Search the live AIVAX catalog before a workload commits to a provider, context window or capability set. Every row below comes from the public catalog during this build.
Integrated models use the AIVAX balance. BYOK keeps the provider contract and model bill with you.
Models are ordered by published release date, newest first. Prices
are USD per million tokens; From marks a context-dependent tier.
Available AIVAX models ordered by release date, with capabilities, context, token pricing and lifecycle status
@model-router/openai:budgetRoute between latest budget OpenAI models.
@model-router/openai:frontierRoute between latest frontier OpenAI models.
@model-router/openai:midRoute between latest mid-tier OpenAI models.
@openai/gpt-5.6-lunaGPT-5.6 Luna is OpenAI's fast, cost-efficient GPT-5.6 model for high-volume chat, classification, and lightweight agentic workflows.
@openai/gpt-5.6-luna:proGPT-5.6 Luna is OpenAI's fast, cost-efficient GPT-5.6 model for high-volume chat, classification, and lightweight agentic workflows.
@openai/gpt-5.6-solGPT-5.6 Sol is OpenAI's flagship GPT-5.6 model for complex reasoning, coding, and agentic workflows.
@openai/gpt-5.6-sol:proGPT-5.6 Sol is OpenAI's flagship GPT-5.6 model for complex reasoning, coding, and agentic workflows.
@openai/gpt-5.6-terraGPT-5.6 Terra is OpenAI's balanced GPT-5.6 model for everyday coding, reasoning, and agentic tasks.
@openai/gpt-5.6-terra:proGPT-5.6 Terra is OpenAI's balanced GPT-5.6 model for everyday coding, reasoning, and agentic tasks.
@model-router/grok:latestRoute between latest Grok models.
@x-ai/grok-4.5Grok 4.5 is xAI's smartest model with frontier performance on coding, knowledge work, and STEM.
@aion-labs/aion-3.0Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models.
@aion-labs/aion-3.0-miniAion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models.
@tencent/hy3Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent, built for reasoning, agentic workflows, and real-world production use.
@poolside/laguna-xs-2.1Laguna XS 2.1 is Poolside's compact coding agent model in the 33B-A3B category, combining tool calling and reasoning for agentic software engineering tasks.
@anthropic/claude-5-sonnetClaude Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
@model-router/claude:midRoute between latest mid-tier Claude models.
@nex-agi/nex-n2-miniNex-N2-Mini is an open-source agentic mixture-of-experts model from Nex AGI for coding, tool use, deep research, and long-horizon agentic workflows.
@model-router/glm:latestRoute between latest GLM models.
@z-ai/glm-5.2GLM-5.2 is Z.ai's flagship model for long-horizon tasks, with a usable 1M-token context window for project-level engineering context and long-running agent workflows.
@model-router/kimi:latestRoute between latest Kimi models.
@moonshotai/kimi-k2.7-codeKimi 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.
@anthropic/claude-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 output, with reasoning support and a 1M-token context window.
@nex-agi/nex-n2-proNex-N2-Pro is an agentic mixture-of-experts model from Nex AGI, with 17B active parameters out of 397B total, built for coding, tool use, and long-horizon agentic workflows.
@nvidia/nemotron-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 hybrid Transformer-Mamba mixture-of-experts architecture.
@qwen/qwen3.7-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 capabilities with a comprehensive upgrade to its vision-language abilities.
@minimax/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 for long-horizon agentic work, coding, and tool use.
@model-router/minimax:latestRoute between latest MiniMax models.
@anthropic/claude-4.8-opusClaude 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 context window.
@model-router/claude:frontierRoute between latest frontier Claude models.
@qwen/qwen3.7-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 strengths in coding, office and productivity tasks, and long-horizon autonomous agents.
@x-ai/grok-build-0.1Grok Build 0.1 is xAI’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 agents, tool use, and multi-step development.
@google/gemini-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.
@model-router/google:midRoute between latest mid-tier Google models.
@google/gemini-3.1-flash-liteGemini 3.1 Flash Lite Preview is Google's high-efficiency model optimized for high-volume use cases.
@model-router/google:budgetRoute between latest budget Google models.
@x-ai/grok-4.3Grok 4.3 is a reasoning model from xAI. It accepts text and image inputs with text output, and is suited for agentic workflows, instruction-following tasks, and applications requiring high factual logic.
@qwen/qwen3.6-27bQwen3.6 27B is a dense 27-billion-parameter model from Alibaba Qwen, designed for agentic coding, long-context reasoning, and multimodal workflows.
