Reference

API Reference

Complete type reference for all Skytells Inference sub-APIs — Chat, Responses, and Embeddings. Every request parameter, response object, and stream event is defined here.

Reference

This section is the canonical type and object reference for all Skytells Inference sub-APIs. Its purpose is precise cross-linking — throughout the rest of the docs, when a guide says "returns a ChatCompletion object" or "emits a ResponsesStreamEvent", those links point here.

Each sub-API has three pages:

  • Overview (index) — what the API does, its endpoint at a glance, and SDK access pattern.
  • Create (create) — the full endpoint reference: every request parameter, the response type it returns, streaming behavior, and multi-client code examples.
  • Objects (objects) — named, linkable definitions of every response type, schema object, and stream event the API emits.

Language Model Objects

These objects are used to represent the response from v1/chat/completions, v1/responses, and v1/embeddings.

ObjectAPIDescription
ChatCompletionChatNon-streaming response from POST /v1/chat/completions
ChatCompletionChunkChatOne SSE chunk in a streaming chat response
ChatMessageChatA single message inside choices[].message
ChatCompletionUsageChatToken counts for a chat completion
ContentFilterResultsChatPer-choice safety evaluation (hate, violence, etc.)
PromptFilterResultsChatPrompt-level safety evaluation including jailbreak detection
ResponseResponsesThe full response object from POST /v1/responses
OutputItemResponsesOne entry in response.output[]
OutputTextContentResponsesText content within an OutputItem
ContentFilterResponsesPrompt or completion safety filter entry
ResponsesUsageResponsesInput/output token counts for a response
ResponsesStreamEventResponsesDiscriminated union of all 9 SSE event types
EmbeddingResponseEmbeddingsFull response from POST /v1/embeddings
EmbeddingEmbeddingsOne vector entry inside EmbeddingResponse.data[]
EmbeddingUsageEmbeddingsToken counts for an embedding request

Prediction Objects

These objects are used to represent the response from v1/predictions.

ObjectAPIDescription
PredictionPredictionsThe full response object from POST /v1/predictions

Model Objects

These objects are used to represent the response from v1/models.

ObjectAPIDescription
ModelModelsThe full response object from GET /v1/models/{slug}
ModelSchemaModelsThe JSON Schema for the model's input and output

SDK Clients

All Inference sub-APIs are covered by the Skytells TypeScript SDK and fully compatible with the OpenAI SDK (change base_url only).

ClientPackageAccess Pattern
Skytells SDKnpm install skytellsclient.chat.completions.create() / client.responses.create() / client.embeddings.create()
OpenAI SDKnpm install openaiSame methods — set baseURL: "https://api.skytells.ai/v1"
RESTcurl https://api.skytells.ai/v1/... with x-api-key header

For more information on the SDKs, see the SDKs page.

How is this guide?

On this page