The model market on one key.

Claude Opus 5.5

Anthropic

Anthropic Claude Opus 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

GPT-6 Astra

OpenAI

OpenAI GPT-6 Astra text model. Available over the Chat Completions protocol.

GPT-6.1 Sol

OpenAI

OpenAI GPT-6.1 Sol text model. Available over the Chat Completions and Responses protocols.

Claude Sonnet 5.5

Anthropic

Anthropic Claude Sonnet 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

GPT-6.1 Terra

OpenAI

OpenAI's fast, lower-cost GPT-6.1 model for computer use, visual reasoning, agentic tasks and natural writing. 1.05M-token context, up to 128K output tokens.

Gemini 4 Argon

Google

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents. It has a 1M-token context, reads text, images, video, audio and PDF, and supports reasoning at low, medium and high effort, tool calling and structured output.

Claude Fable 5.1

Anthropic

Anthropic Claude Fable 5.1 text model. Available over the Anthropic Messages and Chat Completions protocols.

Kimi K3.1 Pro

Moonshot AI

Moonshot AI's new flagship, a post-trained successor to Kimi K3 with open weights. A multimodal reasoning model with a 1M-token context: it reads text, images and video and is built for long-horizon coding and agent work that runs over many steps. Reasoning effort is adjustable; tool calling and structured output are supported.

GPT-6 Sol

OpenAI

OpenAI GPT-6 Sol text model. Available over the Chat Completions protocol.

Claude Haiku 5.5

Anthropic

Anthropic Claude Haiku 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

Grok 4.7

xAI

xAI Grok 4.7 text model. Available over the Chat Completions and Responses protocols.

GPT-5.6 Terra

OpenAI

OpenAI GPT-5.6 Terra text model. Available over the Chat Completions protocol.

Span-02

Respan

An open-weight decision model from Respan. It reads a state of text and images and answers the questions you define about it — picking one of several options, a yes/no probability or a score — with calibrated probabilities.

Decider Flash V1.2

Perplexity

A 4B decision model from Perplexity, the smaller, lower-cost sibling of Decider V1.2 with the same API contract. It reads a state of text or images and returns calibrated probabilities for typed questions.

D1

Liquid AI

Liquid AI's structured decision model, served as a System One endpoint. Send a state of text or images with typed questions and it returns a choice, a score or a yes/no probability instead of generated text.

Span-01

Respan

Respan's behaviour scoring model. It reads a conversation span and returns, for each plain-language behaviour you define, the probability that the behaviour is present.

Decider V1.2

Perplexity

A 27B checkpoint of Perplexity's decision model, successor to Decider V1.1. Instead of generating text, it reads content passed as state — text or images — and returns calibrated probabilities for typed questions.

Mercury Decide

Inception

Inception's structured decision model, served as a System One endpoint. Send a state of text or images with typed questions and it returns a choice, a score or a yes/no probability instead of generated text.

OpenJev Small

RawModels

A lighter OpenJev on Qwen3.5 0.8B: faster and half the price, weaker on multi-step policies and on reading values off images. It reads a state — text, JSON, an image or a video — and answers typed questions with probabilities: yes/no, a choice between options or a score. 32K-token context. Models run on GPUs that are started on demand, so the first request after a quiet spell waits for a worker to boot — usually one to five minutes. Everything after that answers in seconds.

Clef Flash

Cloudflare

The fast 9B member of Cloudflare's open-source Clef decision family, a fine-tune of Qwen3.5-9B served on Workers AI. It reads a state of text, JSON or images and returns calibrated probabilities for yes/no, choice and score questions at low latency.

Mercury 2.5

Inception

A diffusion language model from Inception: instead of writing tokens one after another, it drafts and refines many tokens in parallel, reaching over 1,000 tokens per second on standard GPUs. It offers adjustable reasoning, parallel tool calls and schema-conforming JSON, and suits latency-sensitive uses such as search agents, voice pipelines and coding sub-agents. Text only, with a 260K-token context.

