> ## Documentation Index > Fetch the complete documentation index at: https://docs.nemu.cc/llms.txt > Use this file to discover all available pages before exploring further. # How the gateway works > One key, your own providers, and the endpoints Nemu exposes 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 | Protocol | Base URL | Main endpoint | | ------------------ | ------------------------------- | ------------------- | | OpenAI-compatible | `https://api.nemu.cc/v1` | `/chat/completions` | | OpenAI Responses | `https://api.nemu.cc/v1` | `/responses` | | Anthropic Messages | `https://api.nemu.cc/anthropic` | `/v1/messages` | 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. ```bash theme={null} curl https://api.nemu.cc/v1/chat/completions \ -H "Authorization: Bearer YOUR_NEMU_GATEWAY_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"openrouter/nemotron","messages":[{"role":"user","content":"hi"}]}' ``` 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 | Method | Path | What it does | | ------ | ------------------------------------- | --------------------------------------------- | | POST | `/v1/chat/completions` | Chat completions, streaming or buffered | | POST | `/v1/responses` | OpenAI Responses API | | POST | `/v1/embeddings` | Embeddings | | POST | `/v1/images/generations` | Image generation | | POST | `/v1/moderations` | Moderation | | POST | `/v1/audio/speech` | Text to speech | | POST | `/v1/audio/transcriptions` | Speech to text | | POST | `/v1/audio/translations` | Speech to English text | | POST | `/v1/count_tokens` | Token count for an OpenAI-shaped request | | GET | `/v1/models` | Models enabled for the key's workspace | | POST | `/anthropic/v1/messages` | Anthropic Messages, streaming or buffered | | POST | `/anthropic/v1/messages/count_tokens` | Anthropic token count | | GET | `/anthropic/v1/models` | The same models, in Anthropic's shape | | GET | `/reader` | Fetch a URL as clean text, metered in credits | | GET | `/health` | Liveness, no key required | ## 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. ```json theme={null} { "object": "list", "data": [ { "id": "openrouter/nemotron", "object": "model", "owned_by": "openrouter" } ] } ``` 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. ```json theme={null} { "error": { "message": "Model openrouter/nemotron does not exist or you do not have access to it.", "type": "model_not_found", "code": "model_not_found" } } ``` 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: | Plan | Maximum request body | | ---------- | -------------------- | | Free | 2 MB | | Starter | 4 MB | | Pro | 8 MB | | Max | 16 MB | | Enterprise | 32 MB | 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.