CompanyFabric
New chatOne prompt, one model, any model in the catalogCouncilThree models answer, one writes the verdictJev DecisionsTyped answers with probabilities, no textPerplexity DeciderPerplexity's decision model, same contract as Jev
How the council works →

Text & code

ClaudeClaude Haiku 5.5$0.1/Mtok in · 7 OctMistralMistral Large 4$0.68/Mtok in · 6 OctGemini 4 Argon soonTracking availability
ClaudeClaude Sonnet 5.5$2/Mtok in · 28 SepGPT-4.1 mini$0.4/Mtok in · 27 SepZhipu (智谱)GLM-5.3$1.4/Mtok in · 23 Sep
Xiaomi MiMoMiMo-V2.5-Pro$0.435/Mtok in · 23 SepMetaMuse Spark 1.3$1.25/Mtok in · 23 SepGPT-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 →DocsPricing & API
All models, newest first →Best for codingBest for reasoningBest for writingCheapestOpen sourceFree

Tools

Claude CodeClaude CodeAny model in Claude Code, one keyCursorAny model in Cursor, one keyClineClineAny model in Cline, one keyContinueAny model in Continue, one keyAiderAny model in Aider, one keyOpenClawAny model in OpenClaw, one keyMuseAny model in Muse, one key

Popular pairings

Gemini in Claude CodeSetup in under two minutesDeepSeek in Claude CodeSetup in under two minutesKimi in Claude CodeSetup in under two minutesGPT-5.5 in Claude CodeSetup in under two minutes
All integrations →

Model vs model

ClaudeClaude Haiku 4.5 vs DeepSeek V4.1 FlashAnthropic against DeepSeekGPT-6 Luna vs MiMo-V2.6-ProOpenAI against XiaomiZhipu (智谱)GLM-5.3-Flash vs Mistral Large 4Z.ai against MistralGPT-6 Sol vs Muse Spark 1.3OpenAI against MetaClaudeClaude Haiku 5.5 vs Grok 4.3Anthropic against xAIAll comparisonsEvery pair, priced from the live catalog

Gateways

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

Alternatives

CodeRabbit alternativeCodeRabbit charges per seat for AI code reviewViktor alternativeViktor sells AI employees in Slack at enterprise pricingOpenRouter 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 minutesAuthenticationKeys, budget caps, revocationChat CompletionsOpenAI-compatible /v1/chat/completionsModels & IDsGET /v1/models, ids, aliases, meta-modelsJev DecisionsTyped answers with probabilities, no textFor agentsMCP server, skills, machine-readable pricesllms.txtEvery page, indexed for agents
All docs →
Pricing
Log inRegister
ChatModelsComparePricingDocs
CouncilClaude CodeCursorCheapest modelsBest for codingFor agentsFree models
Log inRegister

API docs

QuickstartAuthenticationChat CompletionsModels & IDsJev DecisionsMedia JobsErrorsBYOK, Bring Your Own Keys
llms.txtFor agents

Documentation

One key, one balance, every model. The API is OpenAI-compatible for chat and submit-then-poll for media, these pages cover the whole surface. Raw markdown mirrors of every doc live under /llm for agents.

Quickstart

Get a key, point any OpenAI SDK at the CompanyFabric base URL, and make your first metered call.

Authentication

Bearer authentication with sk-cf- keys: creation, budget caps, revocation, and how metering attributes spend per key.

Chat Completions

POST /v1/chat/completions, the OpenAI wire format across every text and code model, with streaming and exact usage.

Models & IDs

How model ids work: canonical 2-segment ids, branded aliases, and the companyfabric/* meta-models, plus the /v1/models listing endpoint.

Jev Decisions

Decisions on CompanyFabric. POST /v1/decisions, the endpoint for decision models, TypeSafe's Jev and Perplexity's Decider 27B: send a state and typed questions (noul, choice, score), get calibrated probabilities back. Same key and balance as chat.

Media Jobs

POST /v1/jobs, the async API for video, image, and audio models: submit with the model in the body, poll until completed, read outputs and exact cost.

Errors

Every error is structured JSON with a code, a human message, and a machine-actionable resolution, built for agents that fix their own failures.

BYOK, Bring Your Own Keys

Route through CompanyFabric on your own provider keys at 0% fee, the vault stores them encrypted and never returns more than the last four characters.

CompanyFabric

one API for AI

Run text and code models from every major provider through one API key.

Model APIs

  • Claude Sonnet 4.5 API
  • Claude Haiku 4.5 API
  • Claude Opus 4.6 API
  • GPT-5.5 API
  • GPT-6 Astra API
  • Kimi K3 API
  • All models A–Z →

Use cases

  • Best coding models, ranked with exact prices
  • Best reasoning models, where the frontier tier earns its price
  • Best writing models, voice, control, and cost compared
  • Cheapest AI models
  • Best open source models, open-weight LLMs you can run anywhere
  • Free AI models, every way to run models at $0

Integrations & compare

  • Claude Code
  • Cursor
  • Cline
  • vs OpenRouter
  • vs LiteLLM
  • CodeRabbit alternative
  • Viktor alternative

Head to head

  • Claude Haiku 4.5 vs DeepSeek V4.1 Flash
  • GPT-6 Luna vs MiMo-V2.6-Pro
  • GLM-5.3-Flash vs Mistral Large 4
  • GPT-6 Sol vs Muse Spark 1.3
  • All comparisons →

Developers

  • API docs
  • For agents
  • llms.txt
© 2026 CompanyFabric.
Terms of ServiceAcceptable UsePrivacy PolicyRefund PolicyContact