{ "openapi": "3.1.0", "info": { "title": "Pioneer Inference API", "version": "1.0.0", "description": "Public inference API for Pioneer AI. Covers the Pioneer-native endpoint, OpenAI-compatible endpoints (/v1/chat/completions, /v1/completions, /v1/models), the Anthropic-compatible endpoint (/v1/messages), and inference history. Authenticate with an X-API-Key header (keys begin with pio_sk_).", "contact": { "name": "Pioneer AI", "url": "https://docs.pioneer.ai", "email": "support@pioneer.ai" } }, "servers": [ { "url": "https://api.pioneer.ai", "description": "Production" } ], "security": [ { "ApiKeyAuth": [] }, { "BearerAuth": [] } ], "tags": [ { "name": "inference", "description": "Pioneer-native inference endpoint (encoder NER/classification/extraction and decoder text generation)." }, { "name": "openai-compat", "description": "OpenAI-compatible endpoints. Use with the OpenAI SDK by setting base_url=https://api.pioneer.ai/v1." }, { "name": "anthropic-compat", "description": "Anthropic-compatible endpoints. Use with the Anthropic SDK by setting base_url=https://api.pioneer.ai." }, { "name": "inference-history", "description": "List and retrieve past inference records." } ], "paths": { "/inference": { "post": { "operationId": "run_inference", "summary": "Run inference (Pioneer native)", "description": "Unified inference endpoint for encoder tasks (NER, text classification, JSON extraction) and decoder tasks (text generation). Discriminated by the presence of a `messages` field: include `messages` for decoder generation; use `text` + `schema` for encoder tasks.", "tags": [ "inference" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "oneOf": [ { "$ref": "#/components/schemas/EncoderInferenceRequest" }, { "$ref": "#/components/schemas/GenerateInferenceRequest" } ] }, "examples": { "encoder_ner": { "summary": "NER — extract entities", "value": { "model_id": "YOUR_MODEL_ID", "text": "Apple launched the iPhone 16 in San Francisco.", "schema": { "entities": [ { "name": "organization" }, { "name": "product" }, { "name": "location" } ] } } }, "decoder_generate": { "summary": "Decoder — text generation", "value": { "model_id": "YOUR_MODEL_ID", "task": "generate", "messages": [ { "role": "user", "content": "Summarize this document in one sentence." } ], "max_tokens": 256, "temperature": 0.7 } } } } } }, "responses": { "200": { "description": "Inference result. `type` is `\"encoder\"` for encoder tasks and `\"decoder\"` for generation.", "content": { "application/json": { "schema": { "oneOf": [ { "$ref": "#/components/schemas/EncoderInferenceResponse" }, { "$ref": "#/components/schemas/GenerateInferenceResponse" } ], "discriminator": { "propertyName": "type", "mapping": { "encoder": "#/components/schemas/EncoderInferenceResponse", "decoder": "#/components/schemas/GenerateInferenceResponse" } } } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "402": { "$ref": "#/components/responses/PaymentRequired" }, "404": { "$ref": "#/components/responses/ModelNotFound" }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimited" } } } }, "/v1/chat/completions": { "post": { "operationId": "create_chat_completion", "summary": "Chat completions (OpenAI-compatible)", "description": "OpenAI-compatible chat completions endpoint. Works with the OpenAI Python SDK by setting `base_url=\"https://api.pioneer.ai/v1\"`. Set `stream=true` for SSE streaming. The response includes a `x_pioneer` extension field with `inference_id` and `routed_model`.", "tags": [ "openai-compat" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ChatCompletionRequest" }, "examples": { "simple": { "summary": "Simple chat completion", "value": { "model": "Qwen/Qwen3-8B", "messages": [ { "role": "user", "content": "Hello!" } ] } }, "streaming": { "summary": "Streaming chat completion", "value": { "model": "Qwen/Qwen3-8B", "messages": [ { "role": "user", "content": "Tell me a short story." } ], "stream": true, "max_tokens": 512 } }, "pioneer_auto": { "summary": "Use pioneer/auto router", "value": { "model": "pioneer/auto", "messages": [ { "role": "user", "content": "Classify this text." } ] } } } } } }, "responses": { "200": { "description": "Chat completion result. Returns `application/json` when `stream=false` (default) and `text/event-stream` SSE when `stream=true`. Each SSE event is `data: {...