Models
Every new AI model, as it lands
222 models from 18 labs — 25 new in the last 30 days. Release date, context window, API price and benchmark scores for each — tick any models to compare them side by side.
Tick up to 4 models to compare their benchmarks.
DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model... |
Oct 17, 2026 | 1M393K out | $0.15 | $0.60 | 89.8% |
|---|---|---|---|---|---|
Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers... |
Oct 15, 2026 | 1M944K out | $1.25 | $4.25 | — |
NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video... |
Oct 15, 2026 | 1M236K out | $0.10 | $0.40 | — |
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. Google trained it to keep context across... |
Oct 13, 2026 | 1M944K out | $2.00 | $10.00 | 96.4% |
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 returns text, with... |
Oct 12, 2026 | 1M944K out | $4.00 | $20.00 | — |
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 software engineering and professional... |
Oct 8, 2026 | 1M64K out | $1.00 | $2.70 | — |
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 coding, computer use, and... |
Oct 7, 2026 | 1M128K out | $0.10 | $0.50 | 89.6% |
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 recontextualization,... |
Oct 6, 2026 | 66K59K out | $1.50 | $7.50 | — |
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 up... |
Oct 6, 2026 | 1M262K out | $0.68 | $2.09 | 88.1% |
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 complex tasks. **Cost note:** pro mode spends far more... |
Sep 29, 2026 | 1.05M128K out | $2.00 | $10.00 | — |
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 professional... |
Sep 29, 2026 | 1.05M128K out | $2.00 | $10.00 | 95.4% |
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, fixing bugs, and producing... |
Sep 28, 2026 | 1M128K out | $2.00 | $10.00 | 95.6% |
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 supports text input and output with a 1M-token... |
Sep 23, 2026 | 1M131K out | $2.80 | $8.80 | — |
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... |
Sep 23, 2026 | 1M131K out | $4.00 | $12.00 | — |
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 schemas, structured... |
Sep 22, 2026 | 192K64K out | $0.30 | $1.50 | — |
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 complex tasks. **Cost note:** pro mode spends far more... |
Sep 22, 2026 | 1.05M128K out | $0.10 | $0.50 | — |
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, classification, and lightweight agentic... |
Sep 22, 2026 | 1.05M128K out | $0.10 | $0.50 | 90.5% |
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 tasks. **Cost note:** pro mode spends far more... |
Sep 22, 2026 | 1.05M128K out | $2.00 | $10.00 | — |
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 professional... |
Sep 22, 2026 | 1.05M128K out | $2.00 | $10.00 | 94.3% |
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 changes in large codebases, code... |
Sep 22, 2026 | 1M128K out | $4.00 | $20.00 | 90.6% |
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 model in quality while delivering roughly 10x... |
Sep 21, 2026 | 1M131K out | $4.35 | $8.70 | — |
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 employs a hybrid attention mechanism for... |
Sep 21, 2026 | 1.05M131K out | $0.14 | $0.28 | — |
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... |
Sep 21, 2026 | 1.05M131K out | $0.43 | $0.87 | — |
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, verifying its own work, and... |
Sep 21, 2026 | 500K450K out | $2.00 | $6.00 | 92.7% |
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 audio-video analysis and summarization,... |
Sep 21, 2026 | 1M131K out | $0.15 | $0.47 | — |
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 linear attention architecture... |
Sep 18, 2026 | 1M131K out | $0.37 | $1.25 | — |
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 on input and 16B on... |
Sep 10, 2026 | 1M944K out | $0.03 | $0.08 | 89.8% |
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 creation, with particular strengths in long-horizon... |
Sep 4, 2026 | 1.05M128K out | $10.00 | $50.00 | 95.8% |
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 complex tasks. **Cost note:** pro mode spends far more... |
Sep 4, 2026 | 1.05M128K out | $10.00 | $50.00 | — |
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 and returns text,... |
Sep 3, 2026 | 1M131K out | $2.00 | $6.00 | 92.7% |
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 coding workflows. It is designed to track information... |
Sep 2, 2026 | 1M944K out | $0.10 | $0.20 | — |
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 tasks, work through... |
