{"openapi":"3.0.0","info":{"description":"Inference.net — OpenAI-compatible LLM inference gateway with chat completions, text completions, Anthropic-compatible messages, embeddings, Batch API, and Group API for async processing.","version":[{"name":"v1","value":"v1"}]},"servers":[{"description":"Inference.net — OpenAI-compatible LLM inference gateway with chat completions, text completions, Anthropic-compatible messages, embeddings, Batch API, and Group API for async processing.","url":"https://api.apirails.com/inferencenet"}],"paths":{"/chat/completions":{"post":{"tags":["Chat Completions"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/api-quickstart","api_endpoint":"https://api.inference.net/v1/chat/completions"},"summary":"Create chat completion","description":"Create chat completion","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"model":{"type":"string","description":"Model ID","required":true},"messages":{"type":"array","description":"Array of message objects","items":{"type":"object","properties":{"role":{"type":"string","description":"Role (system/user/assistant/tool)","required":true,"enum":["system","user","assistant","tool"]},"content":{"type":"string","description":"Message content","required":true}}}},"max_tokens":{"type":"integer","description":"Maximum tokens to generate"},"temperature":{"type":"number","description":"Sampling temperature"},"top_p":{"type":"number","description":"Nucleus sampling probability"},"n":{"type":"integer","description":"Number of completions to generate"},"stream":{"type":"boolean","description":"Stream responses","enum":[true,false]},"stop":{"type":"array","description":"Stop sequences","items":{"type":"string"}},"tools":{"type":"array","description":"Tool definitions for function calling","items":{"type":"object","properties":{}}},"response_format":{"type":"object","description":"Response format (e.g. JSON schema)","properties":{}},"reasoning_effort":{"type":"string","description":"Control reasoning effort","enum":["low","medium","high"]}}},"example":{"model":"glm-5.2","messages":[],"max_tokens":"1024","temperature":"0.7","top_p":"0.9","n":"1","stream":"false","stop":"stop1","tools":[],"response_format":"{\"type\": \"json_object\"}","reasoning_effort":"medium"}}}}}},"/completions":{"post":{"tags":["Text Completions"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/api-quickstart","api_endpoint":"https://api.inference.net/v1/completions"},"summary":"Create text completion","description":"Create text completion","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"model":{"type":"string","description":"Model ID","required":true},"prompt":{"type":"string","description":"The prompt to complete","required":true},"max_tokens":{"type":"integer","description":"Maximum tokens to generate"},"temperature":{"type":"number","description":"Sampling temperature"},"top_p":{"type":"number","description":"Nucleus sampling probability"},"n":{"type":"integer","description":"Number of completions"},"stream":{"type":"boolean","description":"Stream responses","enum":[true,false]},"stop":{"type":"array","description":"Stop sequences","items":{"type":"string"}}}},"example":{"model":"glm-5.2","prompt":"Say hello","max_tokens":"1024","temperature":"","top_p":"","n":"","stream":"","stop":[]}}}}}},"/messages":{"post":{"tags":["Anthropic Messages"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/anthropic-sdk","api_endpoint":"https://api.inference.net/v1/messages"},"summary":"Create Anthropic-compatible message","description":"Create Anthropic-compatible message","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"model":{"type":"string","description":"Model ID","required":true},"max_tokens":{"type":"integer","description":"Maximum tokens to generate","required":true},"messages":{"type":"array","description":"Array of message objects","items":{"type":"object","properties":{"role":{"type":"string","description":"Role (user/assistant)","required":true,"enum":["user","assistant"]},"content":{"type":"string","description":"Message content","required":true}}}},"system":{"type":"string","description":"System prompt"},"temperature":{"type":"number","description":"Sampling temperature"},"top_p":{"type":"number","description":"Nucleus sampling probability"},"stream":{"type":"boolean","description":"Stream responses","enum":[true,false]},"stop_sequences":{"type":"array","description":"Stop sequences","items":{"type":"string"}},"tools":{"type":"array","description":"Tool definitions","items":{"type":"object","properties":{}}}}},"example":{"model":"glm-5.2","max_tokens":"1024","messages":[],"system":"You are a helpful assistant.","temperature":"","top_p":"","stream":"","stop_sequences":[],"tools":[]}}}}}},"/embeddings":{"post":{"tags":["Embeddings"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/api-quickstart","api_endpoint":"https://api.inference.net/v1/embeddings"},"summary":"Create embeddings","description":"Create embeddings","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"model":{"type":"string","description":"Embedding model ID","required":true},"input":{"type":"string","description":"Input text or array of texts to embed","required":true},"encoding_format":{"type":"string","description":"Embedding format (float or base64)","enum":["float","base64"]}}},"example":{"model":"text-embedding-3-small","input":"The quick brown fox","encoding_format":""}}}}}},"/models":{"get":{"tags":["Models"],"parameters":[{"name":"wildcard","in":"query","description":"Filter models by name","required":false,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/api-quickstart","api_endpoint":"https://api.inference.net/v1/models"},"summary":"List available models","description":"List available models","security":[{"bearerAuth":[]}]}},"/batch/files":{"post":{"tags":["Batch - Files"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/files"},"summary":"Upload