@deepseek/deepseek-v4-flashAn efficiency-optimized Mixture-of-Experts model from DeepSeek designed for fast inference and high-throughput workloads.
@deepseek/deepseek-v4-proDeepSeek V4 Pro is a large-scale Mixture-of-Experts model designed for advanced reasoning, coding, and long-horizon agent workflows with 1.6T total parameters.
@model-router/deepseek:latestRoute between latest DeepSeek models.
@openai/gpt-5.5GPT-5.5 is OpenAI’s frontier model designed for complex professional workloads, building on GPT-5.4 with stronger reasoning and higher reliability.
@openai/gpt-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 window.
@model-router/xiaomi:budgetRoute between latest budget Xiaomi models.
@model-router/xiaomi:frontierRoute between latest frontier Xiaomi models.
@model-router/xiaomi:midRoute between latest mid-tier Xiaomi models.
@xiaomi/mimo-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 multimodal perception across image and video understanding tasks.
@xiaomi/mimo-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, with top rankings on benchmarks such as ClawEval, GDPVal, and SWE-bench Pro.
@moonshotai/kimi-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.
@anthropic/claude-4.7-opusOpus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents.
@z-ai/glm-5.1GLM-5.1 represents a major advance in coding ability, with especially notable improvements in tackling long-horizon tasks.
@moonshotai/kimi-k2.5:fastKimi K2.5 turbo is a high-performance variant of the Kimi K2.5 model, optimized for faster processing and enhanced capabilities.
@google/gemma-4-26b-a4b-itGemma 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 a fraction of the compute cost. Supports multimodal input including text, images, and video.
@google/gemma-4-31b-itGemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input. Strong on coding, reasoning, and document understanding tasks with multilingual support across 140+ languages.
@qwen/qwen3.6-plusQwen 3.6 Plus builds on a hybrid architecture that combines efficient linear attention with sparse mixture-of-experts routing, enabling strong scalability and high-performance inference.
@arcee-ai/trinity-large-thinkingTrinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks.
@x-ai/grok-4.20-multi-agentGrok 4.20 Multi-Agent Beta is a variant of xAI’s Grok 4.20 designed for collaborative, agent-based workflows.
@x-ai/grok-4.20-reasoningGrok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities.
@reka/reka-edgeReka Edge is an extremely efficient 7B multimodal vision-language model that accepts image/video+text inputs and generates text outputs.
@openai/gpt-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.
@openai/gpt-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.
@z-ai/glm-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.
@x-ai/grok-4.20Grok 4.20 Beta is xAI's newest flagship model with industry-leading speed and agentic tool calling capabilities.
@qwen/qwen3.5-9bQwen3.5 9B is an efficient multimodal model from the Qwen3.5 family for low-cost reasoning, coding, and visual understanding workloads.
@openai/gpt-5.4GPT-5.4 is OpenAI’s latest frontier model, unifying the Codex and GPT lines into a single system.
@openai/gpt-5.4-proGPT-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.
@inception/mercury-2The fastest reasoning LLM and Inception most powerful model.
@openai/gpt-5.3-chatGPT-5.3 Chat is an update to ChatGPT's most-used model that makes everyday conversations smoother, more useful, and more directly helpful.
@bytedance/seed-2.0-miniSeed-2.0-mini targets latency-sensitive, high-concurrency, and cost-sensitive scenarios, emphasizing fast response and flexible inference deployment.
@qwen/qwen3.5-27bThe 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 the Qwen3.5-122B-A10B.
@qwen/qwen3.5-flashThe 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.
@google/gemini-3.1-proGemini 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.
@model-router/google:frontierRoute between latest frontier Google models.
@anthropic/claude-4.6-sonnetSonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work.
@qwen/qwen3.5-397b-a17bThe 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.
@qwen/qwen3.5-plusThe 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.
@minimax/m2.5MiniMax-M2.5 is a state-of-the-art large language model built for real-world productivity.
@minimax/m2.7MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.
@z-ai/glm-5GLM-5 is Z.ai’s flagship open-source foundation model engineered for complex systems design and long-horizon agent workflows.
@anthropic/claude-4.6-opusOpus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks.
@moonshotai/kimi-k2.5Kimi K2.5 is Moonshot AI's native multimodal model, delivering state-of-the-art visual coding capability and a self-directed agent swarm paradigm.
@z-ai/glm-4.7-flashAs a SOTA 30B-class model, GLM-4.7-Flash provides a new option that balances efficiency and performance.