Sep 2, 2026 | 1M944K out | $1.25 | $4.25 | — |
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. |
Sep 2, 2026 | 1M66K out | $0.82 | $4.13 | 95.4% |
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, front-end and visual... |
Sep 1, 2026 | 1M128K out | $10.00 | $50.00 | — |
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 productivity tasks that... |
Aug 28, 2026 | 1M64K out | $0.75 | $2.25 | — |
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 interaction, chart analysis, and long-video analysis. |
Aug 26, 2026 | 1M131K out | $0.15 | $0.47 | — |
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 accurate long-context behavior while... |
Aug 26, 2026 | 1M944K out | $0.048 | $0.16 | 90.1% |
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... |
Aug 21, 2026 | 1M944K out | $0.10 | $0.20 | — |
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 image understanding while matching the base model on text… |
Aug 21, 2026 | 1M262K out | $0.22 | $0.65 | — |
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 structured, delimiter-based, contextual, glossary-based, and… |
Aug 20, 2026 | 8K4K out | $0.044 | $0.18 | — |
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 structured, delimiter-based, contextual, glossary-based… |
Aug 20, 2026 | 8K4K out | $0.074 | $0.29 | — |
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, delimiter-based, contextual, glossary-based, and style-guided… |
Aug 19, 2026 | 8K4K out | $0.074 | $0.29 | — |
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 window, and improves... |
Aug 18, 2026 | 1M944K out | $0.079 | $1.40 | 90.9% |
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, with flexible thinking that can be... |
Aug 14, 2026 | 1M236K out | $0.24 | $2.20 | — |
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 performance and reliable multi-step... |
Aug 13, 2026 | 1M66K out | $0.75 | $3.75 | 94.8% |
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 understanding visual and... |
Aug 12, 2026 | 262K236K out | $0.50 | $2.50 | — |
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 of 2.4 trillion total. It is... |
Aug 12, 2026 | 1M131K out | $2.00 | $6.00 | — |
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 tools such as Claude... |
Aug 12, 2026 | 262K131K out | $0.50 | $3.00 | — |
DeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro. |
Aug 12, 2026 | 1M384K out | $0.66 | $1.98 | 91.7% |
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). |
Aug 12, 2026 | 500K450K out | $2.00 | $6.00 | 94.0% |
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 specialized tasks that... |
Aug 11, 2026 | 262K236K out | $0.07 | $0.20 | — |
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 is suited for long-horizon... |
Aug 9, 2026 | 131K16K out | $0.30 | $1.20 | — |
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 window.... |
Aug 5, 2026 | 1M944K out | $1.25 | $4.25 | — |
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, reasoning, and agent workflows.... |
Jul 31, 2026 | 1M131K out | $0.13 | $0.39 | 91.0% |
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 recognition, spatial understanding, and real-world... |
Jul 27, 2026 | 1M66K out | $0.03 | $0.13 | 82.3% |
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 bug finding, visual analysis... |
Jul 24, 2026 | 1M128K out | $5.00 | $25.00 | 93.9% |
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 unnecessary edits and... |
Jul 21, 2026 | 1M66K out | $0.75 | $3.75 | 94.1% |
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 workflows. |
Jul 21, 2026 | 1M66K out | $0.30 | $2.50 | 83.3% |
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 particularly strong at... |
Jul 16, 2026 | 1M944K out | $0.24 | $11.94 | 93.1% |
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 window.... |
Jul 16, 2026 | 1M944K out | $1.25 | $4.25 | — |
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 on complex tasks. **Cost note:** pro mode spends far more... |
Jul 9, 2026 | 1.05M128K out | $0.20 | $1.20 | — |
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 workflows, providing capable reasoning for... |
Jul 9, 2026 | 1.05M128K out | $0.20 | $1.20 | 91.6% |
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 responses on complex tasks. **Cost note:** pro mode spends far… |
Jul 9, 2026 | 1.05M128K out | $2.00 | $12.00 | — |
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, and agentic... |
Jul 9, 2026 | 1.05M128K out | $2.00 | $12.00 | 93.3% |
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 complex tasks. **Cost note:** pro mode spends far more... |
Jul 9, 2026 | 1.05M128K out | $4.00 | $20.00 | — |
