OpenRouter models in Big-AGI
400+ models on one key - with Anthropic, Google, OpenAI and xAI controls restored to their native ranges, not the router's flattened ones.
OpenRouter gives you the models. Big-AGI adds the workspace.
OpenRouter is the routing layer: one key, hundreds of models, automatic fallback. It is not where you organize the work. Point Big-AGI at that key and the catalog turns into an expert workspace.
| Capability | Through your OpenRouter key | Inside Big-AGI |
|---|---|---|
| Model catalog | Hundreds, one key | The same catalog, same key |
| Reasoning and parameter control | Router-flattened | Vendor-accurate ranges |
| Merging multiple answers | Basic Fusion | Advanced and custom merges |
| Personas and saved prompts | Not the router's job | Built in, with memory |
| Chat history and attachments | Bring your own | Local-first, yours |
| Request transparency | API-level | AI Inspector on every call |
Start for $0
You do not need credits to begin. On October 4, 2026 OpenRouter listed 17 models at $0, five of them NVIDIA Nemotron builds and two Gemma 4 sizes, and Big-AGI runs them the moment your key is linked. Add a Google key for the Gemini free tier and you have a second vendor at no cost. Free usage runs under OpenRouter's own daily and per-minute limits, so it is built for trying things, not production loads. When you outgrow it, the same key unlocks every paid model at OpenRouter's rates.
All supported OpenRouter models
ModelContextInputOutputReleased
Particle-1NEWParticle-1 is a token-efficient agentic coding model from Particle AI, post-trained on DeepSeek V4.1 Flash. It is suited for software engineering work such as…1M$0.05$0.50Oct 2026GPT-6.1 TerraNEWGPT-6.1 Terra is the mid-tier model in OpenAI's GPT-6.1 series, priced below GPT-6.1 Sol. It is suited for everyday agentic, coding, and writing work, is parti…1.1M$1.00$5.00Oct 2026GPT-6.1 Terra ProNEWGPT-6.1 Terra Pro is the same underlying model as GPT-6.1 Terra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cos…1.1M$1.00$5.00Oct 2026Kimi K3.1 ProNEWKimi K3.1 Pro is Moonshot AI's flagship open-weight multimodal reasoning model and a post-trained successor to Kimi K3, with a 1M-token context window. It is b…1M$2.00$10.00Oct 2026Flint (free)NEWFlint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system E…262KFreeFreeOct 2026MiniMax M3.1 FlashNEWMiniMax-M3.1-Flash is a multimodal model from MiniMax. Compared with M3, it delivers significant improvements across multiple benchmarks, particularly in compl…1M$0.15$0.60Oct 2026DeepSeek V4.1 Flash 1017NEWDeepSeek 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…1M$0.02$0.16Oct 2026GlimpseNEWGlimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons dire…262K$0.60$3.00Oct 2026Xing4.0 29B A4B (free)NEWXing4.0-29B-A4B is an open-weight mixture-of-experts language model from China Telecom's AI team (TeleAI) and the successor to the TeleChat series. It has 29B…262KFreeFreeOct 2026Beam 1.0 501B A23BNEWBeam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B…1M$0.25$1.00Oct 2026Mercury 3NEWMercury 3 is a diffusion-based language model from Inception, and the lab's most capable model to date. It is suited for agentic workflows and real-time applic…1M$0.10$0.35Oct 2026Ternary Bonsai 2 9BNEWTernary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights…262K$0.08$0.13Oct 2026Nemotron 3.5 Super VLNEWNVIDIA 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, d…1M$0.15$0.50Oct 2026Moondream 3.1NEWMoondream 3.1 is a vision-language model from Moondream, the successor to Moondream 3 Preview, with 9B total parameters and 2B active (mixture-of-experts). It…32K$0.30$2.50Oct 2026Moondream 3 PreviewNEWMoondream 3 Preview is a vision-language model from Moondream with 9B total parameters and 2B active (mixture-of-experts). It handles visual question answering…32K$0.30$2.50Oct 2026Muse Spark OpenNEWMuse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable…1M$1.25$4.25Oct 2026Pareto 26.10NEWPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of g…1M$0.80$3.20Oct 2026ExtractNEWExtract 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…1M$0.04FreeOct 2026LFM2.5-24B-A2BNEWLFM2.5-24B-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 bui…128K$0.05$0.70Oct 2026Pareto 26.9NEWPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of g…262K$2.50$7.50Oct 