Skip to main content
Nemu sits between your application and the model providers you have connected. You send one gateway key; Nemu resolves the model, picks the provider credential, applies your mappings, quotas and budgets, records the request, and forwards it upstream. Provider keys never leave the console.

​
Base URLs

Anthropic clients append /v1/messages to whatever base URL you give them, so https://api.nemu.cc works as an Anthropic base URL too: both https://api.nemu.cc/v1/messages and https://api.nemu.cc/anthropic/v1/messages serve the Messages API.

​
Authentication

Send the gateway key either way. Anthropic clients tend to use x-api-key, OpenAI clients use the bearer header, and Nemu accepts both on every endpoint.
Keys are created in the console and look like sk_xxxxx-xxxxx. followed by a 40 character secret. A key belongs to one workspace and can only reach the providers and models enabled in that workspace.

​
Endpoints

​
Choosing a model

GET /v1/models returns exactly the strings you can put in model. Each one is the model’s gateway name: the provider name, a slash, and the alias you gave it in the console.
For models added from the models.dev catalog, the gateway name is yours to choose and is independent of the upstream model id, so openrouter/nemotron can point at nvidia/nemotron-nano-9b-v2 upstream. Edit it under Models in the console. The gateway name is the only model name a client may send. The upstream id is not accepted, so nothing you run can address a provider model that you have not deliberately exposed, and renaming a model in the console changes the name your clients use without touching the provider. Two other values are accepted in model:
  • A mapping. Mappings match a pattern and rewrite it to a gateway name, which is how you keep a client that hardcodes gpt-4o pointed at whatever you want.
  • auto. When automatic routing is configured, Nemu picks the model.

​
Variants

A gateway name can carry a variant in square brackets, the way some clients write claude-opus-5[1m]. The variant is stripped before the model is resolved, so openrouter/nemotron[1m] addresses openrouter/nemotron. [1m] asks for a one million token context: it raises the accounted context window and, for Anthropic providers, sends the context-1m-2025-08-07 beta header upstream.

​
Compatibility

Nemu speaks three wire protocols on the way in and translates to whatever the upstream provider speaks. An Anthropic-shaped request can be served by an OpenAI-compatible provider and the other way round: system blocks, tool calls, streaming events, thinking blocks and cache breakpoints are converted in both directions. Reasoning is handled per model. Anthropic-style thinking budgets, OpenAI-style reasoning_effort and adaptive modes are mapped to whatever the target model actually supports, so a request that asks for thinking on a model without it succeeds instead of failing with a 400.

​
Errors

Every error says which side failed. The x-nemu-error-origin response header is nemu when the gateway stopped the request and provider when the upstream did, so a 402 from your provider’s billing is never confused with a 402 from your nemu budget.
Anthropic endpoints return Anthropic’s {"type":"error","error":{...}} shape with the matching invalid_request_error, authentication_error, not_found_error, rate_limit_error or overloaded_error type. Errors that the gateway itself raised end with a reference, as in ... (id: 6f1c2a9e-...). That is the id of the request’s row under Metrics, so a report can be traced to the exact request without guessing.

​
Limits and accounting

Requests are counted against your plan and against any quota rules and monthly budget set for the workspace. A 429 carries Retry-After and the limit that was hit, so a client can pace itself instead of guessing. Request bodies are capped per plan, which matters for coding agents because the whole conversation is resent every turn: Going over returns a 413 naming both the size sent and the limit. Every request lands in Metrics with its model, provider, latency, token counts, cost and origin. Requests that came from nemu’s own chat are labelled as such rather than showing an internal address.

​
Caching

Providers, models, mappings, prompts and quota rules are cached for speed. Changing any of them in the console or through the management API clears the gateway’s copy immediately, so a rotated provider key takes effect on the next request.