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 multi-step coding tasks... |
Jul 9, 2026 | 1.05M128K out | $4.00 | $20.00 | 93.5% |
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. |
Jul 8, 2026 | 500K450K out | $2.00 | $6.00 | 93.4% |
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 supports a configurable reasoning effort:... |
Jul 6, 2026 | 262K128K out | $0.083 | $0.33 | — |
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 reasoning effort levels (low, medium, high, max,... |
Jun 30, 2026 | 1M128K out | $2.00 | $10.00 | 90.5% |
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 exploration. It delivers text-to-image generation... |
Jun 30, 2026 | 66K59K out | $0.25 | $1.50 | — |
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 combines advanced... |
Jun 18, 2026 | 131K33K out | $0.50 | $3.00 | — |
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 reasoning, real-world grounding, and... |
Jun 18, 2026 | 131K33K out | $2.00 | $12.00 | — |
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 software engineering,... |
Jun 16, 2026 | 1M944K out | $0.62 | $2.42 | 91.9% |
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 multimodal mixture-of-experts... |
Jun 12, 2026 | 262K236K out | $0.67 | $3.35 | 87.9% |
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 support and... |
Jun 9, 2026 | 1M128K out | $10.00 | $50.00 | 85.9% |
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 from LLMs and VLMs, accepting... |
Jun 4, 2026 | 131K118K out | $0.20 | $0.20 | — |
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 mixture-of-experts architecture, it... |
Jun 4, 2026 | 262K183K out | $0.60 | $2.40 | — |
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 comprehensive upgrade to its... |
Jun 3, 2026 | 1M131K out | $0.32 | $1.28 | 87.9% |
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 agentic work, coding,... |
May 31, 2026 | 1M512K out | $0.30 | $1.20 | 90.9% |
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 understanding, activating roughly 11B parameters... |
May 28, 2026 | 262K230K out | $0.20 | $1.15 | — |
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-token... |
May 27, 2026 | 1M128K out | $5.00 | $25.00 | 91.0% |
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, office and productivity tasks,... |
May 21, 2026 | 1M131K out | $1.48 | $4.42 | 90.9% |
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 for interactive coding... |
May 20, 2026 | 256K230K out | $1.00 | $2.00 | — |
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 proficiency and parallel agentic execution... |
May 19, 2026 | 1M66K out | $1.50 | $9.00 | 92.8% |
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 is designed for lightweight agentic... |
May 7, 2026 | 1M66K out | $0.25 | $1.50 | 81.8% |
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 updates... |
May 5, 2026 | 400K128K out | $5.00 | $30.00 | — |
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 requiring high factual... |
Apr 30, 2026 | 1M900K out | $1.25 | $2.50 | 88.8% |
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, and complex... |
Apr 30, 2026 | 262K210K out | $1.50 | $7.50 | — |
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. This... |
Apr 27, 2026 | 1M66K out | $0.30 | $1.80 | 84.9% |
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... |
Apr 27, 2026 | 1M66K out | $0.19 | $1.13 | 83.3% |
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-experts architecture combining Gated... |
Apr 27, 2026 | 262K236K out | $0.15 | $1.00 | 84.9% |
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, and video inputs... |
Apr 27, 2026 | 262K66K out | $0.25 | $2.00 | 85.9% |
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 output) with support for... |
Apr 24, 2026 | 1.05M128K out | $30.00 | $180.00 | — |
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 hard tasks. It features a 1M+ token... |
Apr 24, 2026 | 1.05M128K out | $5.00 | $30.00 | 90.7% |
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 designed for advanced reasoning, coding,... |
Apr 24, 2026 | 1M384K out | $0.40 | $0.79 | 91.7% |
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. It is designed for fast inference and... |
Apr 24, 2026 | 1M944K out | $0.091 | $0.18 | 91.0% |
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, low, and high modes, allowing it to... |
Apr 22, 2026 | 262K236K out | $0.18 | $0.60 | — |
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 benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.... |
Apr 22, 2026 | 1.05M131K out | $0.43 | $0.87 | — |
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 perception across image and video understanding... |