2026SummarizeNEWSummarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting senten…1M$0.04FreeOct 2026Muse WonderNEWMuse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and P…1M$4.00$20.00Oct 2026Step 5 PreviewNEWStep 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It perform…1M$1.00$2.70Oct 2026Claude Haiku 5.5NEWClaude 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 Ha…1M$0.10$0.50Oct 2026Nano Banana 2.1NEWNano 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 imp…66K$1.50$7.50Oct 2026Mistral Large 4NEWMistral 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…1M$0.70$2.10Oct 2026Ling 3.1 FlashNEWLing 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.1M$0.08$0.23Oct 2026Apodex 1.1 Mini (free)deprecatedApodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, cod…262KFreeFreeOct 2026Pareto 26.10 PreviewdeprecatedPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of g…1M$0.80$3.20Oct 2026Gemini 4 ArgonNEWGemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous m…1M$2.00$10.00Sep 2026GPT-6.1 SolNEWGPT-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 us…1.1M$2.00$10.00Sep 2026GPT-6.1 Sol ProNEWGPT-6.1 Sol Pro is the same underlying model as GPT-6.1 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost no…1.1M$2.00$10.00Sep 2026Claude Sonnet 5.5NEWHOTClaude 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 b…1M$2.00$10.00Sep 2026Jev RouterNEWJev Router picks the best model and reasoning effort for each request, balancing quality, speed, and cost. It runs on Jev, TypeSafe's first System One model, a…1M--Sep 2026Perceptron Mk1.5NEWPerceptron Mk1.5 is Perceptron's embodied reasoning model for physical agents. It accepts text, image, video, and audio input, and answers with text plus optio…37K$0.15$1.50Sep 2026Ember-1NEWEmber-1 is a specialized reasoning model from Fireworks Research, built on Kimi K3. It is designed to make every token go further: it produces shorter reasonin…1M$3.00$15.00Sep 2026Aion 3.5 MiniNEWAion 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 A…262K$0.70$1.40Sep 2026Aion 3.5NEWAion 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 w…262K$3.00$6.00Sep 2026GLM 5.3 PrimeNEWGLM-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 acc…1M$2.80$8.80Sep 2026Qwen3.8 Max PrimeNEWQwen3.8 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, im…1M$4.00$12.00Sep 2026Solar Mini 4NEWSolar 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…524K$0.05$0.20Sep 2026Space Bunny AlphadeprecatedSpace Bunny Alpha is an anonymous large model with blazing-fast inference, strong coding capabilities and native multimodal input support. It delivers adjustab…1MFreeFreeSep 2026Claude Opus 5.5NEWHOTClaude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly stro…1M$4.00$20.00Sep 2026GPT-6 Luna ProNEWGPT-6 Luna Pro is the same underlying model as GPT-6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note…1.1M$0.10$0.50Sep 2026GPT-6 LunaNEWGPT-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…1.1M$0.10$0.50Sep 2026GPT-6 SolNEWGPT-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 su…1.1M$2.00$10.00Sep 2026Command A+NEWCommand A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calli…192K$0.30$1.50Sep 2026GPT-6 Sol ProNEWGPT-6 Sol Pro is the same underlying model as GPT-6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:*…1.1M$2.00$10.00Sep 2026Grok 4.7NEWGrok 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 en…500K$2.00$6.00Sep 2026MiMo-V2.6-ProNEWMiMo-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 fo…1.1M$0.44$0.87Sep 2026MiMo-V2.6-FlashNEWMiMo-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…1.1M$0.14$0.28Sep 2026MiMo-V2.6-Pro-UltraSpeedNEWMiMo-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 ma…1M$4.35$8.70Sep 2026Qwen3.8 Omni FlashNEWQwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding.…1M$0.15$0.47Sep 2026SwitchyardNEWSwitchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter mar…1M--Sep 2026GLM 5.3 FlashXNEWGLM-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 sam…1M$0.37$1.25Sep 2026Ternary Bonsai 2 27BNEWBonsai 2 27B is a 27B-parameter reasoning model from PrismML derived from Qwen3.8-27B. It supports coding, mathematics, tool calling, and image understanding w…262K$0.08$0.50Sep 2026ParetodeprecatedPareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of g…262K$2.50$7.50Sep 2026Union AlphadeprecatedUnion Alpha is a multimodal model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of genera…262KFreeFreeSep 2026Schematron V2 SmallSchematron V2 Small is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes extraction quality for complex schemas and long pages. E…128K$0.05$0.23Sep 2026Schematron V2 TurboSchematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extract…128K$0.03$0.15Sep 2026Fugu MaxFugu 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…1M$2.00$6.00Sep 2026Fugu Ultra v2Fugu 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 sy…1M$5.00$30.00Sep 2026DeepSeek V4.1 FlashDeepSeek 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 acti…1M$0.05$0.50Sep 2026Ling 3.0 Flash VLLing 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…131K$0.06$0.18Sep 2026Mercury 2.5Mercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces a…260K$0.04$0.15Sep 2026Nex-N2.5-MiniNex-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 exp…262K$0.03$0.10Sep 2026Nex-N2.5-ProNex-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 exp…262K$0.08$0.25Sep 2026Ling 3.0 Flash SantedeprecatedLing 3.0 Flash Sante is a health and medicine-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124…262K$0.04$0.12Sep 2026GPT-6 AstraGPT-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,…1.1M$10.00$50.00Sep 2026GPT-6 Astra ProGPT-6 Astra Pro is the same underlying model as GPT-6 Astra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost no…1.1M$10.00$50.00Sep 2026Gemini 3.8 FlashHOTGemini 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 reas…1M$0.75$3.75Sep 2026Muse Spark 1.3Muse 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 informati…1M$1.25$4.25Sep 2026Muse Spark 1.3 ContributordeprecatedMuse Spark 1.3 Contributor is the cost-efficient contributor tier of Meta’s multimodal reasoning model for experimentation, learning, and early-stage agentic,…1M$0.10$0.20Sep 2026Qwen3.8 Max (0902)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, ima…1M$2.00$6.00Sep 2026Claude Fable 5.1Claude 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: lon…1M$10.00$50.00Sep 2026Granite 4.2 8BGranite 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…131K$0.06$0.15Aug 2026Mercury 2.5 PreviewdeprecatedMercury 2.5 is the fastest reasoning LLM, and the latest diffusion LLM (dLLM) from Inception. Instead of generating tokens sequentially, Mercury 2.5 produces a…260K$0.20$0.75Aug 2026Hy4 previewTencent: 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-u…1M$0.83$2.50Aug 2026Ling 3.0 Flash FindeprecatedLing 3.0 Flash Fin is a finance-focused mixture-of-experts model from InclusionAI, built on Ling 3.0 Flash with 5.1B active parameters out of 124B total. It is…262K$0.04$0.12Aug 2026Qwen3.8 FlashQwen3.8 Flash is a multimodal reasoning model from Alibaba. It is suited for coding assistance, agentic workflows, visual understanding, document and codebase…1M$0.15$0.47Aug 2026GLM 5.3 FlashGLM-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 ar…1M$0.02$0.15Aug 2026DeepSeek V4 Flash Vision ExpDeepSeek V4 Flash Vision Exp is an experimental vision-enabled version of DeepSeek V4 Flash 0731 from DeepSeek, adding image understanding while matching the b…1M$0.22$0.65Aug 2026Hy-MT2-1.8BHy-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, wit…8K$0.04$0.18Aug 2026Hy-MT2-30B-A3BHy-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…8K$0.07$0.30Aug 2026Ox AlphadeprecatedOx Alpha is a reasoning model designed for coding, sustained agentic work, and production workloads. It is suited for long-horizon software engineering, comple…1MFreeFreeAug 2026Hy-MT2-7BHy-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…8K$0.07$0.30Aug 2026Dots3-Note Preview (free)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 D…512KFreeFreeAug 2026GLM 5.3GLM-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…1M$0.07$1.40Aug 2026Qwen3.8 27BQwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and lon…1M$0.04$2.30Aug 2026Gemini 3.7 FlashHOTGemini 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…1M$0.75$3.75Aug 2026DeepSeek V4 Pro 0813HOTDeepSeek V4 Pro 0813 is a large-scale mixture-of-experts model from DeepSeek. This is the GA release of DeepSeek V4 Pro.1M$0.10$8.00Aug 2026Grok 4.6Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.500K$2.00$6.00Aug 