Call the API in one minute.

Endpoint reference

Inferway keeps the OpenAI-compatible path small and predictable, then exposes account, billing, usage, and agent operations as separate first-party endpoints.

Interactions: one route, five operations

Video generation does not return inline. Every call goes to POST /v1/interactions and names the operation in the body's op field; the job is durable, so a dropped connection never loses work already paid for.

• mode must be "background". Synchronous and streaming modes are rejected with 422; there is no inline variant of this route.
• Idempotency-Key is required on create. The same key with the same request returns the original receipt without charging again; the same key with a different request fails closed with 409.
• model, mode, duration_seconds and prompt are all top-level fields of the request body. duration_seconds is required and accepts only the published whole-second tiers — it is what the job is billed on.
• Poll with the get operation until the state is terminal. Our own console polls every 2 seconds; there is no webhook and no long-poll.

Supported public endpoints are POST /v1/chat/completions, POST /v1/interactions and GET /v1/models. The legacy POST /v1/completions is not served: it answers 501 (not implemented) and names the chat completions route to use instead. POST /v1/messages (Anthropic-format) is served and open to API keys; every request must carry the anthropic-version: 2023-06-01 header.

Choose a model to see its published capability facts. API examples and tool setup use the same selection.

No model is currently selected.

Authentication

• API keys. Every key is prefixed inferway_live_… and is issued for server-side workloads.
• Key expiry. When you create a key in the Console, you can give it a fixed expiry date or have it expire a set time after its first call. The first request that uses the key for real work starts the countdown; listing models or checking on a video job does not. Once started, it never pauses or resets. Rotating a key before its countdown starts gives the new key the same countdown. An expired key gets 401, the same as an invalid one.
• Browser apps. Do not expose direct keys client-side; proxy requests through your backend.

Error codes

Inferway returns OpenAI-compatible error objects: {"error": { "type": "...", "message": "...", "code": "..." }}

Live error catalog

The complete set of error codes /v1/chat/completions and /v1/agent/chat can return, read from the gateway's own catalog rather than transcribed. Each row carries the HTTP status, whether a retry is safe, and the exact message the API sends. Checkout, billing and key-management endpoints return their own codes, not listed here.

Platform rate limits and quotas

These are platform request windows and account quotas, not generation-capability or retention claims for an unselected model.

Next steps