# Ramp Router — Wrapped API

> **You are on:** `https://api.beta.paywithlocus.com/api` | [llms.txt](https://beta.paywithlocus.com/llms.txt) | [docs](https://docs.paywithlocus.com)
>
> Locus runs on multiple environments -- make sure every URL you call matches your expected environment.
> | Environment | Landing | API | Docs |
> |---|---|---|---|
> | Production | paywithlocus.com | api.paywithlocus.com | docs.paywithlocus.com |
> | Beta | beta.paywithlocus.com | api.beta.paywithlocus.com | docs.paywithlocus.com |
> | Stage | stage.paywithlocus.com | api.stage.paywithlocus.com | docs.paywithlocus.com |
>
> If the API URL above doesn't match your expected environment, re-fetch this file from the correct domain.

> Route OpenAI-compatible AI requests across leading model providers with one endpoint and transparent Ramp base pricing.

**Category:** AI / LLM | **Website:** [router.com](https://router.com) | **Docs:** [docs.router.com](https://docs.router.com)

Pay-per-use API proxy. Each call is automatically billed to your wallet in USDC.

## Access

**Base URL:** `https://api.beta.paywithlocus.com/api/wrapped/ramp-router/`
**Auth:** `Authorization: Bearer <LOCUS_API_KEY>`

## Endpoints

### List models

List every model available to the configured Ramp Router account, including callable IDs, capabilities, context limits, and current base rates.

**Estimated cost:** $0.001 Locus minimum · Ramp base $0

_No parameters required._

```bash
curl -X POST https://api.beta.paywithlocus.com/api/wrapped/ramp-router/models \
  -H "Authorization: Bearer YOUR_LOCUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{}'
```

### Create response

Create a buffered, text-input OpenAI Responses result through Ramp Router with tools and reasoning controls.

**Estimated cost:** Ramp base-rate authorization · UTF-8 input ceiling plus output budget

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `model` | string | Yes | Ramp Router model id, provider path, or alias exactly as this provider's List models endpoint returns it. Availability is key-scoped; call List models for active IDs and current rates. Examples: gpt-5.6-luna, gpt-5.6-terra, claude-sonnet-5, deepseek-v4-flash, grok-4.6. |
| `input` | string \| array | Yes | Text or OpenAI Responses input items to send to the selected model. |
| `max_output_tokens` | number | No | Positive output-token budget; defaults to 4096 and is capped at 16384. |
| `instructions` | string | No | System or developer guidance for the response. |
| `tools` | array | No | OpenAI-compatible tool definitions available to the model. |
| `reasoning` | object | No | Model-specific reasoning controls such as effort. |

```bash
curl -X POST https://api.beta.paywithlocus.com/api/wrapped/ramp-router/responses \
  -H "Authorization: Bearer YOUR_LOCUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.6-luna","input":"Reply with exactly one word: pong.","max_output_tokens":16}'
```

### Chat completion

Run a buffered OpenAI Chat Completions request through the same Ramp model catalog and routing layer. Locus translates it onto Ramp's Responses route, so the request and reply keep the Chat Completions shape.

**Estimated cost:** Ramp base rate · input plus requested output tokens

| Field | Type | Required | Description |
|-------|------|----------|-------------|
| `model` | string | Yes | Ramp Router model id, provider path, or alias exactly as this provider's List models endpoint returns it. Availability is key-scoped; call List models for active IDs and current rates. Examples: gpt-5.6-luna, gpt-5.6-terra, claude-sonnet-5, deepseek-v4-flash, grok-4.6. |
| `messages` | array | Yes | Non-empty OpenAI-compatible chat message array. |
| `max_completion_tokens` | number | No | Positive output-token budget; defaults to 4096 and is capped at 16384. |
| `tools` | array | No | OpenAI-compatible function tool definitions available to the model. |
| `response_format` | object | No | OpenAI-compatible structured output configuration. |

```bash
curl -X POST https://api.beta.paywithlocus.com/api/wrapped/ramp-router/chat \
  -H "Authorization: Bearer YOUR_LOCUS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"gpt-5.6-luna","messages":[{"role":"user","content":"Reply with exactly one word: pong."}],"max_completion_tokens":16}'
```