2026Seed 2.1 TurboSeed 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…262K$0.50$2.50Aug 2026Qwen3.8 2.4T A95BQwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of Qwen3.8 Max, with 95 billion active parameters out…1M$2.00$6.00Aug 2026Seed-2.0-CodeSeed 2.0 Code is a model from ByteDance Seed optimized for agentic coding. It is suited for frontend development, multilingual programming tasks, and coding-ag…262K$0.50$3.00Aug 2026Nemotron 3.5 LightningNVIDIA 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 age…262K$0.07$0.20Aug 2026LFM2.5-2.6BLFM2.5-2.6B is a compact reasoning model from Liquid AI. It is suited for agent workflows, data extraction, RAG, and long-context processing. Liquid advises ag…128K$0.35$0.50Aug 2026NamazudeprecatedSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts…262K$0.95$4.00Aug 2026Muse Glimmer 30BMuse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on co…131K$0.30$1.20Aug 2026Solar Pro 4Solar 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 s…524K$0.15$0.60Aug 2026Ling 3.0 Tiny (free)deprecatedLing 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction…262KFreeFreeAug 2026Muse Spark 1.2Muse 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…1M$1.25$4.25Aug 2026Muse Spark 1.2 ContributordeprecatedMuse 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 chea…1M$0.10$0.20Aug 2026Sakana NamazudeprecatedSakana Namazu is a Japanese-specialized reasoning model from Sakana AI, based on Kimi K2.6 with additional training for Japanese language and business contexts…262K$0.95$4.00Aug 2026DeepSeek V4 Flash 0423DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-to…1M$0.09$0.18Jul 2026Inkling SmallInkling 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…524K$0.45$1.20Jul 2026Claude Opus 5Claude 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 ta…1M$5.00$25.00Jul 2026Claude Opus 5 (Fast)deprecatedFast-mode variant of Opus 5 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 5. Learn more in Anthropic's docs: https:/…1M$10.00$50.00Jul 2026Ling 3.0 Flash*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 *to…262K$0.02$0.06Jul 2026Gemini 3.5 Flash LiteGemini 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 c…1M$0.30$2.50Jul 2026Gemini 3.6 FlashGemini 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…1M$0.75$3.75Jul 2026Laguna S 2.1Laguna S 2.1 is the latest coding agent model from Poolside. Laguna S 2.1 is a 118B total parameter model with 8B active parameters, scoring 70.2% on Terminal-…1M$0.09$0.18Jul 2026LongCat 2.0LongCat 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…1M$0.30$1.20Jul 2026Qwen3.8 Max (0803)deprecatedQwen3.8 Max (0803) is the August 3, 2026 checkpoint of Qwen3.8 Max, the flagship model in Alibaba's Qwen3.8 series and the general-availability successor to th…1M$2.00$6.00Jul 2026Auto Router (Beta)The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, b…2M--Jul 2026InklingInkling 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 gene…524K$1.00$4.05Jul 2026Kimi K3Kimi 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…1M$0.19$15.00Jul 2026Qwen3.7 FlashQwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with stre…1M$0.03$0.13Jul 2026KAT-Coder-Air V2.5deprecatedKAT-Coder-Air V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to au…256K$0.15$0.60Jul 2026KAT-Coder-Pro V2.5deprecatedKAT-Coder-Pro V2.5 is a flagship-level Agentic Coding model that can directly hand over an entire issue or an entire business workflow to it, allowing it to au…262K$0.74$2.96Jul 2026GPT-5.6 TerraGPT-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 every…1.1M$2.00$12.00Jul 2026GPT-5.6 SolGPT-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…1.1M$4.00$20.00Jul 2026GPT-5.6 LunaGPT-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, an…1.1M$0.20$1.20Jul 2026GPT-5.6 Luna ProGPT-5.6 Luna Pro is the same underlying model as GPT-5.6 Luna, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost…1.1M$0.20$1.20Jul 2026GPT-5.6 Sol ProGPT-5.6 Sol Pro is the same underlying model as GPT-5.6 Sol, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost no…1.1M$4.00$20.00Jul 2026GPT-5.6 Terra ProGPT-5.6 Terra Pro is the same underlying model as GPT-5.6 Terra, served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cos…1.1M$2.00$12.00Jul 2026Muse Spark 1.1Muse 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 1…1M$1.25$4.25Jul 2026Grok 4.5Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.500K$2.00$6.00Jul 2026Aion-3.0Aion-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 w…131K$3.00$6.00Jul 2026Aion-3.0-MiniAion-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 pr…131K$0.70$1.40Jul 2026Hy3Hy3 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-wor…262K$0.13$0.53Jul 2026Laguna XS 2.1Laguna XS 2.1 is the latest coding agent model in the 33B-A3B category from Poolside and a step forward from their Laguna XS.2 model (released in April 2026).