}\\n\\n` terminated by `data: [DONE]\\n\\n`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ChatCompletionResponse" } }, "text/event-stream": { "schema": { "$ref": "#/components/schemas/ChatCompletionStreamChunk" }, "example": "data: {\"id\":\"chatcmpl-abc\",\"object\":\"chat.completion.chunk\",\"created\":0,\"model\":\"Qwen/Qwen3-8B\",\"choices\":[{\"index\":0,\"delta\":{\"content\":\"Hi\"},\"finish_reason\":null}]}\n\ndata: [DONE]\n\n" } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "402": { "$ref": "#/components/responses/PaymentRequired" }, "404": { "$ref": "#/components/responses/ModelNotFound" }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimited" } } } }, "/v1/completions": { "post": { "operationId": "create_text_completion", "summary": "Text completions (OpenAI-compatible)", "description": "OpenAI-compatible legacy text completions endpoint. Accepts a `prompt` string and returns a completion. Set `stream=true` for SSE streaming.", "tags": [ "openai-compat" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TextCompletionRequest" }, "examples": { "simple": { "summary": "Simple text completion", "value": { "model": "Qwen/Qwen3-8B-Base", "prompt": "The capital of France is", "max_tokens": 32 } } } } } }, "responses": { "200": { "description": "Text completion result. `application/json` when `stream=false`, `text/event-stream` SSE when `stream=true`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/TextCompletionResponse" } }, "text/event-stream": { "schema": { "$ref": "#/components/schemas/TextCompletionStreamChunk" }, "example": "data: {\"id\":\"cmpl-abc\",\"object\":\"text_completion\",\"created\":0,\"model\":\"Qwen/Qwen3-8B-Base\",\"choices\":[{\"index\":0,\"text\":\" Paris.\",\"finish_reason\":\"stop\"}]}\n\ndata: [DONE]\n\n" } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "402": { "$ref": "#/components/responses/PaymentRequired" }, "404": { "$ref": "#/components/responses/ModelNotFound" }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimited" } } } }, "/v1/models": { "get": { "operationId": "list_models", "summary": "List available models", "description": "Returns the Pioneer model catalog including base encoder models (GLiNER), base decoder LLMs, and any fine-tuned models you have deployed. Compatible with both Anthropic and OpenAI model-list consumers.", "tags": [ "anthropic-compat" ], "parameters": [ { "name": "limit", "in": "query", "schema": { "type": "integer", "minimum": 1 }, "description": "Maximum number of models to return. Omit for the full catalog." }, { "name": "before_id", "in": "query", "schema": { "type": "string" }, "description": "Cursor for paginating backward (Anthropic-style)." }, { "name": "after_id", "in": "query", "schema": { "type": "string" }, "description": "Cursor for paginating forward (Anthropic-style)." } ], "responses": { "200": { "description": "Combined Anthropic-compatible and OpenAI-compatible model catalog.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ModelListResponse" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" } } } }, "/v1/messages": { "post": { "operationId": "create_message", "summary": "Messages (Anthropic-compatible)", "description": "Anthropic Messages API compatible endpoint. Works with the Anthropic Python SDK by setting `base_url=\"https://api.pioneer.ai\"`. Set `stream=true` for SSE streaming in Anthropic event format. Extended-thinking is supported via the `thinking` field.", "tags": [ "anthropic-compat" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AnthropicMessagesRequest" }, "examples": { "simple": { "summary": "Simple message", "value": { "model": "claude-sonnet-4-6", "max_tokens": 1024, "messages": [ { "role": "user", "content": "Hello, Claude!" } ] } }, "with_system": { "summary": "Message with system prompt", "value": { "model": "claude-sonnet-4-6", "max_tokens": 512, "system": "You are a helpful assistant.", "messages": [ { "role": "user", "content": "What is the weather like?" } ] } }, "streaming": { "summary": "Streaming message", "value": { "model": "claude-sonnet-4-6", "max_tokens": 1024, "stream": true, "messages": [ { "role": "user", "content": "Write a haiku about inference routing." } ] } } } } } }, "responses": { "200": { "description": "Message response. `application/json` when `stream=false`, `text/event-stream` SSE (Anthropic event format) when `stream=true`.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/AnthropicMessagesResponse" } }, "text/event-stream": { "schema": { "type": "string" }, "example": "event: message_start\ndata: {\"type\":\"message_start\",\"message\":{\"id\":\"msg_abc\",\"type\":\"message\",\"role\":\"assistant\",\"content\":[],\"model\":\"claude-sonnet-4-6\",\"stop_reason\":null,\"usage\":{\"input_tokens\":10,\"output_tokens\":0}}}\n\nevent: content_block_delta\ndata: {\"type\":\"content_block_delta\",\"index\":0,\"delta\":{\"type\":\"text_delta\",\"text\":\"Hello\"}}\n\nevent: message_stop\ndata: {\"type\":\"message_stop\"}\n\n" } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "402": { "$ref": "#/components/responses/PaymentRequired" }, "404": { "$ref": "#/components/responses/ModelNotFound" }, "422": { "$ref": "#/components/responses/ValidationError" }, "429": { "$ref": "#/components/responses/RateLimited" } } } }, "/inferences": { "get": { "operationId": "list_inferences", "summary": "List inference history", "description": "Paginated list of past inference records for the authenticated user's team. Supports filtering by model, project, task type, latency range, and LLM-as-Judge score.", "tags": [ "inference-history" ], "parameters": [ { "name": "limit", "in": "query", "schema": { "type": "integer", "minimum": 1, "maximum": 500, "default": 100 }, "description": "Maximum records to return." }, { "name": "offset", "in": "query", "schema": { "type": "integer", "minimum": 0, "default": 0 }, "description": "Records to skip for pagination." }, { "name": "model_id", "in": "query", "schema": { "type": "string" }, "description": "Filter by model ID." }, { "name": "project_id", "in": "query", "schema": { "type": "string" }, "description": "Filter by project ID." }, { "name": "training_job_id", "in": "query", "schema": { "type": "string" }, "description": "Filter by training job UUID." }, { "name": "task", "in": "query", "schema": { "type": "string" }, "description": "Filter by task type (extract_entities, classify_text, extract_json, generate)." }, { "name": "latency_min", "in": "query", "schema": { "type": "number", "minimum": 0 }, "description": "Minimum latency in ms." }, { "name": "latency_max", "in": "query", "schema": { "type": "number", "minimum": 0 }, "description": "Maximum latency in ms." }, { "name": "llmaj_score_min", "in": "query", "schema": { "type": "number", "minimum": 0, "maximum": 1 }, "description": "Minimum LLM-as-Judge score [0.0, 1.0]." }, { "name": "llmaj_score_max", "in": "query", "schema": { "type": "number", "minimum": 0, "maximum": 1 }, "description": "Maximum LLM-as-Judge score [0.0, 1.0]." }, { "name": "since", "in": "query", "schema": { "type": "string", "format": "date-time" }, "description": "Return records created at or after this ISO 8601 timestamp." }, { "name": "until", "in": "query", "schema": { "type": "string", "format": "date-time" }, "description": "Return records created at or before this ISO 8601 timestamp." } ], "responses": { "200": { "description": "Paginated list of inference records.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InferenceListResponse" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" } } } }, "/inferences/{inference_id}": { "get": { "operationId": "get_inference", "summary": "Get an inference record", "description": "Retrieve a single inference record by ID. Includes LLM-as-Judge verdict and score when judging has completed (fields are null until then).", "tags": [ "inference-history" ], "parameters": [ { "name": "inference_id", "in": "path", "required": true, "schema": { "type": "string" }, "description": "The inference record UUID returned in `inference_id` on any inference response." } ], "responses": { "200": { "description": "The inference record.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InferenceRecord" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "404": { "$ref": "#/components/responses/NotFound" } } } }, "/inferences/{inference_id}/feedback": { "post": { "operationId": "submit_inference_feedback", "summary": "Submit inference feedback", "description": "Submit a human correction on a past inference. Corrections are used as labeled examples for Adaptive Inference — Pioneer's continuous improvement loop that retrains your model on corrected live-traffic examples.", "tags": [ "inference-history" ], "parameters": [ { "name": "inference_id", "in": "path", "required": true, "schema": { "type": "string" }, "description": "The inference record UUID to annotate." } ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InferenceFeedbackRequest" }, "examples": { "correct": { "summary": "Mark as correct", "value": { "verdict": "correct" } }, "incorrect": { "summary": "Mark as incorrect with correction", "value": { "verdict": "incorrect", "corrected_output": { "entities": [ { "text": "Apple", "label": "organization", "start": 0, "end": 5 }, { "text": "iPhone", "label": "product", "start": 18, "end": 24 } ] }, "notes": "Missed the product entity" } } } } } }, "responses": { "200": { "description": "Feedback recorded.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/InferenceFeedbackResponse" } } } }, "401": { "$ref": "#/components/responses/Unauthorized" }, "404": { "$ref": "#/components/responses/NotFound" }, "422": { "$ref": "#/components/responses/ValidationError" } } } } }, "components": { "securitySchemes": { "ApiKeyAuth": { "type": "apiKey", "in": "header", "name": "X-API-Key", "description": "Pioneer API key. Generate one at https://agent.pioneer.ai/settings/api-keys. Keys begin with `pio_sk_`." }, "BearerAuth": { "type": "http", "scheme": "bearer", "bearerFormat": "JWT", "description": "Supabase access token or Pioneer API key as a Bearer token." } }, "responses": { "Unauthorized": { "description": "Missing or invalid API key.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "PaymentRequired": { "description": "Insufficient credits or no active billing plan.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "NotFound": { "description": "Resource not found.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "ModelNotFound": { "description": "Model ID not found or not yet deployed.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } }, "ValidationError": { "description": "Request body failed schema validation.", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ValidationErrorResponse" } } } }, "RateLimited": { "description": "Rate limit exceeded. Retry after the duration in the `Retry-After` response header.", "headers": { "Retry-After": { "schema": { "type": "integer" }, "description": "Seconds to wait before retrying." } }, "content": { "application/json": { "schema": { "$ref": "#/components/schemas/ErrorResponse" } } } } }, "schemas": { "ErrorResponse": { "type": "object", "properties": { "detail": { "oneOf": [ { "type": "string" }, { "type": "object" } ], "description": "Human-readable error message or structured detail object." } } }, "ValidationErrorResponse": { "type": "object", "properties": { "detail": { "type": "array", "items": { "type": "object", "properties": { "loc": { "type": "array", "items": { "oneOf": [ { "type": "string" }, { "type": "integer" } ] } }, "msg": { "type": "string" }, "type": { "type": "string" } } } } } }, "ReasoningConfig": { "type": "object", "description": "Opt-in reasoning / extended-thinking controls. Normalized across providers — Anthropic (`thinking`), OpenAI/Fireworks (`reasoning_effort`), OpenRouter (`reasoning`). Pioneer does not enable reasoning by default.", "properties": { "enabled": { "type": "boolean", "default": true, "description": "Set false to explicitly disable thinking on models that have it on by default." }, "effort": { "type": "string", "enum": [ "minimal", "low", "medium", "high", "xhigh", "none" ], "description": "OpenAI/Grok-style effort tier. Mutually exclusive with `max_tokens`." }, "max_tokens": { "type": "integer", "minimum": 1, "description": "Anthropic-style reasoning budget in tokens. Mutually exclusive with `effort`." }, "mode": { "type": "string", "enum": [ "manual", "adaptive" ], "description": "Anthropic extended-thinking dispatch mode. Leave unset to let Pioneer pick the per-model default." }, "display": { "type": "string", "enum": [ "summarized", "omitted" ], "description": "Whether thinking text streams back (`summarized`) or is omitted to save latency (`omitted`)." }, "exclude": { "type": "boolean", "default": false, "description": "Model reasons internally but reasoning tokens are not returned to the caller." } } }, "EncoderInferenceRequest": { "type": "object", "required": [ "model_id", "text", "schema" ], "description": "Request for encoder (GLiNER) tasks. Discriminated from GenerateInferenceRequest by the absence of a `messages` field.", "properties": { "model_id": { "type": "string", "description": "Training job UUID, project name, or base encoder model ID (e.g. `fastino/gliner2-base-v1`)." }, "text": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } } ], "description": "Input text or list of texts for batch processing." }, "schema": { "oneOf": [ { "type": "object", "description": "Unified extraction schema dict with keys: entities, classifications, structures, relations." }, { "type": "array", "items": { "type": "string" }, "description": "Deprecated flat entity label list. Use the dict form instead." } ], "description": "Extraction schema. Use the unified dict form: `{\"entities\": [{\"name\": \"organization\"}]}`." }, "threshold": { "type": "number", "minimum": 0, "maximum": 1, "default": 0.5, "description": "Confidence threshold for predictions." }, "include_confidence": { "type": "boolean", "default": true }, "include_spans": { "type": "boolean", "default": true, "description": "Include character-level start/end positions." }, "store": { "type": "boolean", "default": true, "description": "Persist to inference history. Set false to opt out." }, "project_id": { "type": "string", "description": "Project ID for attribution and auto-improvement." } } }, "GenerateInferenceRequest": { "type": "object", "required": [ "model_id", "task", "messages" ], "description": "Request for decoder text generation. Discriminated from EncoderInferenceRequest by the presence of a `messages` field.", "properties": { "model_id": { "type": "string", "description": "Training job UUID, project name, or base decoder model ID (e.g. `Qwen/Qwen3-8B`)." }, "task": { "type": "string", "enum": [ "generate" ] }, "messages": { "type": "array", "minItems": 1, "items": { "type": "object", "required": [ "role", "content" ], "properties": { "role": { "type": "string", "enum": [ "system", "user", "assistant" ] }, "content": { "type": "string" } } }, "description": "Chat messages. The last message must have role `\"user\"`." }, "max_tokens": { "type": "integer", "minimum": 1, "maximum": 131072 }, "temperature": { "type": "number", "minimum": 0, "maximum": 2 }, "top_p": { "type": "number", "minimum": 0, "maximum": 1 }, "reasoning": { "$ref": "#/components/schemas/ReasoningConfig" }, "include_reasoning_trace": { "type": "boolean", "default": false, "description": "Return extracted `` trace text separately in the response." }, "store": { "type": "boolean", "default": true, "description": "Persist to inference history. Set false to opt out." }, "project_id": { "type": "string" } } }, "EncoderInferenceResponse": { "type": "object", "required": [ "type", "inference_id", "result", "model_id", "latency_ms", "token_usage", "model_used" ], "properties": { "type": { "type": "string", "enum": [ "encoder" ] }, "inference_id": { "type": "string", "description": "Unique inference ID. Use with GET /inferences/{inference_id} or POST /inferences/{inference_id}/feedback." }, "result": { "oneOf": [ { "type": "object" }, { "type": "array" } ], "description": "Extraction result. Shape depends on the schema and task." }, "model_id": { "type": "string" }, "latency_ms": { "type": "number", "description": "Server-side inference latency in milliseconds." }, "token_usage": { "type": "integer", "description": "Input tokens processed." }, "model_used": { "type": "string", "description": "Resolved model identifier." } } }, "GenerateInferenceResponse": { "type": "object", "required": [ "type", "inference_id", "completion", "model_id", "latency_ms" ], "properties": { "type": { "type": "string", "enum": [ "decoder" ] }, "inference_id": { "type": "string", "description": "Unique inference ID." }, "completion": { "type": "string", "description": "Generated text." }, "reasoning_trace": { "type": "string", "description": "Extracted `` reasoning trace when `include_reasoning_trace=true`." }, "model_id": { "type": "string" }, "latency_ms": { "type": "number" } } }, "PioneerExtension": { "type": "object", "description": "Pioneer-specific extension on OpenAI-compatible responses.", "properties": { "inference_id": { "type": "string", "description": "Pioneer inference record ID. Use with GET /inferences/{inference_id} to poll for async LLM-judge results. Null when persistence was disabled." }, "routed_model": { "type": "string", "description": "Actual backend model selected by a router project (e.g. `pioneer/auto`). Null when not routed." } } }, "ChatCompletionRequest": { "type": "object", "required": [ "model", "messages" ], "properties": { "model": { "type": "string", "description": "Model ID, project name, or `pioneer/auto` for automatic routing." }, "messages": { "type": "array", "minItems": 1, "items": { "type": "object", "properties": { "role": { "type": "string" }, "content": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object" } } ] }, "tool_calls": { "type": "array" }, "tool_call_id": { "type": "string" } } } }, "temperature": { "type": "number" }, "max_tokens": { "type": "integer", "minimum": 1, "maximum": 131072 }, "stream": { "type": "boolean", "default": false }, "stop": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } } ] }, "response_format": { "type": "object" }, "tools": { "type": "array" }, "tool_choice": { "oneOf": [ { "type": "string" }, { "type": "object" } ] }, "top_p": { "type": "number" }, "store": { "type": "boolean", "default": true, "description": "Persist to inference history. Set false to opt out." }, "metadata": { "type": "object", "description": "Pioneer reads `metadata.project_id` for attribution." }, "reasoning": { "type": "object", "description": "Opt-in reasoning controls (OpenRouter-normalized). Keys: enabled, effort (minimal/low/medium/high/xhigh/none), max_tokens, exclude, mode (manual/adaptive, Anthropic-only), display (summarized/omitted, Anthropic-only). effort and max_tokens are mutually exclusive." }, "schema": { "oneOf": [ { "type": "object" }, { "type": "array", "items": { "type": "string" } } ], "description": "Pioneer encoder extension: extraction schema dict." }, "seed": { "type": "integer" }, "n": { "type": "integer" }, "presence_penalty": { "type": "number" }, "frequency_penalty": { "type": "number" }, "user": { "type": "string" } } }, "ChatCompletionResponse": { "type": "object", "required": [ "id", "object", "created", "model", "choices", "usage" ], "properties": { "id": { "type": "string" }, "object": { "type": "string", "enum": [ "chat.completion" ] }, "created": { "type": "integer" }, "model": { "type": "string" }, "choices": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "integer" }, "message": { "type": "object" }, "finish_reason": { "type": "string" } } } }, "usage": { "$ref": "#/components/schemas/UsageStats" }, "x_pioneer": { "$ref": "#/components/schemas/PioneerExtension" } } }, "ChatCompletionStreamChunk": { "type": "object", "description": "One SSE event payload when `stream=true`. Terminal chunk carries `finish_reason` and optionally `usage` and `x_pioneer`. Stream ends with `data: [DONE]`.", "properties": { "id": { "type": "string" }, "object": { "type": "string", "enum": [ "chat.completion.chunk" ] }, "created": { "type": "integer" }, "model": { "type": "string" }, "choices": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "integer" }, "delta": { "type": "object", "properties": { "content": { "type": "string" }, "reasoning_content": { "type": "string", "description": "Chain-of-thought tokens (de facto vLLM/DeepSeek/Fireworks/OpenRouter extension)." }, "tool_calls": { "type": "array" } } }, "finish_reason": { "type": "string" } } } }, "usage": { "$ref": "#/components/schemas/UsageStats" }, "x_pioneer": { "$ref": "#/components/schemas/PioneerExtension" } } }, "TextCompletionRequest": { "type": "object", "required": [ "model", "prompt" ], "properties": { "model": { "type": "string" }, "prompt": { "type": "string" }, "temperature": { "type": "number" }, "max_tokens": { "type": "integer", "minimum": 1, "maximum": 131072 }, "stream": { "type": "boolean" }, "stop": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } } ] }, "echo": { "type": "boolean", "default": false }, "logprobs": { "type": "integer", "minimum": 0, "maximum": 20 }, "store": { "type": "boolean", "default": true }, "reasoning": { "type": "object" } } }, "TextCompletionResponse": { "type": "object", "required": [ "id", "object", "created", "model", "choices", "usage" ], "properties": { "id": { "type": "string" }, "object": { "type": "string", "enum": [ "text_completion" ] }, "created": { "type": "integer" }, "model": { "type": "string" }, "choices": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "integer" }, "text": { "type": "string" }, "logprobs": { "type": "object" }, "finish_reason": { "type": "string" }, "reasoning_content": { "type": "string" } } } }, "usage": { "$ref": "#/components/schemas/UsageStats" }, "x_pioneer": { "$ref": "#/components/schemas/PioneerExtension" } } }, "TextCompletionStreamChunk": { "type": "object", "description": "One SSE event payload for /v1/completions when `stream=true`.", "properties": { "id": { "type": "string" }, "object": { "type": "string", "enum": [ "text_completion" ] }, "created": { "type": "integer" }, "model": { "type": "string" }, "choices": { "type": "array", "items": { "type": "object", "properties": { "index": { "type": "integer" }, "text": { "type": "string" }, "finish_reason": { "type": "string" }, "reasoning_content": { "type": "string" } } } }, "usage": { "$ref": "#/components/schemas/UsageStats" }, "x_pioneer": { "$ref": "#/components/schemas/PioneerExtension" } } }, "UsageStats": { "type": "object", "properties": { "prompt_tokens": { "type": "integer" }, "completion_tokens": { "type": "integer" }, "total_tokens": { "type": "integer" }, "prompt_tokens_details": { "type": "object", "properties": { "cached_tokens": { "type": "integer", "description": "Input tokens served from cache (cache read)." }, "cache_write_tokens": { "type": "integer", "description": "Input tokens written to cache (cache creation)." } } } } }, "AnthropicMessagesRequest": { "type": "object", "required": [ "model", "messages", "max_tokens" ], "properties": { "model": { "type": "string", "description": "Model ID (e.g. `claude-sonnet-4-6`, `claude-opus-4-8`)." }, "messages": { "type": "array", "minItems": 1, "items": { "type": "object", "required": [ "role", "content" ], "properties": { "role": { "type": "string", "enum": [ "user", "assistant" ] }, "content": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object" } } ] } } } }, "max_tokens": { "type": "integer", "minimum": 1, "maximum": 131072, "default": 1024 }, "system": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object" } } ], "description": "System prompt. Accepts a plain string or list of Anthropic system content blocks (with cache_control support)." }, "temperature": { "type": "number", "minimum": 0, "maximum": 1 }, "top_p": { "type": "number", "minimum": 0, "maximum": 1 }, "top_k": { "type": "integer", "minimum": 1 }, "stream": { "type": "boolean", "default": false }, "stop_sequences": { "type": "array", "items": { "type": "string" } }, "tools": { "type": "array", "items": { "type": "object" } }, "tool_choice": { "type": "object" }, "thinking": { "type": "object", "description": "Anthropic-native extended-thinking config. Examples: `{\"type\": \"enabled\", \"budget_tokens\": 8000}` for manual mode; `{\"type\": \"adaptive\", \"effort\": \"high\"}` for adaptive mode (required on Opus 4.7+); `{\"type\": \"disabled\"}` to turn off. Pioneer auto-upgrades manual configs on models that require adaptive." }, "store": { "type": "boolean", "default": true, "description": "Persist to inference history. Set false to opt out." }, "schema": { "oneOf": [ { "type": "object" }, { "type": "array", "items": { "type": "string" } } ], "description": "Pioneer encoder extension: extraction schema dict." } } }, "AnthropicMessagesResponse": { "type": "object", "required": [ "id", "type", "role", "content", "model", "stop_reason", "usage" ], "properties": { "id": { "type": "string" }, "type": { "type": "string", "enum": [ "message" ] }, "role": { "type": "string", "enum": [ "assistant" ] }, "content": { "type": "array", "items": { "type": "object", "properties": { "type": { "type": "string", "enum": [ "text", "tool_use", "thinking" ] }, "text": { "type": "string" } } } }, "model": { "type": "string" }, "stop_reason": { "type": "string", "enum": [ "end_turn", "max_tokens", "stop_sequence", "tool_use" ] }, "stop_sequence": { "type": "string" }, "usage": { "type": "object", "properties": { "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" }, "cache_read_input_tokens": { "type": "integer" }, "cache_creation_input_tokens": { "type": "integer" } } } } }, "ModelListResponse": { "type": "object", "properties": { "data": { "type": "array", "items": { "type": "object", "properties": { "id": { "type": "string", "description": "Model identifier used in API requests." }, "type": { "type": "string", "enum": [ "model" ] }, "display_name": { "type": "string" }, "created_at": { "type": "string", "format": "date-time" } } } }, "has_more": { "type": "boolean" }, "first_id": { "type": "string" }, "last_id": { "type": "string" } } }, "InferenceRecord": { "type": "object", "required": [ "id", "user_id", "model_id", "input", "source", "status", "created_at" ], "properties": { "id": { "type": "string" }, "user_id": { "type": "string" }, "model_id": { "type": "string" }, "model_name": { "type": "string" }, "task": { "type": "string" }, "input": { "type": "string" }, "output": {}, "latency_ms": { "type": "integer" }, "tokens": { "type": "integer" }, "input_tokens": { "type": "integer" }, "output_tokens": { "type": "integer" }, "cache_read_tokens": { "type": "integer" }, "cache_write_tokens": { "type": "integer" }, "source": { "type": "string", "enum": [ "api", "ui" ] }, "status": { "type": "string", "enum": [ "success", "failed" ] }, "error_type": { "type": "string", "enum": [ "validation", "timeout", "model_not_ready", "model_not_found", "model_not_supported", "capacity_exhausted", "internal" ] }, "error_message": { "type": "string" }, "created_at": { "type": "string", "format": "date-time" }, "project_id": { "type": "string" }, "training_job_id": { "type": "string" }, "provider": { "type": "string" }, "base_model": { "type": "string" }, "metadata": { "type": "object" }, "human_verdict": { "type": "string", "enum": [ "correct", "incorrect" ] }, "human_corrected_output": {}, "human_feedback_notes": { "type": "string" }, "human_feedback_at": { "type": "string", "format": "date-time" }, "llmaj_verdict": { "type": "string", "enum": [ "pass", "fail", "uncertain" ], "description": "LLM-as-Judge verdict. Null until judging completes." }, "llmaj_score": { "type": "number", "description": "LLM-as-Judge confidence score [0.0, 1.0]. Null until judging completes." }, "llmaj_judged_at": { "type": "string", "format": "date-time" }, "llmaj_reasoning": { "type": "string" } } }, "InferenceListResponse": { "type": "object", "required": [ "inferences", "total", "limit", "offset" ], "properties": { "inferences": { "type": "array", "items": { "$ref": "#/components/schemas/InferenceRecord" } }, "total": { "type": "integer", "description": "Total matching records (for pagination)." }, "limit": { "type": "integer" }, "offset": { "type": "integer" } } }, "InferenceFeedbackRequest": { "type": "object", "required": [ "verdict" ], "properties": { "verdict": { "type": "string", "enum": [ "correct", "incorrect" ] }, "corrected_output": { "description": "Required when verdict is `incorrect`. Shape should match the original inference schema." }, "notes": { "type": "string", "maxLength": 5000 } } }, "InferenceFeedbackResponse": { "type": "object", "properties": { "inference_id": { "type": "string" }, "human_verdict": { "type": "string" }, "human_feedback_at": { "type": "string", "format": "date-time" } } } } } }