Frontier models, below list price.

One OpenAI- and Anthropic-compatible API for 29 models: Claude, GPT-6, Gemini 4, DeepSeek, Kimi and more. Pay per token from prepaid credits.

Sign in with GitHub, Google, Discord, Apple or an email link.

29 models, all below list

Per million tokens. You pay the first price; list is struck through. Up to 80% off. Cached input is billed at the lower cache-read rate.

Model prices per million tokens
ModelContextInputOutputCached inputBelow list
Claude Fable 5.2claude-fable-5.21M contextCached input $0.111M$4.40$8.00$22.00$40.00$0.1145% off
Claude Opus 5.5claude-opus-5.51M contextCached input $0.111M$2.20$4.00$11.00$20.00$0.1145% off
Claude Sonnet 5.5claude-sonnet-5.51M contextCached input $0.081M$1.60$2.00$8.00$10.00$0.0820% off
Claude Haiku 5.5claude-haiku-5.5100K contextCached input $0.0055100K$0.055$0.10$0.275$0.50$0.005545% off
Claude Opus 5claude-opus-51M contextCached input $0.1751M$1.75$5.00$8.75$25.00$0.17565% off
Claude Sonnet 5claude-sonnet-51M contextCached input $0.101M$1.00$2.00$5.00$10.00$0.1050% off
GPT-6 Astragpt-6-astra1.05M contextCached input $0.601.05M$6.00$10.00$30.00$50.00$0.6040% off
GPT-6.1 Solgpt-6.1-sol1.05M contextCached input $0.031.05M$0.60$2.00$3.00$10.00$0.0370% off
GPT-6.1 Terragpt-6.1-terra1.05M contextCached input $0.021.05M$0.40$1.00$2.00$5.00$0.0260% off
GPT-6 Lunagpt-6-luna1.05M contextCached input $0.00651.05M$0.065$0.10$0.325$0.50$0.006535% off
GPT-OSS 120Bgpt-oss-120b128K contextCached input $0.0021128K$0.014$0.07$0.06$0.30$0.002180% off
Gemini 4 Argongemini-4-argon1.05M contextCached input $0.0251.05M$0.50$2.00$2.50$10.00$0.02575% off
Gemini 4 Carbongemini-4-carbon1.05M contextCached input $0.021.05M$0.40$2.00$2.00$10.00$0.0280% off
Gemini 4 Hydrogengemini-4-hydrogen1.05M contextCached input $0.0151.05M$0.30$1.50$1.50$7.50$0.01580% off
Gemini 3.8 Flashgemini-3.8-flash1.05M contextCached input $0.01651.05M$0.165$0.825$0.825$4.125$0.016580% off
DeepSeek V4 Prodeepseek-v4-pro1M contextCached input $0.051M$0.18$0.90$0.30$1.50$0.0580% off
DeepSeek V4.1 Flashdeepseek-v4.1-flash1.05M contextCached input $0.00031.05M$0.01521$0.0507$0.06084$0.2028$0.000370% off
Kimi K3kimi-k31M contextCached input $0.03641M$0.0384$0.192$3.20$16.00$0.036480% off
Kimi K3.1 Prokimi-k3.1-pro1.05M contextCached input $0.181.05M$0.20088$0.2232$7.57026$8.4114$0.1810% off
Kimi K2.7 Codekimi-k2.7-code262K contextCached input $0.032262K$0.12$0.60$0.70$3.50$0.03280% off
GLM 5.3glm-5.31M contextCached input $0.01581M$0.0168$0.084$0.72$3.60$0.015880% off
GLM 5.3 Flashglm-5.3-flash1.05M contextCached input $0.0061.05M$0.00798$0.0399$0.01568$0.0784$0.00680% off
Qwen3.8 Maxqwen3.8-max1M contextCached input $0.051M$0.40$2.00$1.20$6.00$0.0580% off
Qwen3.8 Flashqwen3.8-flash1M contextCached input $0.00321M$0.03$0.15$0.094$0.47$0.003280% off
MiniMax M3minimax-m3200K contextCached input $0.027200K$0.135$0.30$0.54$1.20$0.02755% off
Grok 4.7grok-4.7500K contextCached input $0.275500K$1.10$2.00$3.30$6.00$0.27545% off
MiMo V2.6 Promimo-v2.6-pro1.05M contextCached input $0.001981.05M$0.23925$0.435$0.4785$0.87$0.0019845% off
Mistral Large 4mistral-large-4524K contextCached input $0.049524K$0.49$0.70$1.47$2.10$0.04930% off
Nemotron 3 Ultranemotron-3-ultra1M contextCached input $0.056251M$0.1875$0.625$0.9375$3.125$0.0562570% off

The same list as JSON: GET api.routing.run/v1/pricing

Switch in three lines

Keep your SDK and your code. Point the base URL at Routing, use your key, pick a model id.

from openai import OpenAI
client = OpenAI(base_url="https://api.routing.run/v1", api_key="rk_...")
client.chat.completions.create(model="gpt-6.1-sol", messages=[{"role": "user", "content": "Hi"}])

Any OpenAI client works the same way: chat completions, responses and models.

Pay as you go

No plans and no monthly fee. You pay the per-token prices above, from prepaid credits.

  1. Add credits

    Top up from $5. Credits you buy don't expire.

  2. Pay per token

    Each request costs its uncached input tokens at the input price plus its output tokens at the output price. A key you don't use costs nothing.

    Cached input is billed at each model's lower cache-read rate, listed in the models table.

  3. See every request

    The dashboard lists every request with its model, tokens and cost, next to your balance.

Questions

Anything else: support@routing.run

Why is it cheaper than list?

We buy inference capacity below list price and pass most of the saving on. The price in the table is the price you pay per token.

Do I get the model I ask for?

Yes. Every request runs the model id you send, and the table shows the context each one accepts.

What works with it?

Anything that speaks the OpenAI or Anthropic API: the official SDKs, LangChain and similar libraries, and coding agents such as Claude Code, Codex, OpenCode and Cline. Use https://api.routing.run/v1 as the OpenAI base URL, or https://api.routing.run for Anthropic clients.

Do you store my prompts?

We keep the model, token counts and cost of each request for billing. We don't store prompt or response text.

What happens if a model is unavailable?

The API answers 503 with a short message. Retry after a moment, or send the request to another model id.

Do credits expire?

Credits you buy don't expire. The smallest top-up is $5.

How do I sign in?

With GitHub, Google, Discord or Apple, or with a sign-in link sent to your email. There is no password to set.