Skip to content

Inference proxy

The proxy is the inference entry point. It mirrors the upstream OpenAI/Anthropic API surface, with your token in the URL path.

Prefer to pay per request with no token at all? See Pay per request with x402.

https://api.usepod.ai/proxy/<token>/... # Anthropic-compatible
https://api.usepod.ai/proxy/<token>/v1/... # OpenAI-compatible

Common endpoints behind the proxy:

Endpoint Surface
/v1/chat/completions OpenAI chat completions (streaming and non-streaming)
/v1/messages Anthropic messages
/v1/models Model listing
/v1/responses (also /responses) OpenAI Responses API, translated onto the same routing and billing as chat completions. Streaming and tool calls work; stateless — previous_response_id is rejected, so clients resend history — and hosted tools (web_search, file_search, tool_search) are ignored. Used by Codex CLI, which speaks only this surface.
Header Required Meaning
Content-Type: application/json yes Standard JSON body
X-Pod-Max-Price-Input no Max price per million input tokens (USDC microunits)
X-Pod-Max-Price-Output no Max price per million output tokens (USDC microunits)
X-Pod-Routing-Mode no auto (default), marketplace-only, or centralized-only
X-Pod-Providers no Comma-separated provider names to pin this request to

The Authorization / api_key your SDK sends is ignored — auth is the token in the path. See Spend controls for the price headers and Routing & matching for the routing headers.

Header Meaning
X-Balance-Remaining Remaining token balance after this request
X-Pod-Route Which source served the request: marketplace, key relay, or centralized
X-Pod-Provider-Id The specific provider that served it — a provider name for centralized routes, a provider UUID for marketplace and key-relay routes
Limit Value Applies to When exceeded
Request size 15 MiB (15,728,640 bytes) per request Inference endpoints: chat completions, messages, Responses, token counting, image generation and edits, and the x402 routes 413
Requests per minute Set per token Requests made with a token 429 with Retry-After
Concurrent requests Set per token Requests made with a token 429 with Retry-After

Request size is measured on the raw HTTP body, so base64-encoded images count at their encoded size. An oversized request is rejected on arrival, before routing, and nothing is billed.

  • A body over the request size limit returns 413.
  • Going over the requests-per-minute or concurrency limit returns 429.
  • A token with no balance is rejected before any upstream call.
  • An unknown token returns 401.
  • In marketplace-only mode, no provider at your price returns a dedicated no-provider result rather than billing at a higher price.

Streaming responses are relayed byte-for-byte from the selected source; token usage is extracted from the stream for settlement.