{ "openapi": "3.1.0", "info": { "title": "Inference APIs", "version": "2026-09-18", "summary": "OpenAI-compatible inference for open-weight models, embeddings, rerank and speech.", "description": "Base URL https://api.inferenceapis.com/v1. Requests and responses follow the OpenAI wire format; the official OpenAI SDKs work with base_url changed. Prepaid, per-token billing, no rate limits on your requests. Plain-text overview for agents: https://inferenceapis.com/llms.txt. Errors: https://inferenceapis.com/docs/errors.", "contact": { "name": "Inference APIs", "url": "https://inferenceapis.com/contact", "email": "support@inferenceapis.com" }, "termsOfService": "https://inferenceapis.com/terms" }, "servers": [ { "url": "https://api.inferenceapis.com/v1" } ], "security": [ { "bearer": [] } ], "tags": [ { "name": "chat" }, { "name": "embeddings" }, { "name": "audio" }, { "name": "account" } ], "paths": { "/signup": { "post": { "tags": [ "account" ], "security": [], "summary": "Create an account and an API key without a browser", "description": "Returns a working key with a zero balance. The $1 starter credit is added when the person opens the confirmation email. Funds are added by a person at https://inferenceapis.com/billing. One account per email, throwaway domains refused, 5 signups per IP per day.", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "email" ], "properties": { "email": { "type": "string", "format": "email" }, "name": { "type": "string", "maxLength": 100 }, "password": { "type": "string", "minLength": 8, "description": "Optional. Without one, the person signs in with an emailed link." }, "key_name": { "type": "string" } } } } } }, "responses": { "201": { "description": "Created", "content": { "application/json": { "schema": { "type": "object", "properties": { "object": { "type": "string", "const": "signup" }, "email": { "type": "string" }, "api_key": { "type": "string", "description": "Shown once" }, "base_url": { "type": "string" }, "balance": { "type": "number" }, "starter_credit": { "type": "object" }, "top_up_url": { "type": "string" }, "dashboard": { "type": "object" }, "next_steps": { "type": "array", "items": { "type": "string" } }, "docs": { "type": "string" } } } } } }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "429": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/models": { "get": { "tags": [ "account" ], "security": [], "summary": "List models with prices, context length and capabilities", "responses": { "200": { "description": "OK", "content": { "application/json": { "schema": { "type": "object", "properties": { "object": { "type": "string" }, "data": { "type": "array", "items": { "$ref": "#/components/schemas/Model" } } } } } } } } } }, "/chat/completions": { "post": { "tags": [ "chat" ], "summary": "Chat completion (OpenAI format), streaming, tools, JSON mode, vision", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "messages" ], "properties": { "model": { "type": "string", "description": "Chat or vision model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "openai/gpt-oss-120b", "deepseek-ai/DeepSeek-V4-Flash", "deepseek-ai/DeepSeek-V4.1-Flash", "zai-org/GLM-5.3-Flash", "meta-llama/Llama-3.3-70B-Instruct-Turbo", "zai-org/GLM-5.3", "deepseek-ai/DeepSeek-V4-Pro", "MiniMaxAI/MiniMax-M3", "moonshotai/Kimi-K2.7-Code", "Qwen/Qwen3-VL-235B-A22B-Instruct" ] }, "messages": { "type": "array", "items": { "type": "object", "required": [ "role", "content" ], "properties": { "role": { "type": "string", "enum": [ "system", "developer", "user", "assistant", "tool" ] }, "content": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object" } } ] }, "name": { "type": "string" }, "tool_calls": { "type": "array", "items": { "type": "object" } }, "tool_call_id": { "type": "string" } } } }, "stream": { "type": "boolean" }, "stream_options": { "type": "object" }, "max_tokens": { "type": "integer" }, "temperature": { "type": "number" }, "top_p": { "type": "number" }, "stop": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "string" } } ] }, "tools": { "type": "array", "items": { "type": "object" } }, "tool_choice": { "oneOf": [ { "type": "string" }, { "type": "object" } ] }, "parallel_tool_calls": { "type": "boolean" }, "response_format": { "type": "object", "description": "{\"type\":\"json_object\"} or {\"type\":\"json_schema\",\"json_schema\":{...}}" }, "reasoning_effort": { "type": "string", "enum": [ "none", "minimal", "low", "medium", "high" ], "description": "\"none\" switches thinking off on every reasoning model; the gateway maps it to the parameter each model honours." }, "seed": { "type": "integer" }, "user": { "type": "string" } } } } } }, "responses": { "200": { "description": "OK (JSON, or text/event-stream when stream is true)" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "402": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "404": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "429": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "502": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "503": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/responses": { "post": { "tags": [ "chat" ], "summary": "OpenAI Responses API (stateless), used by Codex CLI", "description": "Send the whole conversation in input on every call; previous_response_id, store and background are not supported. Codex CLI extensions are translated: namespace-wrapped MCP and sub-agent tools are expanded and calls come back with namespace restored; agent_message hand-offs become user messages. Streaming emits the standard response.* events.", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "input" ], "properties": { "model": { "type": "string", "description": "Chat model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "openai/gpt-oss-120b", "deepseek-ai/DeepSeek-V4-Flash", "deepseek-ai/DeepSeek-V4.1-Flash", "zai-org/GLM-5.3-Flash", "meta-llama/Llama-3.3-70B-Instruct-Turbo", "zai-org/GLM-5.3", "deepseek-ai/DeepSeek-V4-Pro", "MiniMaxAI/MiniMax-M3", "moonshotai/Kimi-K2.7-Code", "Qwen/Qwen3-VL-235B-A22B-Instruct" ] }, "input": { "oneOf": [ { "type": "string" }, { "type": "array", "items": { "type": "object" } } ] }, "instructions": { "type": "string" }, "tools": { "type": "array", "items": { "type": "object" } }, "tool_choice": [], "stream": { "type": "boolean" }, "max_output_tokens": { "type": "integer" }, "reasoning": { "type": "object", "properties": { "effort": { "type": "string" } } }, "text": { "type": "object" }, "temperature": { "type": "number" }, "top_p": { "type": "number" } } } } } }, "responses": { "200": { "description": "Response object, or text/event-stream" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "402": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "404": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/messages": { "post": { "tags": [ "chat" ], "summary": "Anthropic Messages API, translated to the same chat models", "description": "Accepts the Anthropic request shape (x-api-key or Bearer auth) and returns Anthropic-shaped responses and errors, so Anthropic SDKs and Claude Code can use these models.", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "messages", "max_tokens" ], "properties": { "model": { "type": "string", "description": "Chat model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "openai/gpt-oss-120b", "deepseek-ai/DeepSeek-V4-Flash", "deepseek-ai/DeepSeek-V4.1-Flash", "zai-org/GLM-5.3-Flash", "meta-llama/Llama-3.3-70B-Instruct-Turbo", "zai-org/GLM-5.3", "deepseek-ai/DeepSeek-V4-Pro", "MiniMaxAI/MiniMax-M3", "moonshotai/Kimi-K2.7-Code", "Qwen/Qwen3-VL-235B-A22B-Instruct" ] }, "messages": { "type": "array", "items": { "type": "object" } }, "system": [], "max_tokens": { "type": "integer" }, "stream": { "type": "boolean" }, "tools": { "type": "array", "items": { "type": "object" } }, "temperature": { "type": "number" } } } } } }, "responses": { "200": { "description": "Anthropic message object, or text/event-stream" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/embeddings": { "post": { "tags": [ "embeddings" ], "summary": "Text embeddings (OpenAI format)", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "input" ], "properties": { "model": { "type": "string", "description": "Embedding model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "BAAI/bge-m3", "Qwen/Qwen3-Embedding-8B" ] }, "input": { "oneOf": [ { "type": "string" }, { "type": "array", "maxItems": 1024, "items": { "type": "string" } } ] }, "encoding_format": { "type": "string", "enum": [ "float", "base64" ] }, "dimensions": { "type": "integer" } } } } } }, "responses": { "200": { "description": "OK" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "413": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/rerank": { "post": { "tags": [ "embeddings" ], "summary": "Rerank documents for a query (Cohere-style response)", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "query", "documents" ], "properties": { "model": { "type": "string", "description": "Rerank model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "Qwen/Qwen3-Reranker-8B" ] }, "query": { "type": "string" }, "documents": { "type": "array", "maxItems": 1000, "items": { "oneOf": [ { "type": "string" }, { "type": "object" } ] } }, "top_n": { "type": "integer" }, "return_documents": { "type": "boolean" } } } } } }, "responses": { "200": { "description": "OK: {results: [{index, relevance_score, document?}]}" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/audio/speech": { "post": { "tags": [ "audio" ], "summary": "Text to speech (OpenAI format); OpenAI voice names are mapped", "requestBody": { "required": true, "content": { "application/json": { "schema": { "type": "object", "required": [ "model", "input", "voice" ], "properties": { "model": { "type": "string", "description": "Speech model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "hexgrad/Kokoro-82M", "canopylabs/orpheus-3b-0.1-ft" ] }, "input": { "type": "string", "maxLength": 20000 }, "voice": { "type": "string" }, "response_format": { "type": "string", "enum": [ "mp3", "wav", "opus", "flac", "pcm" ] }, "speed": { "type": "number" } } } } } }, "responses": { "200": { "description": "Audio bytes" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "413": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } }, "/audio/transcriptions": { "post": { "tags": [ "audio" ], "summary": "Speech to text (OpenAI multipart format), with srt/vtt/verbose_json", "requestBody": { "required": true, "content": { "multipart/form-data": { "schema": { "type": "object", "required": [ "model", "file" ], "properties": { "model": { "type": "string", "description": "Transcription model. Canonical ids listed; aliases from GET /v1/models are accepted too.", "enum": [ "openai/whisper-large-v3", "nvidia/parakeet-tdt-0.6b-v3", "mistralai/Voxtral-Small-24B-2507", "mistralai/Voxtral-Mini-3B-2507" ] }, "file": { "type": "string", "format": "binary", "description": "Up to 100 MB" }, "language": { "type": "string", "description": "ISO 639-1; omit for auto-detect" }, "response_format": { "type": "string", "enum": [ "json", "text", "srt", "vtt", "verbose_json" ] }, "timestamp_granularities[]": { "type": "string", "enum": [ "word", "segment" ] }, "prompt": { "type": "string" } } } } } }, "responses": { "200": { "description": "Transcript" }, "400": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "401": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } }, "413": { "description": "Error", "content": { "application/json": { "schema": { "$ref": "#/components/schemas/Error" } } } } } } } }, "components": { "securitySchemes": { "bearer": { "type": "http", "scheme": "bearer", "description": "API key from https://inferenceapis.com/api-keys or POST /v1/signup" } }, "schemas": { "Error": { "type": "object", "properties": { "error": { "type": "object", "properties": { "message": { "type": "string" }, "type": { "type": "string" }, "param": { "type": [ "string", "null" ] }, "code": { "type": [ "string", "null" ], "description": "See https://inferenceapis.com/docs/errors" }, "docs_url": { "type": "string" } } } } }, "Model": { "type": "object", "properties": { "id": { "type": "string" }, "object": { "type": "string" }, "type": { "type": "string", "enum": [ "chat", "vision", "embedding", "rerank", "tts", "stt" ] }, "canonical": { "type": "string" }, "pricing": { "type": "object", "description": "On canonical rows: input/output(/cached_input) or price, plus unit" }, "context_length": { "type": "integer" }, "dimensions": { "type": "integer" }, "capabilities": { "type": "object" }, "aliases": { "type": "array", "items": { "type": "string" } }, "docs": { "type": "string" } } } } } }