batch input file","description":"Upload batch input file","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"purpose":{"type":"string","description":"Must be 'batch'","required":true,"enum":["batch"]},"file":{"type":"string","format":"binary","description":"JSONL file to upload","required":true}}},"example":{"purpose":"batch","file":"(binary)"}}}}}},"/batch/files/{file_id}":{"get":{"tags":["Batch - Files"],"parameters":[{"name":"file_id","in":"path","description":"File ID","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/files/{file_id}"},"summary":"Retrieve batch file info","description":"Retrieve batch file info","security":[{"bearerAuth":[]}]},"delete":{"tags":["Batch - Files"],"parameters":[{"name":"file_id","in":"path","description":"File ID","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/files/{file_id}"},"summary":"Delete batch file","description":"Delete batch file","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{}},"example":{}}}}}},"/batch/files/{file_id}/content":{"get":{"tags":["Batch - Files"],"parameters":[{"name":"file_id","in":"path","description":"File ID","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/files/{file_id}/content"},"summary":"Retrieve batch file content","description":"Retrieve batch file content","security":[{"bearerAuth":[]}]}},"/batch/batches":{"post":{"tags":["Batch - Batches"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/batches"},"summary":"Create batch job","description":"Create batch job","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"input_file_id":{"type":"string","description":"ID of the uploaded input file","required":true},"endpoint":{"type":"string","description":"Endpoint to use (/v1/chat/completions or /v1/completions)","required":true,"enum":["/v1/chat/completions","/v1/completions"]},"completion_window":{"type":"string","description":"Completion window","required":true,"enum":["24h"]},"webhook_url":{"type":"string","description":"HTTPS webhook URL for completion notifications"},"metadata":{"type":"object","description":"Custom metadata for the batch","properties":{}}}},"example":{"input_file_id":"file-abc123","endpoint":"/v1/chat/completions","completion_window":"24h","webhook_url":"https://example.com/webhook","metadata":"{\"description\": \"nightly eval\"}"}}}}},"get":{"tags":["Batch - Batches"],"parameters":[{"name":"limit","in":"query","description":"Number of batches to return","required":false,"schema":{"type":"integer","example":""}},{"name":"after","in":"query","description":"Pagination cursor","required":false,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/batches"},"summary":"List batches","description":"List batches","security":[{"bearerAuth":[]}]}},"/batch/batches/{batch_id}":{"get":{"tags":["Batch - Batches"],"parameters":[{"name":"batch_id","in":"path","description":"Batch ID","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/batches/{batch_id}"},"summary":"Retrieve batch","description":"Retrieve batch","security":[{"bearerAuth":[]}]}},"/batch/batches/{batch_id}/cancel":{"post":{"tags":["Batch - Batches"],"parameters":[{"name":"batch_id","in":"path","description":"Batch ID","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/batch-api","api_endpoint":"https://batch.inference.net/v1/batches/{batch_id}/cancel"},"summary":"Cancel batch","description":"Cancel batch","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{}},"example":{}}}}}},"/slow/group/chat/completions":{"post":{"tags":["Group API"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/group","api_endpoint":"https://api.inference.net/v1/slow/group/chat/completions"},"summary":"Submit group of chat completions","description":"Submit group of chat completions","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"requests":{"type":"array","description":"Array of chat completion request objects","required":true,"items":{"type":"object","properties":{"model":{"type":"string","description":"Model ID","required":true},"messages":{"type":"array","description":"Messages array"},"max_tokens":{"type":"integer","description":"Max tokens"}}}},"webhook_id":{"type":"string","description":"Webhook ID for notifications"}}},"example":{"requests":[],"webhook_id":"my-webhook-123"}}}}}},"/slow/group/completions":{"post":{"tags":["Group API"],"parameters":[],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/group","api_endpoint":"https://api.inference.net/v1/slow/group/completions"},"summary":"Submit group of text completions","description":"Submit group of text completions","security":[{"bearerAuth":[]}],"requestBody":{"description":"","required":true,"content":{"application/json":{"schema":{"type":"object","required":[],"properties":{"requests":{"type":"array","description":"Array of completion request objects","required":true,"items":{"type":"object","properties":{"model":{"type":"string","description":"Model ID","required":true},"prompt":{"type":"string","description":"Prompt text","required":true},"max_tokens":{"type":"integer","description":"Max tokens"}}}},"webhook_id":{"type":"string","description":"Webhook ID for notifications"}}},"example":{"requests":[],"webhook_id":""}}}}}},"/slow/group/{group_id}/generations":{"get":{"tags":["Group API"],"parameters":[{"name":"group_id","in":"path","description":"Group ID","required":true,"schema":{"type":"string","example":""}}],"responses":{"401":{"description":"Bearer token required (Authorization header)","content":{"application/json":{}}}},"externalDocs":{"api_ref":"https://docs.inference.net/api/async-inference/group","api_endpoint":"https://api.inference.net/v1/slow/group/{group_id}/generations"},"summary":"Retrieve group generation results","description":"Retrieve group generation results","security":[{"bearerAuth":[]}]}}},"components":{"securitySchemes":{"bearerAuth":{"type":"http","scheme":"bearer"}}},"security":[{"bearerAuth":[]}]}