Apr 22, 2026 | 1.05M131K out | $0.14 | $0.28 | — |
[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 multimodal workflows, allowing users to seamlessly move between… |
Apr 21, 2026 | 272K128K out | $8.00 | $15.00 | — |
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-to-end coding tasks across Python, Rust, and Go, and... |
Apr 20, 2026 | 262K236K out | $0.65 | $3.41 | 90.8% |
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 stronger performance on... |
Apr 16, 2026 | 1M128K out | $5.00 | $25.00 | 90.1% |
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 interactions, GLM-5.1 can work independently and continuously on... |
Apr 7, 2026 | 205K128K out | $0.97 | $3.04 | 89.9% |
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 — delivering near-31B quality at... |
Apr 3, 2026 | 262K236K out | $0.077 | $0.26 | 73.2% |
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/reasoning mode, native function... |
Apr 2, 2026 | 262K16K out | $0.20 | $0.40 | 75.8% |
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 inference. Compared to the 3.5 series, it delivers... |
Apr 2, 2026 | 1M66K out | $0.33 | $1.95 | 88.4% |
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, excels at long-horizon planning, complex coding,... |
Apr 1, 2026 | 203K131K out | $1.20 | $4.00 | — |
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, coordinate tool use, and synthesize information... |
Mar 31, 2026 | 2M1.8M out | $1.25 | $2.50 | — |
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 prompt adherance, delivering... |
Mar 31, 2026 | 2M1.8M out | $1.25 | $2.50 | — |
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, 48kHz... |
Mar 30, 2026 | 1M66K out | Free | Free | — |
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... |
Mar 30, 2026 | 1M66K out | Free | Free | — |
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 evolution, M2.7 integrates advanced agentic capabilities through… |
Mar 18, 2026 | 205K131K out | $0.30 | $1.20 | — |
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 designed for low-latency... |
Mar 17, 2026 | 400K128K out | $0.20 | $1.25 | 78.5% |
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 performance across reasoning, coding,... |
Mar 17, 2026 | 400K128K out | $0.75 | $4.50 | 86.9% |
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 reasoning from... |
Mar 16, 2026 | 262K210K out | $0.15 | $0.60 | 47.5% |
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-world agent workflows... |
Mar 15, 2026 | 203K131K out | $1.20 | $4.00 | — |
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. Built on a hybrid Mamba-Transformer... |
Mar 11, 2026 | 262K236K out | $0.08 | $0.45 | — |
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 practical default choice for most production workloads across... |
Mar 10, 2026 | 262K131K out | $0.25 | $2.00 | — |
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 architecture. It uses a unified vision-language design... |
Mar 10, 2026 | 262K33K out | $0.10 | $0.15 | 79.0% |
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 context window (922K input, 128K... |
Mar 5, 2026 | 1.05M128K out | $30.00 | $180.00 | 94.6% |
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... |
Mar 5, 2026 | 1.05M128K out | $2.50 | $15.00 | 93.3% |
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 2.5 Flash performance across... |
Mar 3, 2026 | 1M66K out | $0.25 | $1.50 | 81.8% |
Seed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment. It delivers performance comparable to ByteDance-Seed-1.6, supports 256k context, four… |
Feb 26, 2026 | 262K131K out | $0.10 | $0.40 | — |
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. It combines... |
Feb 26, 2026 | 66K59K out | $0.50 | $3.00 | — |
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, achieving higher inference efficiency. Its overall... |
Feb 25, 2026 | 262K236K out | $0.15 | $1.00 | 83.5% |
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 overall capabilities are comparable to those of... |
Feb 25, 2026 | 262K66K out | $0.27 | $2.16 | — |
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 higher inference efficiency. In terms of... |
Feb 25, 2026 | 262K66K out | $0.26 | $2.08 | — |
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 higher inference efficiency. Compared to the... |
Feb 25, 2026 | 1M66K out | $0.065 | $0.26 | — |
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-party... |
Feb 25, 2026 | 1M66K out | $2.00 | $12.00 | — |
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 knowledge capabilities of GPT-5.2. It achieves… |
Feb 24, 2026 | 400K128K out | $1.75 | $14.00 | — |
Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows. Building on the multimodal… |
