Get Started

Supported Models

The full catalog of models any BitRouter account can call — with pricing, reachable over your own keys or one hosted BitRouter Cloud account, with automatic discounts on open models.

Every model BitRouter can route to is listed below. Reach any of them over your own provider keys (BYOK, paid to the providers at their list price) or one BitRouter Cloud account — one sign-in, no upstream keys, billed per request with failed requests not charged. Running your own model? See local & private models (free).

Prices are USD per million tokens, taken from the current registry snapshot (each model's lowest-priced provider; means no per-token provider lists it yet). Open models are served 25% below official by default — see Discounted open models below. Every model is served by one or more registered providers — see Supported Providers for the full list and how to register your own.

Model catalog

ModelNameContextModalitiesOpen weightsInput $/MOutput $/M
anthropic/claude-fable-5Anthropic: Claude Fable 51Mtext, image$10$50
anthropic/claude-haiku-4.5Anthropic: Claude Haiku 4.5200Ktext, image$1$5
anthropic/claude-opus-4.6Anthropic: Claude Opus 4.6200Ktext, image$5$25
anthropic/claude-opus-4.7Anthropic: Claude Opus 4.7200Ktext, image$4.5$22.5
anthropic/claude-opus-4.8Anthropic: Claude Opus 4.81Mtext, image$5$25
anthropic/claude-sonnet-4.6Anthropic: Claude Sonnet 4.61Mtext, image$3$15
anthropic/claude-sonnet-5Anthropic: Claude Sonnet 51Mtext, image$2$10
deepseek/deepseek-v3.2DeepSeek: DeepSeek V3.2128Ktext$0.21$0.315
deepseek/deepseek-v4-flashDeepSeek: DeepSeek V4 Flash256Ktext$0.09$0.18
deepseek/deepseek-v4-proDeepSeek: DeepSeek V4 Pro256Ktext$0.435$0.87
google/gemini-3.1-flash-lite-previewGoogle: Gemini 3.1 Flash Lite Preview1Mtext, image$0.25$1.5
google/gemini-3.1-pro-previewGoogle: Gemini 3.1 Pro Preview2Mtext, image$2$12
google/gemini-3.5-flashGoogle: Gemini 3.5 Flash1Mtext, image, audio$1.5$9
google/gemma-4-31bGoogle: Gemma 4 31B128Ktext, image$0.13$0.4
meituan/longcat-2.0LongCat 2.01Mtext$0.75$2.95
minimax/minimax-m2.5MiniMax: M2.5192Ktext$0.15$0.9
minimax/minimax-m2.7MiniMax: M2.7192Ktext$0.225$0.9
minimax/minimax-m3MiniMax: M31Mtext, image$0.3$1.2
moonshotai/kimi-k2.5Kimi: K2.5256Ktext, image$0.375$2.025
moonshotai/kimi-k2.6Kimi: K2.6256Ktext$0.66$3.41
moonshotai/kimi-k2.7-codeKimi: K2.7 Code256Ktext, image$0.612$3.069
moonshotai/kimi-k3Kimi: K31Mtext, image$3$15
openai/gpt-5.4OpenAI: GPT-5.4128Ktext, image$2.5$15
openai/gpt-5.4-miniOpenAI: GPT-5.4 Mini128Ktext, image$0.75$4.5
openai/gpt-5.5OpenAI: GPT-5.5128Ktext, image$5$30
openai/gpt-5.6-lunaOpenAI: GPT-5.6 Luna400Ktext, image$1$6
openai/gpt-5.6-solOpenAI: GPT-5.6 Sol1Mtext, image$5$30
openai/gpt-5.6-terraOpenAI: GPT-5.6 Terra1Mtext, image$2.5$15
qwen/qwen3.5-122b-a10bQwen: Qwen3.5 122B-A10B256Ktext, image$0.26$2.08
qwen/qwen3.5-27bQwen: Qwen3.5 27B256Ktext, image$0.195$1.56
qwen/qwen3.6-27bQwen: Qwen3.6 27B256Ktext, image$0.285$2.4
qwen/qwen3.6-35b-a3bQwen: Qwen3.6 35B-A3B256Ktext, image$0.14$1
qwen/qwen3.6-flashQwen: Qwen3.6 Flash1Mtext, image$0.165$0.99
qwen/qwen3.7-maxQwen: Qwen3.7 Max1Mtext$1.25$3.75
qwen/qwen3.7-plusQwen: Qwen3.7 Plus1Mtext, image$0.276$1.101
stepfun/step-3.5-flashStepFun: Step 3.5 Flash256Ktext$0.072$0.216
stepfun/step-3.7-flashStepFun: Step 3.7 Flash256Ktext, image$0.15$0.8625
tencent/hy3Hunyuan 3256Ktext$0$0
x-ai/grok-4.20xAI: Grok 4.20128Ktext, image$1.25$2.5
x-ai/grok-4.20-multi-agentxAI: Grok 4.20 Multi-Agent1Mtext, image$1.25$2.5
x-ai/grok-4.3xAI: Grok 4.31Mtext, image$1.25$2.5
x-ai/grok-4.5xAI: Grok 4.5500Ktext, image$2$6
x-ai/grok-build-0.1xAI: Grok Build 0.1256Ktext$1$2
xiaomi/mimo-v2.5Xiaomi: MiMo V2.5256Ktext$0.14$0.28
xiaomi/mimo-v2.5-proXiaomi: MiMo V2.5 Pro256Ktext$0.435$0.87
z-ai/glm-4.7Zhipu: GLM-4.7200Ktext$0.4$1.75
z-ai/glm-5Zhipu: GLM-5198Ktext$0.6$1.92
z-ai/glm-5.1Zhipu: GLM-5.1128Ktext$0.83$3.33
z-ai/glm-5.2Zhipu: GLM-5.21Mtext$0.97$3.07