…262K$0.06$0.12Jul 2026Claude Sonnet 5Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking…1M$2.00$10.00Jun 2026Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)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 r…66K$0.25$1.50Jun 2026Nex-N2-MinideprecatedNex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI, the smaller sibling in the Nex-N2 series. It accepts text and image input and is b…262K$0.03$0.10Jun 2026North Mini Code (free)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 ac…256KFreeFreeJun 2026GLM 5.2GLM 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 work…1M$0.01$7.00Jun 2026Fugu UltraFugu 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 syste…1M$5.00$30.00Jun 2026FusionFusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web f…1M--Jun 2026Kimi K2.7 CodeMoonshotAI: 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 context…262K$0.60$3.50Jun 2026Claude Fable 5Claude 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 outpu…1M$10.00$50.00Jun 2026Nex-N2-ProdeprecatedNex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total. Built on the Qwen3.5 architecture, it accepts tex…262K$0.25$1.00Jun 2026Nemotron 3 UltraNVIDIA 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 hybri…262K$0.60$2.40Jun 2026Nemotron 3.5 Content SafetyNVIDIA 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 input…131K$0.20$0.20Jun 2026Qwen3.7 PlusQwen3.7-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 capabilitie…1M$0.32$1.28Jun 2026MiniMax M3MiniMax-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…1M$0.30$1.20May 2026Claude Opus 4.8Claude 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 reaso…1M$5.00$25.00May 2026Nano Banana 2 (Gemini 3.1 Flash Image)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…131K$0.50$3.00May 2026Nano Banana Pro (Gemini 3 Pro Image)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 imp…131K$2.00$12.00May 2026Claude Opus 4.8 (Fast)deprecatedFast-mode variant of Opus 4.8 - identical capabilities with higher output speed at 2x pricing relative to regular Opus 4.8. Learn more in Anthropic's docs: htt…1M$10.00$50.00May 2026Step 3.7 FlashStep 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 n…262K$0.20$1.15May 2026Qwen3.7 MaxQwen3.7-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 s…1M$1.48$4.43May 2026Grok Build 0.1Grok Build 0.1 is SpaceXAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text out…256K$1.00$2.00May 2026Gemini 3.5 FlashGemini 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 optimize…1M$1.50$9.00May 2026Perceptron Mk1Perceptron Mk1 (Mark One) is Perceptron's highest-quality vision-language model for video and embodied reasoning.** It accepts image and video inputs paired wi…33K$0.15$1.50May 2026Ring-2.6-1TdeprecatedRing-2.6-1T is a 1T-parameter-scale thinking model with 63B active parameters, built for real-world agent workflows that require both strong capability and ope…262K$0.08$0.63May 2026Gemini 3.1 Flash LiteGemini 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,…1M$0.25$1.50May 2026GPT Chat LatestGPT Chat Latest400K$5.00$30.00May 2026Granite 4.1 8BdeprecatedGranite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window an…131K$0.05$0.10Apr 2026Nemotron 3 Nano Omni (free)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 acce…256KFreeFreeApr 2026Laguna M.1deprecatedLaguna M.1 is the flagship coding agent model from Poolside, optimized for complex software engineering tasks. Designed for agentic coding workflows, it suppor…262K$0.20$0.40Apr 2026Laguna XS.2deprecatedLaguna XS.2 is the second-generation model in the XS size class from Poolside, their efficient coding agent series. It combines tool calling and reasoning capa…262K$0.10$0.20Apr 2026Mistral Medium 3.5Mistral 