# APIMart

## Docs

- [Query Token Balance](https://docs.apimart.ai/en/api-reference/account/token-balance.md): - Query remaining and used credits of the current API Key - Monitor single token usage - CORS support for cross-origin requests - Real-time balance monitoring
- [Query User Balance](https://docs.apimart.ai/en/api-reference/account/user-balance.md): - Query overall remaining and used credits of user account - Get user-level balance information - CORS support for cross-origin requests - Real-time balance monitoring
- [TTS Text-to-Speech](https://docs.apimart.ai/en/api-reference/audios/tts.md): - Support multiple voice models and voice selections - Output high-quality audio formats: wav, opus, aac, flac, pcm - Maximum input text of 4096 characters
- [Whisper-1 Audio Transcription](https://docs.apimart.ai/en/api-reference/audios/whisper-1.md): - Supports speech recognition in 99 languages - Multiple output formats: json, text, srt, vtt, etc. - Maximum file size 25 MB
- [Gemini-2.5-Flash-Image-preview (Nano banana) Image Generation](https://docs.apimart.ai/en/api-reference/images/gemini-2.5-flash/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Fast generation speed, optimized for quick image creation - Generated image links are valid for 24 hours, please save them promptly
- [Gemini-3-Pro-Image-preview (Nano banana Pro) Image Generation](https://docs.apimart.ai/en/api-reference/images/gemini-3-pro/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - High-quality image generation, professional-grade image creation - Generated image links are valid for 24 hours, please save them promptly
- [Gemini-3.1-Flash-Image-preview (Nano banana2) Image Generation](https://docs.apimart.ai/en/api-reference/images/gemini-3.1-flash/generation.md): - Supports text-to-image and image-to-image, up to 4K resolution output - Up to 14 reference images for style/character consistency - Supports extreme aspect ratios (1:4, 4:1, 1:8, 8:1) - Integrated Google Search enhancement for more realistic image generation
- [GPT-Image(1/1.5) Image Generation](https://docs.apimart.ai/en/api-reference/images/gpt-image-1/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports text-to-image, image-to-image, and inpainting generation modes - Supports transparent backgrounds, multiple output formats, and quality tiers - Generate up to 4 images per request, with up to 15 reference images
- [GPT-Image-2 Image Generation](https://docs.apimart.ai/en/api-reference/images/gpt-image-2/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - OpenAI Images compatible protocol, supports text-to-image / image-to-image - 13 image aspect ratios supported via the `size` field, platform auto-appends to prompt - 1 image per request, up to 16 reference images, URL and base6…
- [GPT-Image-2 Official Channel Image Generation](https://docs.apimart.ai/en/api-reference/images/gpt-image-2/official.md): - OpenAI official `gpt-image-2` model, based on `/v1/images/generations` compatible protocol - Asynchronous processing, returns `task_id` for subsequent queries - Text-to-image / image-to-image / inpainting (mask) — all-in-one - New `resolution` tier field — 1K / 2K / 4K selection - 13 aspect ratios…
- [Grok Imagine 1.0 Image Editing](https://docs.apimart.ai/en/api-reference/images/grok-imagine/edit.md): - Async processing mode, returns task ID for subsequent queries - High-quality image editing based on reference images, supports multilingual prompts - Generated image links are valid for 24 hours, please save them promptly
- [Grok Imagine 1.0 Image Generation](https://docs.apimart.ai/en/api-reference/images/grok-imagine/generation.md): - Async processing mode, returns task ID for subsequent queries - High-quality AI image generation, supports multilingual prompts - Generated image links are valid for 24 hours, please save them promptly
- [Imagen 4.0 Apimart Image Generation](https://docs.apimart.ai/en/api-reference/images/imagen-4.0-apimart/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Based on Google Imagen 4 model, high-quality image generation - Only supports text-to-image, does not support image-to-image / reference images - Supported ratios: 16:9 (landscape), 9:16 (portrait) - Generated image links are v…
- [Qwen Image 2.0 Image Generation](https://docs.apimart.ai/en/api-reference/images/qwen-image/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports text-to-image, image-to-image and other generation modes - Supports 1K/2K resolution tiers, generate up to 6 images
- [Seedream-4.5 Image Generation](https://docs.apimart.ai/en/api-reference/images/seedream-4.5/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports multiple generation modes including text-to-image, image-to-image, and image editing - