docs.emix.ai
language
language
  • 🇺🇸 English
  • 🇨🇳 Chinese
language
language
  • 🇺🇸 English
  • 🇨🇳 Chinese
Market
File Upload API
Market
File Upload API
  1. Gemini
  • Getting Started with Emix API (Important)
  • Market
  • Image Models
    • Topaz
      • Topaz - Image Upscale
    • Seedream
      • Seedream3.0 - Text to Image
      • Seedream4.0 - Text to Image
      • Seedream4.0 - Edit
      • Seedream4.5 - Text to Image
      • Seedream4.5 - Edit
      • Seedream5.0 Lite - Text to Image
      • Seedream5.0 Lite - Image to Image
      • Seedream5.0 Pro - Text to Image
      • Seedream5.0 Pro - Image to Image
      • Seedream 5.0 Pro - Layer Decomposition
    • Z-image
      • Z-Image
    • Google
      • Google - imagen4-fast
      • Google - imagen4-ultra
      • Google - imagen4
      • Google - Nano Banana
      • Google - Nano Banana Pro
      • Google - Nano Banana 2
      • Google - Nano Banana 2 Lite
    • Flux-2
      • Flux-2 - Pro Image to Image
      • Flux-2 - Pro Text to Image
      • Flux-2 - Image to Image
      • Flux-2 - Text to Image
    • Grok Imagine
      • Grok Imagine - Text to Image
      • Grok Imagine - image to image
      • Grok Imagine Image 2.0 Text To Image
      • Grok Imagine Image 2.0 Segment Map
      • Grok Imagine Image 2.0 Image Edit
    • GPT Image
      • GPT Image 2.5 Sunburst Text to Image
      • GPT Image 2.5 Sunburst Image to Image
      • GPT Image 2.5 Flare Text to Image
      • GPT Image 2.5 Flare Image to Image
      • GPT Image-1.5 - Text to Image
      • GPT Image-1.5 - Image to Image
      • GPT Image-2 - Text to Image
      • GPT Image 2 - Image To Image
    • Recraft
      • Recraft - Remove Background
      • Recraft - Crisp Upscale
    • Ideogram
      • Ideogram - V3 Reframe
      • Ideogram - Character Edit
      • Ideogram - Character Remix
      • Ideogram - Character
      • Ideogram V3 Text to Image
      • Ideogram V3 Edit
      • Ideogram V3 Remix
    • 4o Image API
      • 4o Image API Quickstart
      • 4o Image Generation Callbacks
      • Generate 4o Image
      • Get 4o Image Details
      • Get Direct Download URL
    • Flux Kontext API
      • Flux Kontext API Quickstart
      • Image Generation or Editing Callbacks
      • Generate or Edit Image
      • Get Image Details
    • Qwen
      • Qwen - Text to Image
      • Qwen - Image to Image
      • Qwen - Image Edit
      • Qwen2 - Image Edit
      • Qwen2 - Text To Image
      • Qwen3 Pro Text to Image
      • Qwen3 Text to Image
      • Qwen3 Pro Image to Image
      • Qwen3 Image to Image
      • Qwen 2.1 - Text to Image
      • Qwen 2.1 - Image to Image
    • Wan
      • Wan 2.7 Image
      • Wan 2.7 Image Pro
  • Video Models
    • OmniHuman
      • Omnihuman 1.5
      • Omnihuman 1.5 Human Identification
      • OmniHuman 1.5 Subject Detection
    • Hailuo
      • Hailuo 2.3 Pro Image to Video
      • Hailuo 2.3 Standard Image to Video
      • Hailuo Pro Text to Video
      • Hailuo Pro Image to Video
      • Hailuo Standard Text to Video
      • Hailuo Standard Image to Video
    • Topaz
      • Topaz - Video Upscale
    • Runway API
      • Runway Image To Video
      • Runway Text To Video
      • Runway Video Extension
    • HappyHorse
      • HappyHorse - text-to-video
      • HappyHorse - image-to-video
      • HappyHorse - reference-to-video
      • HappyHorse - video-edit
      • HappyHorse-1-1 image-to-video
      • HappyHorse-1-1 text-to-video
      • HappyHorse-1-1 reference-to-video
    • Wan
      • Wan - 2.2 A14B Image to Video Turbo
      • Wan - 2.2 A14B Speech to Video Turbo
      • Wan - 2.2 A14B Text to Video Turbo
      • Wan - Animate Move
      • Wan - Animate Replace
      • Wan 2.6 - Image to Video
      • Wan 2.6 - Text to Video
      • Wan 2.6 - Video to Video
      • Wan 2.5 - Image to Video
      • Wan 2.5 - Text to Video
      • Wan 2.7 - Text to Video
      • Wan 2.7 - Image to Video
      • Wan 2.7 - Video Edit
      • Wan 2.7 - Reference to Video
      • Wan 3.0 - Video
      • Wan 3.0 - Video Prime
    • Grok Imagine
      • Grok Imagine Text to Video
      • Grok Imagine Image to Video
      • Grok Imagine - Video Upscale
      • Grok Imagine - Video Extend
      • Grok Imagine Video 1.5 Preview
    • Kling
      • Kling 2.6 Text to Video
      • Kling 2.6 Image to Video
      • Kling - V2.5 Turbo Image to Video Pro
      • Kling - V2.5 Turbo Text to Video Pro
      • Kling AI Avatar Standard
      • Kling AI Avatar Pro
      • Kling V2.1 Master Image to Video
      • Kling V2.1 Master Text to Video
      • Kling V2.1 Pro
      • Kling V2.1 Standard
      • Kling 2.6 motion-control
