14.8B parameter causal language model from the Qwen3 series, designed for both complex reasoning and efficient dialogue. It supports seamless switching between

Audit: Auto-discovered via live global telemetry registry.

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching betwee

Audit: Auto-discovered via live global telemetry registry.

OpenAI o4-mini-high is the same model as [o4-mini](/openai/o4-mini) with reasoning_effort set to high. OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fa

Audit: Auto-discovered via live global telemetry registry.

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instru

Audit: Auto-discovered via live global telemetry registry.

o3 is a well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks. It also excels at technical writing and instru

Audit: Auto-discovered via live global telemetry registry.

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports

Audit: Auto-discovered via live global telemetry registry.

OpenAI o4-mini is a compact reasoning model in the o-series, optimized for fast, cost-efficient performance while retaining strong multimodal and agentic capabilities. It supports

Audit: Auto-discovered via live global telemetry registry.

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token

Audit: Auto-discovered via live global telemetry registry.

GPT-4.1 is a flagship large language model optimized for advanced instruction following, real-world software engineering, and long-context reasoning. It supports a 1 million token

Audit: Auto-discovered via live global telemetry registry.

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.

Audit: Auto-discovered via live global telemetry registry.

GPT-4.1 Mini is a mid-sized model delivering performance competitive with GPT-4o at substantially lower latency and cost. It retains a 1 million token context window and scores 45.

Audit: Auto-discovered via live global telemetry registry.

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Audit: Auto-discovered via live global telemetry registry.

For tasks that demand low latency, GPT‑4.1 nano is the fastest and cheapest model in the GPT-4.1 series. It delivers exceptional performance at a small size with its 1 million...

Audit: Auto-discovered via live global telemetry registry.

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active

Audit: Auto-discovered via live global telemetry registry.

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B. It supports native multimo

Audit: Auto-discovered via live global telemetry registry.

DeepSeek V3, a 685B-parameter, mixture-of-experts model, is the latest iteration of the flagship chat model family from the DeepSeek team. It succeeds the [DeepSeek V3](/deepseek/d

Audit: Auto-discovered via live global telemetry registry.

The o1 series of models are trained with reinforcement learning to think before they answer and perform complex reasoning. The o1-pro model uses more compute to think harder and pr

Audit: Auto-discovered via live global telemetry registry.

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities. It provides state-of-the-art

Audit: Auto-discovered via live global telemetry registry.

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv

Audit: Auto-discovered via live global telemetry registry.

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv

Audit: Auto-discovered via live global telemetry registry.

Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to

Audit: Auto-discovered via live global telemetry registry.

Reka Flash 3 is a general-purpose, instruction-tuned large language model with 21 billion parameters, developed by Reka. It excels at general chat, coding tasks, instruction-follow

Audit: Auto-discovered via live global telemetry registry.

Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improv

Audit: Auto-discovered via live global telemetry registry.

Skyfall 36B v2 is an enhanced iteration of Mistral Small 2501, specifically fine-tuned for improved creativity, nuanced writing, role-playing, and coherent storytelling.

Audit: Auto-discovered via live global telemetry registry.

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona

Audit: Auto-discovered via live global telemetry registry.

Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sona

Audit: Auto-discovered via live global telemetry registry.

Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates so

Audit: Auto-discovered via live global telemetry registry.

Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining e

Audit: Auto-discovered via live global telemetry registry.

OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks

Audit: Auto-discovered via live global telemetry registry.

Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate eac

Audit: Auto-discovered via live global telemetry registry.

Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts

Audit: Auto-discovered via live global telemetry registry.

Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

Audit: Auto-discovered via live global telemetry registry.

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning

Audit: Auto-discovered via live global telemetry registry.

OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning

Audit: Auto-discovered via live global telemetry registry.

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained

Audit: Auto-discovered via live global telemetry registry.

Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightwei

Audit: Auto-discovered via live global telemetry registry.

DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inf

Audit: Auto-discovered via live global telemetry registry.

MiniMax-01 is a combines MiniMax-Text-01 for text generation and MiniMax-VL-01 for image understanding. It has 456 billion parameters, with 45.9 billion parameters activated per in

Audit: Auto-discovered via live global telemetry registry.

[Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses

Audit: Auto-discovered via live global telemetry registry.

DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tok

Audit: Auto-discovered via live global telemetry registry.

Euryale L3.3 70B is a model focused on creative roleplay from [Sao10k](https://ko-fi.com/sao10k). It is the successor of [Euryale L3 70B v2.2](/models/sao10k/l3-euryale-70b).

Audit: Auto-discovered via live global telemetry registry.

The latest and strongest model family from OpenAI, o1 is designed to spend more time thinking before responding. The o1 model series is trained with large-scale reinforcement learn

Audit: Auto-discovered via live global telemetry registry.

Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning

Audit: Auto-discovered via live global telemetry registry.

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text on

Audit: Auto-discovered via live global telemetry registry.

Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

Audit: Auto-discovered via live global telemetry registry.

Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

Audit: Auto-discovered via live global telemetry registry.

Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

Audit: Auto-discovered via live global telemetry registry.

The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better

Audit: Auto-discovered via live global telemetry registry.

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. R

Audit: Auto-discovered via live global telemetry registry.

Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Sig

Audit: Auto-discovered via live global telemetry registry.

UnslopNemo v4.1 is the latest addition from the creator of Rocinante, designed for adventure writing and role-play scenarios.

Audit: Auto-discovered via live global telemetry registry.

This is a series of models designed to replicate the prose quality of the Claude 3 models, specifically Sonnet(https://openrouter.ai/anthropic/claude-3.5-sonnet) and Opus(https://o

Audit: Auto-discovered via live global telemetry registry.

Qwen2.5 7B is the latest series of Qwen large language models. Qwen2.5 brings the following improvements upon Qwen2: - Significantly more knowledge and has greatly improved capabil

Audit: Auto-discovered via live global telemetry registry.

Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its

Audit: Auto-discovered via live global telemetry registry.

Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summariza

Audit: Auto-discovered via live global telemetry registry.