Skip to main content
Manifest exposes both OpenAI and Anthropic-format endpoints on one proxy. Point your client at the Manifest URL, send manifest/auto as the model, and routing picks the real model behind the scenes.

​
Base URL

ModeURL
Cloudhttps://app.manifest.build
Self-hostedhttp://localhost:2099 (or your custom port)

​
Authentication

Every request requires a Manifest agent key: 
Authorization: Bearer mnfst_YOUR_KEY_HERE
Generate a key from the dashboard’s Agents page. Keys always start with mnfst_.

​
Endpoints

MethodPathFormatUse it for
POST/v1/chat/completionsOpenAIMost clients (OpenAI SDK, LangChain, Vercel AI SDK, custom HTTP)
POST/v1/responsesOpenAI ResponsesCodex, *-pro, o1-pro, deep-research models
POST/v1/messagesAnthropicAnthropic SDK, Claude Code, anything that speaks the Messages API
The proxy translates between formats internally, so you can send an OpenAI-shaped request and Manifest will reshape it before forwarding to an Anthropic-only model. The reverse works too.

​
Chat completions

curl -X POST http://localhost:2099/v1/chat/completions \
  -H "Authorization: Bearer mnfst_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "manifest/auto",
    "messages": [
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'
The body is forwarded verbatim to the resolved provider, with model rewritten to the actual model ID. All standard OpenAI fields (temperature, max_tokens, tools, tool_choice, response_format, stream, etc.) pass through.

​
Anthropic messages

curl -X POST http://localhost:2099/v1/messages \
  -H "Authorization: Bearer mnfst_YOUR_KEY_HERE" \
  -H "Content-Type: application/json" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "manifest/auto",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello"}
    ]
  }'

​
Streaming

Set "stream": true to get an SSE stream back. The stream format matches the upstream protocol: OpenAI-style data: {...} chunks for /v1/chat/completions, Anthropic event blocks for /v1/messages. Routing and fallback both work with streams. If the primary model fails before the first chunk, the request restarts on the fallback. If it fails mid-stream, the connection closes. There’s no silent mid-stream retry.

​
Errors

The proxy returns a standard JSON error envelope: 
{
  "error": {
    "message": "Limit exceeded: cost usage ($1.23) exceeds $1.00 per day",
    "type": "limit_exceeded",
    "code": 429
  }
}
StatusMeaning
401Invalid or missing Authorization header
402Provider requires payment / quota exceeded on the upstream
424Fallback chain exhausted (all configured models failed)
429Hard limit hit, or Manifest rate limit (THROTTLE_LIMIT) tripped
5xxUpstream provider error (triggers fallback)
Status 424 is the only one that does not trigger a fallback. Manifest returns it itself when the chain is exhausted, so re-routing it would loop forever.

​
Rate limits

Self-hosted instances default to 100 requests per 60 seconds per agent. Override with THROTTLE_TTL and THROTTLE_LIMIT (Environment variables). Cloud rate limits are tied to your plan and shown in the dashboard.

​
Response headers

Every response carries routing headers so your client can see which model handled the request, the assigned tier, and confidence, without parsing the response body.