      • Kling-3.0 motion-control
      • Kling 3.0
      • Kling - V3 Turbo Text to Video
      • Kling - V3 Turbo Image to Video
      • Kling 3.0 Omni Reference To Video
      • Kling 3.0 Omni Transformation
      • Kling 3.0 Omni Image To Video
      • Kling 3.0 Omni Text to Video
    • Bytedance
      • Bytedance Seedance 2.0
      • Bytedance Seedance 2.0 Fast
      • Bytedance Seedance 2.0 Mini
      • Bytedance Seedance 1.5 Pro
      • Bytedance V1 Pro Fast Image to Video
      • Bytedance V1 Pro Image to Video
      • Bytedance - V1 Pro Text to Video
      • Bytedance - V1 Lite Image to Video
      • Bytedance - V1 Lite Text to Video
      • Bytedance Seedance 2.5
    • Veo3.1 API
      • Get 4K Video Callbacks
      • Veo3.1 API Quickstart
      • Veo3.1 Video Generation Callbacks
      • Generate Veo3.1 Video
      • Get Veo3.1 Video Details
      • Get 1080P Video
      • Get 4K Video
      • VEO 3.1 Extend Video
      • VEO 3.1 Text to video
      • VEO 3.1 Image to video
      • VEO 3.1 Reference to vidoe
    • Gemini Omni
      • Gemini Omni 1.1 Flash
      • Gemini Omni Video
      • Gemini Omni Audio
      • Gemini Omni Character
    • Volcengine
      • Volcengine video to video lip sync
    • PixVerse
      • PixVerse V6 Text-to-Video
      • PixVerse V6 Image-to-Video
      • PixVerse V6 First & Last Frame Transition
      • PixVerse V6 Video Extension
      • PixVerse V6 Fusion / Reference-to-Video
    • MiniMax H3
      • MiniMax H3 Text-to-Video
      • MiniMax H3 Image-to-Video
      • MiniMax H3 Reference-to-Video
  • Music Models
    • ElevenLabs
      • elevenlabs/audio-isolation
      • elevenlabs/sound-effect-v2
      • elevenlabs/speech-to-text
      • elevenlabs/text-to-dialogue-v3
      • elevenlabs/text-to-speech-multilingual-v2
      • elevenlabs/text-to-speech-turbo-2-5
    • Suno API
      • Music Generation
        • Music Generation Callbacks
        • Music Extension Callbacks
        • Add Instrumental Callbacks
        • Add Vocals Callbacks
        • Music Cover Generation Callbacks
        • Replace Music Section Callbacks
        • Audio Upload and Extension Callbacks
        • Audio Upload and Cover Callbacks
        • Generate Music
        • Extend Music
        • Upload And Cover Audio
        • Upload And Extend Audio
        • Add Instrumental to Music
        • Add Vocals to Music
        • Get Timestamped Lyrics
        • Boost Music Style
        • Generate Music Cover
        • Replace Music Section
        • Generate Persona
        • Generate Mashup Music
      • Lyrics Generation
        • Lyrics Generation Callbacks
        • Generate Lyrics
      • WAV Conversion
        • Convert to WAV Format
      • Vocal Removal
        • Audio Separation Callbacks
        • Vocal & Instrument Stem Separation
        • Generate MIDI from Audio
      • Music Video Generation
        • Music Video Generation Callbacks
        • Create Music Video
      • Sounds Generation
        • Generate sounds
      • voice
        • Suno Voice Generation Callback
        • Suno Voice Validation Phrase Callback
        • Suno Voice Generate Verification Phrase API
        • Suno Voice Create Custom Voice API
        • Suno Voice Regenerate Verification Phrase
        • Suno Voice Check Availability API
    • Gemini
      • Gemini 3.1 Flash Text to speech
      • Gemini 2.5 Pro Text to Speech
  • Chat Models
    • Grok
      • Grok 4.5
      • Grok 4.3
      • Grok 4.6
    • Codex
      • GPT Codex
    • GPT
      • GPT 5.2
      • GPT 5.4 (response)
      • GPT 5.6 Luna
      • GPT 5.6 Terra
      • GPT 5.6 Sol
      • GPT 5.5 (response)
    • Claude
      • Claude Code + emix.ai Integration Guide
      • Claude Sonnet 5
      • Claude Sonnet 4.5
      • Claude Opus 4.7
      • Claude Opus 4.8
      • Claude Opus 5
      • Claude Fable 5
      • Claude Haiku 4.5
      • Claude Opus 4.5
      • Claude Opus 4.6
      • Claude Sonnet 4.5
      • Claude Sonnet 4.6
    • Gemini
      • Gemini 3.6 Flash
        POST
      • Gemini 3.6 Flash (openai)
        POST
      • Gemini 3.7 Flash (openai)
        POST
      • Gemini 2.5 Pro (openai)
        POST
      • Gemini 3 Pro (openai)
        POST
      • Gemini 3.1 Pro (openai)
        POST
      • Gemini 2.5 Flash (openai)
        POST
      • Gemini 3 Flash (openai)
        POST
      • Gemini 3.5 Flash
        POST
      • Gemini 3.5 Flash (openai)
        POST
      • Gemini 3 Flash
        POST
      • Gemini 3.7 Flash
        POST
      • Gemini 3.8 Flash
        POST
      • Gemini 3.8 Flash (openai)
        POST
  • Get Task Details
    GET
  1. Gemini