Feb 19, 2026 | 1M66K out | $2.00 | $12.00 | 94.4% |
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 codebase navigation, end-to-end project management with... |
Feb 17, 2026 | 1M128K out | $3.00 | $15.00 | 87.4% |
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, achieving higher inference efficiency. In a variety of... |
Feb 16, 2026 | 1M66K out | $0.26 | $1.56 | — |
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, achieving higher inference efficiency. It delivers... |
Feb 16, 2026 | 262K236K out | $0.50 | $3.60 | 86.4% |
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 the coding expertise of M2.1... |
Feb 12, 2026 | 205K33K out | $0.27 | $0.95 | — |
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-grade performance on large-scale programming tasks, rivaling… |
Feb 11, 2026 | 205K131K out | $1.00 | $3.20 | 87.8% |
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, making it especially effective... |
Feb 4, 2026 | 1M128K out | $5.00 | $25.00 | 90.5% |
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 3B activated per... |
Feb 4, 2026 | 262K236K out | $0.12 | $0.80 | — |
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 parameters per token.... |
Jan 29, 2026 | 262K66K out | $0.10 | $0.30 | — |
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 pretraining over approximately 15T mixed... |
Jan 27, 2026 | 262K236K out | $0.50 | $2.50 | — |
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 tone and personality, it supports rich message... |
Jan 23, 2026 | 66K2K out | $0.30 | $1.20 | — |
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 consistency. Audio is priced... |
Jan 19, 2026 | 128K16K out | $2.50 | $10.00 | — |
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 $0.60 per million... |
Jan 19, 2026 | 128K16K out | $0.60 | $2.40 | — |
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 capabilities, long-horizon task planning,... |
Jan 19, 2026 | 200K118K out | $0.061 | $0.40 | 60.5% |
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, independent execution of complex engineering tasks.... |
Jan 14, 2026 | 400K128K out | $1.75 | $14.00 | — |
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 outputs of... |
Dec 23, 2025 | 262K33K out | $0.075 | $0.30 | — |
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. |
Dec 23, 2025 | 262K33K out | $0.25 | $2.00 | — |
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 parameters, it delivers a major jump in real-world... |
Dec 23, 2025 | 205K131K out | $0.30 | $1.20 | — |
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 significant improvements in executing complex agent tasks… |
Dec 22, 2025 | 205K131K out | $0.54 | $1.98 | 83.3% |
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 tool... |
Dec 17, 2025 | 1M66K out | $0.50 | $3.00 | 89.4% |
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... |
Dec 14, 2025 | 262K236K out | $0.06 | $0.24 | — |
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 to selectively “think” on... |
Dec 10, 2025 | 128K32K out | $1.75 | $14.00 | — |
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 require step-by-step reasoning,... |
Dec 10, 2025 | 400K128K out | $21.00 | $168.00 | — |
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 computation dynamically, responding quickly... |
Dec 10, 2025 | 400K128K out | $1.75 | $14.00 | 91.4% |
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. Devstral 2 supports exploring... |
Dec 9, 2025 | 262K210K out | $0.40 | $2.00 | — |
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 tokens, processes complex page layouts... |
Dec 8, 2025 | 131K33K out | $0.30 | $0.90 | — |
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 reasoning stack and trained on agentic... |
Dec 4, 2025 | 400K128K out | $1.25 | $10.00 | — |
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 capabilities in processing... |
Dec 2, 2025 | 1M66K out | $0.30 | $2.50 | — |
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 efficient language... |
Dec 2, 2025 | 262K210K out | $0.20 | $0.20 | — |
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities. |
Dec 2, 2025 | 262K210K out | $0.15 | $0.15 | 27.2% |
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. |
Dec 2, 2025 | 131K105K out | $0.10 | $0.10 | 25.3% |
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 Apache 2.0 license. |
Dec 1, 2025 | 262K210K out | $0.50 | $1.50 | 51.3% |
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 Attention (DSA), a fine-grained sparse attention mechanism... |
Dec 1, 2025 | 164K66K out | $0.28 | $0.42 | — |
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 capabilities, competitive performance across real-world coding… |