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…262K$1.50$7.50Apr 2026Owl AlphaOwl Alpha is a high-performance foundation model designed for agentic workloads. Natively supports tool use, and long-context tasks, with strong performance in…1MFreeFreeApr 2026Qwen3.6 27BQwen3.6 27B is a dense 27-billion-parameter language model from the Qwen Team at Alibaba, released in April 2026. It features hybrid multimodal capabilities —…262K$0.45$2.70Apr 2026Qwen3.6 35B A3BQwen3.6-35B-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 hyb…262K$0.10$0.90Apr 2026Qwen3.6 FlashQwen3.6 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. Tier…1M$0.19$1.13Apr 2026Qwen3.6 Max PreviewdeprecatedQwen3.6-Max-Preview is a proprietary frontier model from Alibaba Cloud built on a sparse mixture-of-experts architecture with approximately 1 trillion total pa…262K$1.03$6.16Apr 2026GPT-5.5GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning, higher reliability, and improved t…1.1M$5.00$30.00Apr 2026GPT-5.5 ProGPT-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 wind…1.1M$30.00$180.00Apr 2026Ling-2.6-1TdeprecatedLing-2.6-1T is an instant (instruct) model from inclusionAI and the company’s trillion-parameter flagship, designed for real-world agents that require fast exe…262K$0.08$0.63Apr 2026Hy3 previewHy3 preview is a high-efficiency Mixture-of-Experts model from Tencent designed for agentic workflows and production use. It supports configurable reasoning le…262K$0.18$0.60Apr 2026MiMo-V2.5MiMo-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…1.1M$0.40$2.00Apr 2026MiMo-V2.5-ProMiMo-V2.5-Pro is Xiaomi’s flagship model, delivering strong performance in general agentic capabilities, complex software engineering, and long-horizon tasks,…1.1M$0.48$1.80Apr 2026GPT-5.4 Image 2deprecatedGPT-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, all…272K$8.00$15.00Apr 2026Ling-2.6-flashdeprecatedLing-2.6-flash is an instant (instruct) model from inclusionAI with 104B total parameters and 7.4B active parameters, designed for real-world agents that requi…262K$0.01$0.03Apr 2026Pareto Code RouterThe Pareto Router maintains a tiered shortlist of strong coding models, ranked by Artificial Analysis coding percentiles. Set min_coding_score between 0 and 1…2M--Apr 2026Kimi K2.6Kimi K2.6 is Moonshot AI's next-generation multimodal model, designed for long-horizon coding, coding-driven UI/UX generation, and multi-agent orchestration. I…262K$0.65$3.41Apr 2026Grok 4.3Grok 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 task…1M$1.25$2.50Apr 2026Claude Opus 4.7Opus 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…1M$5.00$25.00Apr 2026Claude Opus 4.7 (Fast)deprecatedFast-mode variant of Opus 4.7 - identical capabilities with higher output speed at premium 6x pricing. Learn more in Anthropic's docs: https://platform.claude.…1M$30.00$150.00Apr 2026GLM 5.1GLM-5.1 delivers a major leap in coding capability, with particularly significant gains in handling long-horizon tasks. Unlike previous models built around min…205K$1.40$4.40Apr 2026Gemma 4 31BGemma 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,…262K$0.20$0.40Apr 2026Gemma 4 26B A4BGemma 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 du…262K$0.07$0.23Apr 2026Qwen3.6 PlusQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and…1M$0.33$1.95Apr 2026GLM 5V TurboGLM-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,…203K$1.20$4.00Apr 2026Trinity Large ThinkingdeprecatedTrinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and r…262K$0.25$0.80Apr 2026Grok 4.20Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on th…2M$1.25$2.50Mar 2026Lyria 3 Clip Previewdeprecated30 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, y…1MFreeFreeMar 2026Lyria 3 Pro PreviewdeprecatedFull-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…1MFreeFreeMar 2026KAT-Coder-Pro V2deprecatedKAT-Coder-Pro V2 is the latest high-performance model in KwaiKAT’s KAT-Coder series, designed for complex enterprise-grade software engineering and SaaS integr…262K$0.30$1.20Mar 2026Reka EdgeReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs. This model is optimize…16K$0.10$0.10Mar 2026MiniMax M2.7MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement. Built to actively participa…205K$0.30$1.20Mar 2026GPT-5.4 MiniGPT-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 