@openai/gpt-5.2-codexGPT-5.2-Codex is an enhanced version of GPT-5.1-Codex, optimized for software engineering and coding tasks.
@openai/gpt-5.3-codexGPT-5.3-Codex is OpenAI’s most advanced agentic coding model. It pairs the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2.
@minimax/m2.1MiniMax-M2.1 is a cutting-edge, lightweight large language model designed for coding, agentic workflows, and modern application development.
@z-ai/glm-4.7GLM-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.
@google/gemini-3-flashGemini 3 Flash Preview is a high speed, high value thinking model designed for agentic workflows, multi turn chat, and coding assistance.
@openai/gpt-5.2-proGPT-5.2 Pro is OpenAI's most advanced model, featuring significant upgrades in agentic coding and long-context capabilities compared to GPT-5 Pro.
@openai/gpt-5.2GPT-5.2 is the newest frontier-level model in the GPT-5 line, providing enhanced agentic abilities and better long-context performance than GPT-5.1.
@openai/gpt-5.2-chatGPT-5.2 Chat (also known as Instant) is the fast and lightweight version of the 5.2 family, built for low-latency chatting while maintaining strong general intelligence.
@openai/gpt-5.1-codex-maxGPT-5.1-Codex-Max is OpenAI’s latest agentic coding model, designed for long-running, high-context software development tasks.
@deepseek/v3.2DeepSeek-V3.2 is a large language model optimized for high computational efficiency and strong tool-use reasoning.
@mistral/large-2512Mistral Large 3 2512 is Mistral’s most capable model to date, featuring a sparse mixture-of-experts architecture with 41B active parameters (675B total).
@anthropic/claude-4.5-opusClaude Opus 4.5 is Anthropic’s latest reasoning model, developed for advanced software engineering, complex agent workflows, and extended computer tasks.
@openai/gpt-5.1GPT-5.1 is the newest top-tier model in the GPT-5 series, featuring enhanced general reasoning, better instruction following, and a more natural conversational tone compared to GPT-5.
@openai/gpt-5.1-chatGPT-5.1 Chat (also known as Instant) is the fast, lightweight member of the 5.1 family, optimized for low-latency chat while retaining strong general intelligence.
@openai/gpt-5.1-codexGPT-5.1-Codex is a specialized version of GPT-5.1 optimized for software engineering and coding workflows.
@moonshotai/kimi-k2-thinkingKimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning.
@anthropic/claude-4.5-haikuClaude Haiku 4.5 is Anthropic’s fastest and most efficient model, offering near-frontier intelligence with much lower cost and latency than larger Claude models.
@model-router/claude:budgetRoute between latest budget-tier Claude models.
@z-ai/glm-4.6GLM‑4.6 is a high‑capacity LLM with a 200K‑token context window, strong coding and reasoning abilities, and enhanced tool‑use capabilities.
@anthropic/claude-4.5-sonnetClaude Sonnet 4.5 is the newest model in the Sonnet series, offering improvements and updates over Sonnet 4.
@openai/gpt-5-codexGPT-5-Codex is a specialized version of GPT-5 tailored for software engineering and coding tasks.
@qwen/qwen3-maxQwen3-Max improves instruction following, multilingual ability, and tool use; reduced hallucinations.
@deepseek/v3.1-terminusDeepSeek-V3.1 is post-trained on the top of DeepSeek-V3.1-Base, which is built upon the original V3 base checkpoint through a two-phase long context extension approach, following the methodology outlined in the original DeepSeek-V3 report.
@moonshotai/kimi-k2Model with 1tri total parameters, 32bi activated parameters, optimized for agentic intelligence.
@openai/gpt-5OpenAI's newest flagship model for coding, reasoning, and agentic tasks across domains.
@openai/gpt-5-chatGPT-5 snapshot currently used by OpenAI's ChatGPT.
@openai/gpt-5-miniGPT-5 mini is a faster, more cost-efficient version of GPT-5.
@openai/gpt-5-nanoOpenAI's fastest, cheapest version of GPT-5.
@anthropic/claude-4.1-opusClaude Opus 4.1 is Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks.
@openai/gpt-oss-120bOpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 120 billion parameters and 128 experts.
@openai/gpt-oss-20bOpenAI's flagship open source model, built on a Mixture-of-Experts (MoE) architecture with 20 billion parameters and 128 experts.
@google/gemini-2.5-flash-liteA Gemini 2.5 Flash model optimized for cost efficiency and low latency.
