New chatOne prompt, one model, any model in the catalog CouncilThree models answer, one writes the verdict Jev DecisionsTyped answers with probabilities, no text Perplexity DeciderPerplexity's decision model, same contract as Jev

How the council works →

Text & code

Claude Haiku 5.5$0.1/Mtok in · 7 Oct Mistral Large 4$0.68/Mtok in · 6 Oct Gemini 4 Argon soonTracking availability

Claude Sonnet 5.5$2/Mtok in · 28 Sep GPT-4.1 mini$0.4/Mtok in · 27 Sep GLM-5.3$1.4/Mtok in · 23 Sep

MiMo-V2.5-Pro$0.435/Mtok in · 23 Sep Muse Spark 1.3$1.25/Mtok in · 23 Sep GPT-6 Luna$0.1/Mtok in · 22 Sep

Decision models

Jev · TypeSafe · $0.042/Mtok inNot a chat model. Send text plus typed questions and get calibrated probabilities back. Use it to route, triage or gate a request before an expensive call.Decider 27B · Perplexity · $0.04/Mtok inNot a chat model. Send text plus typed questions and get calibrated probabilities back. Use it to route, triage or gate a request before an expensive call.

Try the playground →Docs Pricing & API

All models, newest first →Best for coding Best for reasoning Best for writing Cheapest Open source Free

Tools

Claude CodeAny model in Claude Code, one key CursorAny model in Cursor, one key ClineAny model in Cline, one key ContinueAny model in Continue, one key AiderAny model in Aider, one key OpenClawAny model in OpenClaw, one key MuseAny model in Muse, one key

Popular pairings

Gemini in Claude CodeSetup in under two minutes DeepSeek in Claude CodeSetup in under two minutes Kimi in Claude CodeSetup in under two minutes GPT-5.5 in Claude CodeSetup in under two minutes

All integrations →

Model vs model

Claude Haiku 4.5 vs DeepSeek V4.1 FlashAnthropic against DeepSeek GPT-6 Luna vs MiMo-V2.6-ProOpenAI against Xiaomi GLM-5.3-Flash vs Mistral Large 4Z.ai against Mistral GPT-6 Sol vs Muse Spark 1.3OpenAI against Meta Claude Haiku 5.5 vs Grok 4.3Anthropic against xAI All comparisonsEvery pair, priced from the live catalog

Gateways

vs OpenRouterBoth route the major models behind one OpenAI-compatible key vs LiteLLMLiteLLM is a self-hosted proxy you operate; CompanyFabric is a hosted gateway with billing built in vs LLMGatewayBoth are OpenAI-compatible gateways vs PortkeyPortkey is an AI ops control plane, observability, guardrails, routing policies

Alternatives

CodeRabbit alternativeCodeRabbit charges per seat for AI code review Viktor alternativeViktor sells AI employees in Slack at enterprise pricing OpenRouter alternativeLooking for an OpenRouter alternative? CompanyFabric routes text and code behind one key, with BYOK at 0% platform fee

All comparisons →

Documentation

QuickstartFirst call in under three minutes AuthenticationKeys, budget caps, revocation Chat CompletionsOpenAI-compatible /v1/chat/completions Models & IDsGET /v1/models, ids, aliases, meta-models Jev DecisionsTyped answers with probabilities, no text For agentsMCP server, skills, machine-readable prices llms.txtEvery page, indexed for agents

Log in Register

Chat Models Compare Pricing Docs

Council Claude Code Cursor Cheapest models Best for coding For agents Free models

Log in Register

Models / Providers

Claude models

Every Claude model available through the API, published by Anthropic, same key, same balance, exact prices shown before each call.

Anthropic

Available models

Claude Haiku 5.5

Anthropic

Anthropic's cheapest and fastest Claude: a big step up from Haiku 4.5 in coding, computer use and knowledge work, at $0.10 / $0.50 per 1M tokens for prompts up to 100K.

Added 7 Oct 2026 · text

Claude Sonnet 5.5

Anthropic

The fast Claude 5.5: near-Opus coding and knowledge work, 30%+ faster than Sonnet 5, at half Opus 5.5's price.

Added 28 Sep 2026 · text

Claude Opus 5.5

Anthropic

First of the Claude 5.5 generation: Fable-class agentic coding and computer use at 20% below Opus 5.

Added 22 Sep 2026 · text

Claude Fable 5.1

Anthropic

Anthropic's top generally available model, tied for first on the Artificial Analysis Intelligence Index.

Added 1 Sep 2026 · text

Claude Fable 5

Anthropic

Anthropic's first Mythos-class model, the new flagship tier above Opus, tuned for the hardest reasoning and agentic work.

Added 5 Aug 2026 · text

Claude Opus 5

Anthropic

The Claude 5 generation's deep-work model, maximum-capability reasoning for research, architecture, and hard agentic tasks.

Added 5 Aug 2026 · text

Claude Haiku 4.5

Anthropic

Fast, cheap frontier-family model for high-volume tasks.

Added 1 Jun 2026 · text

Claude Opus 4.6

Anthropic

The frontier tier for the hardest reasoning and agentic work.

Added 1 Jun 2026 · text

Claude Sonnet 4.5

Anthropic

Frontier-quality text and reasoning through one OpenAI-compatible endpoint.

Added 1 Jun 2026 · text

One key. Every model. Exact prices.

Run every Anthropic model with free starter credits. Free starter credits included, no subscription required.

Get your API key Browse all models