Gemini 3.8 Flash (openai)

POST
/gemini-3-8-flash-openai/v1/chat/completions

Streaming Support#

When stream: true is set in the request, the API returns responses as server-sent events (SSE) with Content-Type: text/event-stream. This allows for progressive response delivery, where message deltas are sent incrementally as they are generated. Each event contains partial message content, enabling real-time display of responses in your application.
Streaming Response Format:
Content-Type: text/event-stream
Each event line starts with data: followed by JSON
Events contain incremental message deltas
Final event indicates completion with finish_reason
Multimodal
Supports text and image inputs
Real-time Search
Google Search grounding enabled
Streaming
Server-sent events support
Flexible Roles
Multiple message roles supported
⚠️Important: Unified Media Structure
To simplify integration, all media types (Images, Videos, Audio, or Documents) in the messages array share the exact same JSON structure:
  • The type field is fixed as "image_url"
  • The image_url key name remains unchanged for all file types
  • Only the url value points to your specific media file
// Example for Video/Audio/PDF/Image:

{ "type": "image_url", "image_url": { "url": "https://..." } }

Tools Parameter#

The tools parameter is an optional array that allows you to define functions the model can call. The array can contain multiple objects. When using function calling, you can define multiple functions in the array.
Function Calling

Request

Authorization
or
Body Params application/jsonRequired

Examples

Responses

🟢200
application/json
Request successful.
Bodyapplication/json

🟠400
🟠401
🟠429
Request Request Example
Shell
JavaScript
Java
Swift
curl --location 'https://api.emix.ai/gemini-3-8-flash-openai/v1/chat/completions' \
--header 'Content-Type: application/json' \
--data '{
    "messages": [
        {
            "role": "user",
            "content": [
                {
                    "type": "text",
                    "text": "What is in this image?"
                },
                {
                    "type": "image_url",
                    "image_url": {
                        "url": "https://file.aiquickdraw.com/custom-page/akr/section-images/1759055072437dqlsclj2.png"
                    }
                }
            ]
        }
    ],
    "tools": [
        {
            "type": "function",
            "function": {
                "name": "googleSearch"
            }
        }
    ],
    "stream": true,
    "include_thoughts": true,
    "reasoning_effort": "high"
}'
Response Response Example
200 - 成功示例
{
    "candidates": [
        {
            "content": {
                "role": "model",
                "parts": [
                    {
                        "functionCall": {
                            "args": {
                                "location": "Beijing"
                            },
                            "name": "get_weather_forecast",
                            "id": "gp737npz"
                        },
                        "thoughtSignature": "Es8CCswCAb4example"
                    }
                ]
            },
            "finishReason": "STOP"
        }
    ],
    "modelVersion": "gemini-3-8-flash",
    "usageMetadata": {
        "candidatesTokenCount": 18,
        "thoughtsTokenCount": 55,
        "totalTokenCount": 325,
        "promptTokenCount": 252
    },
    "credits_consumed": 0.01,
    "responseId": "xRS0aZC5BNHVz7IPuaO42Qk"
}
Previous
Gemini 3.8 Flash
Next
Get Task Details
Built with