Nov 24, 2025 | 200K64K out | $5.00 | $25.00 | 86.1% |
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 reasoning, real-world grounding, and... |
Nov 20, 2025 | 66K33K out | $2.00 | $12.00 | — |
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 compared to GPT-5. It uses adaptive reasoning... |
Nov 13, 2025 | 400K128K out | $1.25 | $10.00 | 87.6% |
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, independent execution of complex engineering tasks.... |
Nov 13, 2025 | 400K128K out | $1.25 | $10.00 | — |
GPT-5.1-Codex-Mini is a smaller and faster version of GPT-5.1-Codex |
Nov 13, 2025 | 400K128K out | $0.25 | $2.00 | — |
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-of-Experts (MoE) architecture introduced in... |
Nov 6, 2025 | 262K98K out | $0.60 | $2.50 | — |
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. |
Oct 31, 2025 | 1M32K out | $2.50 | $12.50 | — |
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 transcription, translation and audio understanding. Input… |
Oct 30, 2025 | 33K26K out | $0.10 | $0.30 | — |
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 tasks like content classification, LLM filtering, and… |
Oct 29, 2025 | 131K66K out | $0.075 | $0.30 | — |
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 delivers near-frontier intelligence across general… |
Oct 23, 2025 | 205K131K out | $0.26 | $1.02 | — |
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 generation. This natively multimodal model features superior… |
Oct 16, 2025 | 400K128K out | $2.50 | $2.00 | — |
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 Claude Sonnet 4’s performance... |
Oct 15, 2025 | 200K64K out | $1.00 | $5.00 | 71.2% |
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 improved multimodal fusion with Interleaved-MRoPE for… |
Oct 14, 2025 | 262K236K out | $0.25 | $0.75 | — |
[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 quality, and user experience while incorporating GPT Image… |
Oct 14, 2025 | 400K128K out | $10.00 | $10.00 | — |
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 generation,... |
Oct 7, 2025 | 33K8K out | $0.30 | $2.50 | — |
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, math, and complex tasks. It excels... |
Oct 6, 2025 | 262K236K out | $0.29 | $1.00 | — |
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-following for general multimodal tasks. It excels in… |
Oct 6, 2025 | 262K16K out | $0.15 | $0.60 | — |
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 reasoning, instruction following, and... |
Oct 6, 2025 | 400K128K out | $15.00 | $120.00 | — |
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 handle more complex... |
Sep 30, 2025 | 205K131K out | $0.55 | $2.20 | — |
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 benchmarks such as SWE-bench Verified, with... |
Sep 29, 2025 | 1M64K out | $3.00 | $15.00 | 82.3% |
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 Attention (DSA), a fine-grained sparse attention mechanism... |
Sep 29, 2025 | 164K147K out | $0.27 | $0.41 | — |
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 general vision-language use (VQA, document parsing… |
Sep 23, 2025 | 262K33K out | $0.21 | $1.90 | — |
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, including language consistency and agent capabilities, further… |
Sep 22, 2025 | 164K147K out | $0.27 | $1.00 | — |
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 tool calling... |
Sep 17, 2025 | 1M66K out | $0.20 | $0.97 | — |
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; math proofs, code synthesis/debugging, logic, and… |
Sep 11, 2025 | 262K236K out | $0.15 | $1.20 | — |
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 across reasoning, code generation, knowledge QA, and… |
Sep 11, 2025 | 262K16K out | $0.09 | $1.10 | — |
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 trillion total parameters with 32... |
Sep 4, 2025 | 262K98K out | $0.60 | $2.50 | — |
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 base with a two-phase long-context... |
Aug 21, 2025 | 164K33K out | $0.25 | $0.95 | — |
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 significantly reduced operational cost. It balances... |
Aug 13, 2025 | 131K105K out | $0.40 | $2.00 | — |
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, it achieves state-of-the-art results in video… |
Aug 11, 2025 | 66K16K out | $0.60 | $1.80 | — |
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 reasoning, instruction following, and accuracy... |
Aug 7, 2025 | 400K128K out | $1.25 | $10.00 | 86.2% |
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 with reduced latency and cost.... |
