Frontier models, up to 80% under list.
Claude, GPT, Gemini, DeepSeek, Kimi and more through one OpenAI- and Anthropic-compatible API. Pay as you go from $5.
Start in one step
Point your client at routing.run. The rest of your code stays as it is.
import osfrom openai import OpenAIclient = OpenAI( base_url="https://api.routing.run/v1", api_key=os.environ["ROUTING_API_KEY"],)client.chat.completions.create( model="claude-opus-5", messages=[{"role": "user", "content": "Hi"}],)Change two arguments and keep the rest. Chat completions, responses and the model list all work, for every model.
Get a keyimport osfrom anthropic import Anthropicclient = Anthropic( base_url="https://api.routing.run", api_key=os.environ["ROUTING_API_KEY"],)client.messages.create( model="claude-opus-5", max_tokens=1024, messages=[{"role": "user", "content": "Hi"}],)The Anthropic SDK adds /v1/messages itself, so its base URL has no /v1.
Get a keycurl https://api.routing.run/v1/chat/completions \ -H "Authorization: Bearer $ROUTING_API_KEY" \ --json '{ "model": "claude-opus-5", "messages": [{"role": "user", "content": "Hi"}] }'Add "stream": true to get the answer as it is written.
Get a keyexport ANTHROPIC_BASE_URL=https://api.routing.runexport ANTHROPIC_AUTH_TOKEN=$ROUTING_API_KEYclaude --model claude-opus-5Claude Code reads these two variables. Codex, OpenCode and Cline take https://api.routing.run/v1 as their OpenAI base URL.
Get a keyWhat you get
29 models, one key. 12 labs on one balance, at the prices in the table below.
See the modelsPay per token. Each request comes off your credits.
A key for each app. See when each one was last used, and revoke it the moment it leaks.
Choose a model family
Each opens the price table below, filtered to that family.
- Claude Anthropic6 models, input $0.07 to $5.60 per 1M, up to 70% under list
- GPT OpenAI5 models, input $0.014 to $8.00 per 1M, up to 80% under list
- Gemini Google4 models, input $0.165 to $0.50 per 1M, up to 80% under list
- DeepSeek DeepSeek2 models, input $0.0127 to $0.18 per 1M, up to 80% under list
- Kimi Moonshot AI3 models, input $0.0576 to $0.179 per 1M, up to 80% under list
- GLM Z.ai2 models, input $0.00798 to $0.0168 per 1M, up to 80% under list
- Qwen Alibaba2 models, input $0.03 to $0.40 per 1M, up to 80% under list
- Grok xAI1 model, input $1.90 per 1M, 5% under list
- MiniMax MiniMax1 model, input $0.165 per 1M, 45% under list
- MiMo Xiaomi1 model, input $0.24 per 1M, 45% under list
- Mistral Mistral AI1 model, input $0.49 per 1M, 30% under list
- Nemotron NVIDIA1 model, input $0.188 per 1M, 70% under list
Models and prices
Every model next to its list price. What you see is what each token costs.
