DeepInfra website screenshot

DeepInfra

DeepInfra is a serverless inference platform for open-source models. Hosts 100+ LLMs (Llama, Qwen, DeepSeek, Mixtral) plus image (Flux, Stable Diffusion), video, audio (Whisper, TTS, Voxtral), embeddings/reranking, and vision/OCR models. Includes fine-tuning, dedicated GPU rentals, and private deployments. OpenAI- and Anthropic- compatible endpoints.

1 APIs 0 Features
AILLMInferenceServerlessOpen SourceOpenAI CompatibleAnthropic CompatibleImage GenerationAudioEmbeddings

APIs

DeepInfra Platform API

OpenAI- and Anthropic-compatible inference API for 100+ open-source models. Surfaces include chat completions, anthropic messages, embeddings, reranking, audio (speech/transcrip...

Collections

Pricing Plans

Deepinfra Plans Pricing

1 plans

PLANS

Rate Limits

Deepinfra Rate Limits

1 limits

RATE LIMITS

FinOps

Resources

👥
GitHubOrganization
GitHubOrganization
🔗
LinkedIn
LinkedIn
🔗
Website
Website
🔗
Documentation
Documentation
🔗
Plans
Plans
🔗
RateLimits
RateLimits
🔗
FinOps
FinOps
🔗
LlmsText
LlmsText

Sources

Raw ↑
opencollection: 1.0.0
info:
  name: DeepInfra Inference API
  version: 1.0.0
request:
  auth:
    type: bearer
    token: '{{bearerToken}}'
items:
- info:
    name: Chat
    type: folder
  items:
  - info:
      name: Create a chat completion (OpenAI-compatible)
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/chat/completions
      body:
        type: json
        data: '{}'
    docs: Create a chat completion (OpenAI-compatible)
- info:
    name: Completions
    type: folder
  items:
  - info:
      name: Create a text completion (legacy, OpenAI-compatible)
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/completions
      body:
        type: json
        data: '{}'
    docs: Create a text completion (legacy, OpenAI-compatible)
- info:
    name: Embeddings
    type: folder
  items:
  - info:
      name: Create embeddings for input text
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/embeddings
      body:
        type: json
        data: '{}'
    docs: Create embeddings for input text
- info:
    name: Audio
    type: folder
  items:
  - info:
      name: Transcribe audio to text (Whisper)
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/audio/transcriptions
      body:
        type: multipart-form
        data:
        - name: file
          type: text
          value: ''
        - name: model
          type: text
          value: ''
        - name: language
          type: text
          value: ''
        - name: prompt
          type: text
          value: ''
        - name: response_format
          type: text
          value: ''
        - name: temperature
          type: text
          value: ''
    docs: Transcribe audio to text (Whisper)
  - info:
      name: Translate audio into English text
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/audio/translations
      body:
        type: multipart-form
        data:
        - name: file
          type: text
          value: ''
        - name: model
          type: text
          value: ''
        - name: prompt
          type: text
          value: ''
        - name: response_format
          type: text
          value: ''
        - name: temperature
          type: text
          value: ''
    docs: Translate audio into English text
  - info:
      name: Synthesize text to speech
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/audio/speech
      body:
        type: json
        data: '{}'
    docs: Synthesize text to speech
- info:
    name: Images
    type: folder
  items:
  - info:
      name: Generate images from a prompt
      type: http
    http:
      method: POST
      url: https://api.deepinfra.com/v1/openai/images/generations
      body:
        type: json
        data: '{}'
    docs: Generate images from a prompt
- info:
    name: Models
    type: folder
  items:
  - info:
      name: List available models
      type: http
    http:
      method: GET
      url: https://api.deepinfra.com/v1/openai/models
    docs: List available models
  - info:
      name: Get metadata for a model
      type: http
    http:
      method: GET
      url: https://api.deepinfra.com/v1/openai/models/:model
      params:
      - name: model
        value: ''
        type: path
    docs: Get metadata for a model
bundled: true