Using BitRouter Cloud

The BitRouter Cloud provider lets an agent call any model above with a single BitRouter account — no upstream provider keys, no per-provider signups. You pay BitRouter directly at the prices listed here, billed per request; failed requests aren't billed.

bitrouter cloud login   # one-time device-flow sign-in
bitrouter start         # the `bitrouter` provider auto-enables once signed in

Discounted open models

BitRouter runs its own self-hosted provider for open models, priced 25% below official rates. You get that price automatically — and open-source builders can apply for a deeper custom discount.

25% off by default

Every model except the closed-source families — OpenAI (gpt-*), Anthropic (claude-*), Google (gemini-*), xAI (grok-*), and Meta (muse-spark-*) — is served by BitRouter's self-hosted provider at 25% below the model's official price.

This takes no suffix and no configuration. Because the self-hosted provider is the cheapest source for these models, normal routing already sends your requests there and bills the discounted rate. (The five closed-source families above aren't on the self-hosted provider, so they route to their usual upstreams at standard pricing.)

Pin to the self-hosted provider with :discount

Append :discount to a model id to route the request specifically to BitRouter's self-hosted provider:

curl http://127.0.0.1:4356/v1/chat/completions \
  -H "Content-Type: application/json" \
  -d '{
    "model": "moonshotai/kimi-k2.6:discount",
    "messages": [{"role": "user", "content": "Translate to French: Hello."}]
  }'

The suffix rides on the model string — no body fields, no SDK — and works the same on the OpenAI, Anthropic, and Google surfaces (/v1/messages, /v1beta/models/{model}:generateContent). Use it to guarantee your traffic lands on the discounted self-hosted supply; it's also where any custom discount on your account applies.

Custom discounts up to 50% for open-source projects

Building an open-source agent harness or another open-source project on BitRouter? We offer customized discounts — up to 50% off — for you and your community.

Reach out to set it up:

How is this guide?

On this page