| Claude Fable 5.2 | $5.60 | $28.00 | 1M | 30% | |
|---|---|---|---|---|---|
| Claude Opus 5.5 | $2.80 | $14.00 | 1M | 30% | |
| Claude Sonnet 5.5 | $1.80 | $9.00 | 1M | 10% | |
| Claude Haiku 5.5 | $0.07 | $0.35 | 100K | 30% | |
| Claude Opus 5 | $1.50 | $7.50 | 1M | 70% | |
| Claude Sonnet 5 | $0.80 | $4.00 | 1M | 60% | |
| GPT-6 Astra | $8.00 | $40.00 | 1.05M | 20% | |
| GPT-6.1 Sol | $1.80 | $9.00 | 1.05M | 10% | |
| GPT-6.1 Terra | $0.90 | $4.50 | 1.05M | 10% | |
| GPT-6 Luna | $0.095 | $0.475 | 1.05M | 5% | |
| GPT-OSS 120B | $0.014 | $0.06 | 128K | 80% | |
| Gemini 4 Argon | $0.50 | $2.50 | 1.05M | 75% | |
| Gemini 4 Carbon | $0.50 | $2.50 | 1.05M | 75% | |
| Gemini 4 Hydrogen | $0.375 | $1.88 | 1.05M | 75% | |
| Gemini 3.8 Flash | $0.165 | $0.825 | 1.05M | 80% | |
| DeepSeek V4 Pro | $0.18 | $0.30 | 1M | 80% | |
| DeepSeek V4.1 Flash | $0.0127 | $0.0507 | 1.05M | 75% | |
| Kimi K3 | $0.0576 | $4.80 | 1M | 70% | |
| Kimi K3.1 Pro | $0.179 | $6.73 | 1.05M | 20% | |
| Kimi K2.7 Code | $0.12 | $0.70 | 262K | 80% | |
| GLM 5.3 | $0.0168 | $0.72 | 1M | 80% | |
| GLM 5.3 Flash | $0.00798 | $0.0157 | 1.05M | 80% | |
| Qwen3.8 Max | $0.40 | $1.20 | 1M | 80% | |
| Qwen3.8 Flash | $0.03 | $0.094 | 1M | 80% | |
| MiniMax M3 | $0.165 | $0.66 | 200K | 45% | |
| Grok 4.7 | $1.90 | $5.70 | 500K | 5% | |
| MiMo V2.6 Pro | $0.24 | $0.479 | 1.05M | 45% | |
| Mistral Large 4 | $0.49 | $1.47 | 524K | 30% | |
| Nemotron 3 Ultra | $0.188 | $0.938 | 1M | 70% |
No model matches these filters.
Prices per million tokens. Ours rounded up, list rounded down; the exact figures are at api.routing.run/v1/pricing. Select an id to copy it.
Works with
Anything that speaks the OpenAI or Anthropic API. Change one setting and add your key.
- Claude CodeShell environment
ANTHROPIC_BASE_URL=https://api.routing.run - Codex~/.codex/config.toml, as a model provider
base_url = "https://api.routing.run/v1" - CursorSettings, Models, Override OpenAI Base URL
https://api.routing.run/v1 - OpenCodeopencode.json, provider options
"baseURL": "https://api.routing.run/v1" - ClineAPI Provider: OpenAI Compatible, Base URL
https://api.routing.run/v1 - Zedsettings.json, openai_compatible
"api_url": "https://api.routing.run/v1" - OpenAI SDKPython; in TypeScript the option is baseURL
base_url="https://api.routing.run/v1" - Anthropic SDKNo /v1: the SDK adds /v1/messages itself
base_url="https://api.routing.run" - Vercel AI SDKcreateOpenAICompatible, as the provider
baseURL: "https://api.routing.run/v1" - LangChainChatOpenAI, in Python
base_url="https://api.routing.run/v1"
What you'd save
Pay as you go from $5, no plan and no monthly fee. The figures use the per-token prices you pay.
You save each month
$201.60
$2,419 a year, 30% under list
- At list
- $672.00
- On routing.run
- $470.40
108M input and 12M output tokens at Claude Opus 5.5's per-token prices. Cached input costs less again.
How billing works
Credits in, tokens out. No plan, no seats, no monthly fee.
1. Add credits
Sign in with GitHub, Google, Discord, Apple or an email link, then top up from $5. Credits you buy don't expire.
Open the dashboard2. Create a key
Make one key for each place your code runs and name it after that place. The dashboard shows when each key was last used, and you can revoke one the moment it leaks. This call lists every model:
curl https://api.routing.run/v1/models \ -H "Authorization: Bearer $ROUTING_API_KEY"3. Pay per token
Each request is billed per token at the price in the table above and taken from your credits. Usage lists every request with its model, tokens and cost. We don't keep prompts or answers.
Questions
Anything else: support@routing.run
What do I pay?
You pay less than list for the same model id, at the price in the table. That price is what you pay per token.
Do I get the model I ask for?
Yes. We send each request to the model id you ask for and never substitute another model. 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 don't store the content of your prompts or responses. They pass through memory to the model and are discarded once the response is sent. We keep request metadata (model, token counts, cost, timing) for billing.
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.