Aug 7, 2025 | 400K128K out | $0.25 | $2.00 | 75.0% |
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 reasoning depth compared to its larger... |
Aug 7, 2025 | 400K128K out | $0.05 | $0.40 | 69.4% |
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. It activates 5.1B parameters per forward pass and is… |
Aug 5, 2025 | 131K66K out | $0.15 | $0.60 | 75.8% |
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 forward pass, optimized for... |
Aug 5, 2025 | 131K33K out | $0.018 | $0.09 | 60.8% |
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 and shows notable gains... |
Aug 5, 2025 | 200K32K out | $15.00 | $75.00 | 77.3% |
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 correction and test generation. [Blog… |
Aug 1, 2025 | 256K205K out | $0.30 | $0.90 | — |
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-scale understanding, and agentic tool use. Built on the... |
Jul 31, 2025 | 262K236K out | $0.07 | $0.28 | — |
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 designed for high-quality instruction following, multilingual… |
Jul 29, 2025 | 262K236K out | $0.09 | $0.30 | 55.6% |
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 up to 128k tokens. GLM-4.5 delivers significantly... |
Jul 25, 2025 | 131K98K out | $0.60 | $2.20 | — |
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) architecture but with a more compact parameter... |
Jul 25, 2025 | 131K98K out | $0.13 | $0.85 | — |
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 parameters per forward pass and natively supports up to 262,144... |
Jul 25, 2025 | 128K16K out | $0.45 | $3.50 | 80.0% |
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, tool use, and long-context reasoning over... |
Jul 23, 2025 | 262K66K out | $0.30 | $1.00 | — |
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 generation, and better performance... |
Jul 22, 2025 | 1M66K out | $0.10 | $0.40 | — |
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 pass. It is optimized for general-purpose text generation… |
Jul 21, 2025 | 262K16K out | $0.09 | $0.55 | 70.7% |
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. It is optimized for... |
Jul 11, 2025 | 131K98K out | $0.57 | $2.30 | — |
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-Thought. It offers competitive benchmark... |
Jul 8, 2025 | 131K118K out | $0.14 | $0.57 | — |
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. Compared to the 3.1 release, version 3.2 significantly improves… |
Jun 20, 2025 | 256K16K out | $0.094 | $0.25 | — |
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 paired with a custom "lightning attention" mechanism, allowing… |
Jun 17, 2025 | 1M40K out | $0.55 | $2.20 | — |
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 "thinking" capabilities, enabling it to provide responses with… |
Jun 17, 2025 | 1M66K out | $0.30 | $2.50 | — |
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 reason through responses with enhanced accuracy... |
Jun 17, 2025 | 1M66K out | $1.25 | $10.00 | 85.3% |
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 provide consistently... |
Jun 10, 2025 | 200K100K out | $20.00 | $80.00 | — |
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 reason through responses with enhanced accuracy... |
Jun 5, 2025 | 1M66K out | $1.25 | $10.00 | 85.3% |
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 671B parameters in size, with 37B active... |
May 28, 2025 | 164K33K out | $0.50 | $2.15 | 76.3% |
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-of-the-art reasoning and multimodal performance with 8×… |
May 7, 2025 | 131K105K out | $0.40 | $2.00 | — |
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 in both LLM... |
Apr 30, 2025 | 164K16K out | $0.18 | $0.18 | — |
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, and advanced agent tasks. Its unique... |
Apr 28, 2025 | 41K16K out | $0.12 | $0.50 | 61.7% |
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 a "thinking" mode for... |
Apr 28, 2025 | 41K16K out | $0.12 | $0.24 | 63.8% |
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 between a "thinking" mode for... |
Apr 28, 2025 | 131K16K out | $0.08 | $0.28 | 65.7% |
D
M
N
G
S
M
Q
C
T
B
M
M
ANo models match these filters.
Dates are when each model was listed on OpenRouter, usually its launch day. Prices are OpenRouter's USD rate per million tokens; first-party API prices can differ. “Free tier” means a rate-limited free variant exists. Benchmark scores are the best result per model (across reasoning settings and agents) from Epoch AI's benchmarking hub, licensed CC BY 4.0, updated Oct 19, 2026; “—” means the model hasn't been scored yet.