Drex v1.5

Nace.AI

A 9B decision model from Nace.AI. Given a state (text or JSON) and typed questions — yes/no, multiple choice or ordinal score — it returns a calibrated probability for each answer.

Classify-1

ScaleDown

A structured decision model from ScaleDown. It scores text, images or a document against caller-defined choice, yes/no and ordered-scale questions and returns calibrated probabilities; it holds a 1M-token state.

Clef

Cloudflare

Cloudflare's open-source 27B multimodal decision model, a fine-tune of Qwen3.8-27B served on Workers AI. Instead of writing text, it reads a state (text, structured JSON or images) and answers typed questions with calibrated probabilities: yes/no, a choice between options, or a score.

Claude Fable 5.2

Anthropic

Anthropic's model for demanding reasoning and long-horizon agentic work. 1M-token context, up to 128K output tokens. Available over the Anthropic Messages and Chat Completions protocols.

GPT-6.1 Terra

OpenAI

OpenAI's fast, lower-cost GPT-6.1 model for computer use, visual reasoning, agentic tasks and natural writing. 1.05M-token context, up to 128K output tokens.

Kimi K3.1 Pro

Moonshot AI

Moonshot AI's new flagship, a post-trained successor to Kimi K3 with open weights. A multimodal reasoning model with a 1M-token context: it reads text, images and video and is built for long-horizon coding and agent work that runs over many steps. Reasoning effort is adjustable; tool calling and structured output are supported.

Qwen Image 2.1 Pro

Qwen

The higher-quality tier of Alibaba's Qwen Image 2.1 series for text-to-image generation, with more quality and detail than Turbo. Up to 2K resolution with many aspect ratios.

Qwen Image 2.1 Turbo

Qwen

The fast, low-cost tier of Alibaba's Qwen Image 2.1 series for text-to-image generation, when throughput and price matter more than peak quality. Up to 2K resolution with many aspect ratios.

Span-02

Respan

An open-weight decision model from Respan. It reads a state of text and images and answers the questions you define about it — picking one of several options, a yes/no probability or a score — with calibrated probabilities.

Decider V1.2

Perplexity

A 27B checkpoint of Perplexity's decision model, successor to Decider V1.1. Instead of generating text, it reads content passed as state — text or images — and returns calibrated probabilities for typed questions.

Decider Flash V1.2

Perplexity

A 4B decision model from Perplexity, the smaller, lower-cost sibling of Decider V1.2 with the same API contract. It reads a state of text or images and returns calibrated probabilities for typed questions.

D1 Ultra

Liquid AI

Liquid AI's largest decision model, served as a System One endpoint. It reads a state of text and images with typed questions and returns a choice, a score or a yes/no probability, with more accuracy than d1 on harder judgements.

Jev 1.14

TypeSafe

The latest version of Jev, TypeSafe's structured decision model. It reads a state of text or images with typed questions and returns calibrated probabilities for a choice, a score or a yes/no answer, built for fast decisions inside software.

Gemini 4 Argon

Google

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents. It has a 1M-token context, reads text, images, video, audio and PDF, and supports reasoning at low, medium and high effort, tool calling and structured output.

Classify-1

ScaleDown

A structured decision model from ScaleDown. It scores text, images or a document against caller-defined choice, yes/no and ordered-scale questions and returns calibrated probabilities; it holds a 1M-token state.

Mercury 2.5

Inception

A diffusion language model from Inception: instead of writing tokens one after another, it drafts and refines many tokens in parallel, reaching over 1,000 tokens per second on standard GPUs. It offers adjustable reasoning, parallel tool calls and schema-conforming JSON, and suits latency-sensitive uses such as search agents, voice pipelines and coding sub-agents. Text only, with a 260K-token context.

Claude Haiku 5.5

Anthropic

Anthropic Claude Haiku 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

Inkling

Thinking Machines

Thinking Machines Lab publishes the weights of Inkling, a multimodal MoE network with 975B total and 41B active parameters. It is a general model for reasoning, coding, agents, retrieval-augmented generation and multilingual chat, and it natively understands images and audio. Context is 512K tokens; tool calling is supported.

