API Docs — Coder Copilot Dev

API Reference

The Coder Copilot Developer API lets you call AI models directly using an API key. No session cookie required — just pass your key and a prompt.

⚠️ The Developer API is in public beta. Token limits and model availability may change.

Base URL

https://codercopilot.firesmasher.workers.dev

Authentication

All inference endpoints require your API key. Pass it as a query parameter or as an HTTP header.

Query parameter (easiest)

POST /v1/model/orbus-low?apikey=dak_your_key_here

Header

x-api-key: dak_your_key_here

Keys start with dak_ and are 52 characters long. You can create up to 3 keys per account on the API Keys page.

Available Models

Three models are available for the Dev API, each with its own token budget:

Slug	Token Limit	Reset Period	Msgs/min	Best for
flux-plus	200	12 hours	2	Short, precise tasks
orbus-low	1500	12 hours	2	General use, longer conversations
nova-standard	500	12 hours	2	Balanced quality and quota

Token counts are approximate (≈ 1 token per 4 characters for input + output).

POST /v1/model/:model

POST /v1/model/{modelSlug} Send a prompt, receive a reply

Request body (JSON)

Field	Type	Required	Description
message	string	Yes*	The prompt / user message to send to the model.
prompt	string	Yes*	Alias for message.

* Either message or prompt is required.

Example request

curl -X POST \
  "https://codercopilot.firesmasher.workers.dev/v1/model/orbus-low?apikey=dak_your_key" \
  -H "Content-Type: application/json" \
  -d '{"message": "What is a Cloudflare Worker?"}'

Example response (200 OK)

{
  "ok": true,
  "model": "orbus-low",
  "reply": "A Cloudflare Worker is a serverless JavaScript runtime…",
  "usage": {
    "tokensConsumed": 47,
    "tokensUsed": 47,
    "tokensRemaining": 1453,
    "tokensLimit": 1500
  }
}

Error responses

Status	Error	Meaning
401	Invalid API key	Key is missing, wrong, or revoked.
400	Missing 'message'	No prompt was provided in the request body.
404	Unknown model	The model slug in the URL doesn't exist.
429	Rate limit / Token limit	You've hit the per-minute message limit or exhausted your token budget. Check retryIn / resetInMinutes in the response.
502	AI error	The upstream AI provider returned an error.

GET /v1/models

GET /v1/models List all available models (no auth required)

Example response

{
  "models": [
    { "slug": "flux-plus",     "tokenLimit": 200,  "resetHours": 12, "msgsPerMinute": 2 },
    { "slug": "orbus-low",     "tokenLimit": 1500, "resetHours": 12, "msgsPerMinute": 2 },
    { "slug": "nova-standard", "tokenLimit": 500,  "resetHours": 12, "msgsPerMinute": 2 }
  ]
}

Key Management Endpoints

These endpoints require a valid session cookie (you must be logged in via the main Coder Copilot app), not an API key.

GET /api/dev/keys List your API keys

POST /api/dev/keys Create a new API key (body: { "label": "…" })

DELETE /api/dev/keys/:keyId Revoke an API key

GET /api/dev/usage Get token usage for all your keys

Rate Limits

Limit	Value	Scope
Messages	2 per minute	Per API key, per model
Tokens (flux-plus)	200 / 12 hours	Per API key
Tokens (orbus-low)	1500 / 12 hours	Per API key
Tokens (nova-standard)	500 / 12 hours	Per API key
API keys	3 per account	Per user

When you hit a limit, the API returns HTTP 429 with retryIn (seconds, for message limit) or resetInMinutes (for token limit) in the response body.

Quick Start

JavaScript / fetch

const res = await fetch(
  "https://codercopilot.firesmasher.workers.dev/v1/model/orbus-low?apikey=dak_your_key",
  {
    method: "POST",
    headers: { "Content-Type": "application/json" },
    body: JSON.stringify({ message: "Hello, what can you help me with?" }),
  }
);
const data = await res.json();
console.log(data.reply);       // AI response text
console.log(data.usage);       // token consumption details

Python

import requests

res = requests.post(
    "https://codercopilot.firesmasher.workers.dev/v1/model/orbus-low",
    params={"apikey": "dak_your_key"},
    json={"message": "Hello, what can you help me with?"}
)
data = res.json()
print(data["reply"])
print(data["usage"])