@inception/mercuryExtremely fast model by generative diffusion.
@google/gemini-2.5-flashGoogle's best model in terms of price-performance, offering well-rounded capabilities. 2.5 Flash is best for large scale processing, low-latency, high volume tasks that require thinking, and agentic use cases.
@google/gemini-2.5-proOne of the most powerful models today.
@deepseek/r1The DeepSeek R1 model has undergone a minor version upgrade, with the current version being DeepSeek-R1-0528.
@anthropic/claude-4-sonnetAnthropic's mid-size model with superior intelligence for high-volume uses in coding, in-depth research, agents, & more.
@openai/o3A well-rounded and powerful model across domains. It sets a new standard for math, science, coding, and visual reasoning tasks.
@openai/o4-miniOptimized for fast, effective reasoning with exceptionally efficient performance in coding and visual tasks.
@openai/gpt-4.1Versatile, highly intelligent, and top-of-the-line. One of the most capable models currently available.
@openai/gpt-4.1-miniFast and cheap for focused tasks.
@openai/gpt-4.1-nanoThe fastest and cheapest GPT 4.1 model.
@cohere/command-aCommand A is Cohere's most performant model to date, excelling at tool use, agents, retrieval augmented generation (RAG), and multilingual use cases. Command A has a context length of 256K, only requires two GPUs to run, and has 150% higher throughput compared to Command R+ 08-2024.
@perplexity/sonar-proSonar Pro is an enterprise-grade API from Perplexity, built for advanced, multi-step queries with added extensibility.
@openai/o3-minio3-mini provides high intelligence at the same cost and latency targets of previous versions of o-mini series.
@perplexity/sonarSonar is Perplexity’s lightweight, affordable, and fast question-answering model, now featuring citations and customizable sources.
@metaai/llama-3.3-70bPrevious generation model with many parameters and surprisingly fast speed.
@amazon/nova-liteA very low cost multimodal model that is lightning fast for processing image, video, and text inputs.
@amazon/nova-proA highly capable multimodal model with the best combination of accuracy, speed, and cost for a wide range of tasks.
@anthropic/claude-3.5-haikuClaude 3.5 Haiku is the next generation of our fastest model. For a similar speed to Claude 3 Haiku, Claude 3.5 Haiku improves across every skill set and surpasses Claude 3 Opus, the largest model in our previous generation, on many intelligence benchmarks.
@metaai/llama-3.1-8bCheap and fast model for less demanding tasks.
@openai/gpt-4o-miniSmaller version of 4o, optimized for everyday tasks.
@openai/gpt-4oDedicated to tasks requiring reasoning for mathematical and logical problem solving.
@amazon/nova-microA text-only model that delivers the lowest latency responses at very low cost.
@minimax/m2MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.
@mistral/nemo-12b-it-240712B model trained jointly by Mistral AI and NVIDIA, it significantly outperforms existing models smaller or similar in size.
@model-router/complexityModel Router: chooses the best models according to the complexity of the conversation.
@openai/gpt-5.1-codex-miniGPT-5.1-Codex-Mini is a more compact and faster variant of GPT-5.1-Codex.
@qwen/qwen3-32b32B-parameter LLM with a 131K-token context window, offering advanced chain-of-thought reasoning, seamless tool calling, native JSON outputs, and robust multilingual fluency.
@qwen/qwen3-coder-480b-a35b-itQwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.
@qwen/qwen3-coder-plusPowered by Qwen3, this is a powerful Coding Agent that excels in tool calling and environment interaction to achieve autonomous programming.
@qwen/qwen3-next-80b-a3b-itAn 80 B-parameter instruction model with hybrid attention and Mixture‑of‑Experts, optimized for ultra‑long contexts up to 262 k tokens.
@qwen/qwen3-next-80b-a3b-thinkA 80 B‑parameter “thinking‑only” model with hybrid attention and high‑sparsity MoE, designed for deep reasoning over ultra‑long contexts.
@anthropic/claude-3-haikuClaude 3 Haiku is Anthropic's fastest model yet, designed for enterprise workloads which often involve longer prompts.
@venice/dphn-24b-uncensoredVenice Uncensored is a fine-tuned version of Mistral-Small-24B-Instruct-2501, created by dphn.ai in partnership with Venice.ai.
No models match this combination of search and filters.
Cached-input and audio-input rates are published only when they apply. Open the source record before final cost modelling, especially for models with multiple token thresholds.