Command A+

Cohere

Cohere's top model for enterprise agents. It reads text and images, offers a 192K-token context, native tool calling with strict schemas, JSON object and JSON schema output, optional reasoning and adjustable safety modes.

Mistral Medium 3.5

Mistral AI

A dense 128B-parameter open-weight model from Mistral AI aimed at agents, coding and multi-step reasoning. It accepts text and images, has a 256K-token context and lets the caller set reasoning effort per request. Its main strength is dependable calling of several tools within one long task.

Mistral Small 4

Mistral AI

A compact Mistral AI model (snapshot 2603) that merges reasoning, image understanding and agentic coding into a single system, so one model can cover analysis, software work and visual input. It has a 256K-token context and supports tool calling.

Claude Sonnet 5.5

Anthropic

Anthropic Claude Sonnet 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

GPT-6 Luna

OpenAI

OpenAI GPT-6 Luna text model. Available over the Chat Completions protocol.

Gemini 3.8 Flash

Google

Google Gemini 3.8 Flash text model. Available over the Chat Completions and Responses protocols.

GPT-6.1 Terra

OpenAI

OpenAI's fast, lower-cost GPT-6.1 model for computer use, visual reasoning, agentic tasks and natural writing. 1.05M-token context, up to 128K output tokens.

MiniMax M3

MiniMax

MiniMax's multimodal base model for long agent sessions, coding and tool use; it reads text, images and video. MiniMax Sparse Attention picks only relevant KV blocks instead of attending to everything, which makes 1M-token inputs far cheaper and faster to process than in the previous generation. Supports tool calling.

Claude Opus 5.5

Anthropic

Anthropic Claude Opus 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

Claude Opus 5.5

Anthropic

Anthropic Claude Opus 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

Claude Sonnet 5.5

Anthropic

Anthropic Claude Sonnet 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

Claude Haiku 5.5

Anthropic

Anthropic Claude Haiku 5.5 text model. Available over the Anthropic Messages and Chat Completions protocols.

Claude Sonnet 5

Anthropic

Anthropic Claude Sonnet 5 text model. Available over the Chat Completions, Responses and Anthropic Messages protocols.

DeepSeek V4.1 Flash

DeepSeek

The economy tier of DeepSeek's V4.1 family: a sparse mixture-of-experts model on a 552B-parameter backbone that activates about 8B parameters for input and 16B for output. Image understanding is trained in from the start, and a compressed KV cache lowers the cost of long agent sessions. It fits agents that write code, drive a terminal or operate a computer, as well as long-document analysis, with a 1M-token context and tool calling.

GPT-6.1 Sol

OpenAI

OpenAI GPT-6.1 Sol text model. Available over the Chat Completions and Responses protocols.

Kimi K3.1 Pro

Moonshot AI

Moonshot AI's new flagship, a post-trained successor to Kimi K3 with open weights. A multimodal reasoning model with a 1M-token context: it reads text, images and video and is built for long-horizon coding and agent work that runs over many steps. Reasoning effort is adjustable; tool calling and structured output are supported.

Gemini 4 Argon

Google

Google's flagship reasoning model for complex software engineering, deep math and science, and long-horizon autonomous agents. It has a 1M-token context, reads text, images, video, audio and PDF, and supports reasoning at low, medium and high effort, tool calling and structured output.

Gemini 3.8 Flash

Google

Google Gemini 3.8 Flash text model. Available over the Chat Completions and Responses protocols.

DeepSeek V4 Pro 0813

DeepSeek

The generally available August 2026 snapshot (0813) of DeepSeek V4 Pro, the larger mixture-of-experts model of the V4 line. It is a general text model for reasoning, coding and agent tasks, with a 1M-token context and support for tool calling.

Claude Opus 5

Anthropic

Anthropic Claude Opus 5 text model. Available over the Anthropic Messages and Chat Completions protocols.

GPT-6 Luna

OpenAI

OpenAI GPT-6 Luna text model. Available over the Chat Completions protocol.