Gateway protocols and measures
Generated from Metering.GATEWAY_API_KINDS. All listed routes use POST. Streaming means chat-style server-sent-event support; speech may return incremental audio separately. A mounted API does not imply every model or provider supports it.
| API | Path | Request shape | SSE streaming | Measures |
|---|---|---|---|---|
| Chat Completions | /v1/chat/completions | JSON model, messages; optional stream | Yes | requests, tokens, costMicros |
| Completions | /v1/completions | JSON model, prompt; optional stream | Yes | requests, tokens, costMicros |
| Responses | /v1/responses | JSON model, input; optional stream | Yes | requests, tokens |
| Messages | /v1/messages | Anthropic JSON model, messages, max_tokens; optional stream | Yes | requests, tokens |
| Embeddings | /v1/embeddings | JSON model, input | No | requests, tokens |
| Image generation | /v1/images/generations | JSON model, prompt and model options | No | requests, images |
| Image editing | /v1/images/edits | Provider-compatible multipart image input | No | requests, images |
| Speech | /v1/audio/speech | Provider-specific JSON text, voice and model | No | requests, characters, audioMilliseconds, audioBytes |
| Transcription | /v1/audio/transcriptions | Multipart file, model | No | requests, audioMilliseconds, audioBytes |
| Translation | /v1/audio/translations | Multipart file, model | No | requests, audioMilliseconds, audioBytes |
| System One | /v1/systemone | JSON state, questions | No | requests, tokens |
costMicros is an estimated provider cost in millionths of a US dollar, not a subscription credit balance. Audio duration uses milliseconds and audio size uses bytes internally; the Modem UI can present different units.
See request authentication and provider compatibility, limits and estimates, and product configuration.
Last updated on