inpu…400K$0.75$4.50Mar 2026GPT-5.4 NanoGPT-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…400K$0.20$1.25Mar 2026Mistral Small 4Mistral 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 co…262K$0.15$0.60Mar 2026GLM 5 TurboGLM-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 o…203K$1.20$4.00Mar 2026Nemotron 3 SuperNVIDIA Nemotron 3 Super is a 120B-parameter open hybrid MoE model, activating just 12B parameters for maximum compute efficiency and accuracy in complex multi-…1M$0.30$2.40Mar 2026Qwen3.5-9BQwen3.5-9B is a multimodal foundation model from the Qwen3.5 family, designed to deliver strong reasoning, coding, and visual understanding in an efficient 9B-…262K$0.17$0.25Mar 2026Seed-2.0-LiteSeed-2.0-Lite is a versatile, cost‑efficient enterprise workhorse that delivers strong multimodal and agent capabilities while offering noticeably lower latenc…262K$0.25$2.00Mar 2026200 models · sorted by release date · prices in USD per 1M tokens · refreshed hourlyCompare every model across vendors ->
Get started in 3 steps
1
Create an API key at the OpenRouter console.
2
Paste it into Big-AGI's model settings.
3
Start chatting, or Beam it against other models and fuse the answers.
Running OpenRouter in Big-AGI
One OpenRouter key, and Big-AGI adds no markup and no intermediary: the billing relationship runs directly between you and OpenRouter. You bring the aggregator, Big-AGI brings the workspace.
- Vendor-accurate controls, even through the router. Big-AGI recognizes anthropic/, google/, and openai/ model IDs on OpenRouter and applies its own detailed native definitions, correct thinking budgets and effort levels, instead of the aggregator's flattened metadata.
- Full parameter control. Big-AGI exposes the parameters OpenRouter forwards: reasoning effort, verbosity, temperature, and top-p, at their extended ranges.
- Fallback routing. When a provider degrades or a model goes unavailable, OpenRouter reroutes to a healthy backup, so your prompt still lands.
Your keys and your data
Your keys stay in your browser, not on Big-AGI's servers. Chats are stored locally first, and sync only if you turn it on. Nothing is added to your system prompt, and the AI Inspector shows the exact request, the token counts, and a cost estimate for every call.
OpenRouter in Beam
This is the part a router cannot do for you. Send one prompt to models from different providers at once, Anthropic next to OpenAI next to an open model OpenRouter hosts. Where they agree, you can trust the answer. Where they differ, you have caught something worth a second look. Fusions then combine, cross-check, and synthesize the parallel answers instead of just picking the best one. Big-AGI has shipped and refined this workflow since 2024. Parallel runs use more tokens than a single chat.
Big-AGI is an independent, open-source client. It is not affiliated with or endorsed by OpenRouter.
OpenRouter questions
FAQ
Why is a free OpenRouter model slow in Big-AGI?
On purpose. OpenRouter caps its no-charge models per minute and per day, so Big-AGI spaces its own calls to them about five seconds apart instead of collecting rate-limit errors. That is pacing, not a fault.
Where do I get an OpenRouter API key, and what does it look like?
Press Link OpenRouter Key in Big-AGI's setup panel: you authorise at OpenRouter and the key comes back installed, no copy-paste. Or create one at openrouter.ai/keys; it reads sk-or-v1-... and is shown once, so copy it before leaving the page.
Does OpenRouter accept direct browser calls from Big-AGI?
Yes. OpenRouter is one of the services Direct Connection supports: turn it on in the OpenRouter setup panel once the key is in the browser, and requests go browser-to-OpenRouter, skipping the Big-AGI edge. It starts off.
Do I need OpenRouter credits before the first message?
Not for the no-charge models: they answer on a low daily cap with no deposit. Real use runs on prepaid credits added at openrouter.ai/settings/credits, and that balance is the spending limit unless auto top-up is on, which refills it.
Bring your OpenRouter key. Keep control.
Your key, your data, your choice of model. Big-AGI's Open branch is open source and self-hostable, so you can check exactly how OpenRouter is called.
Launch Big-AGIBIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego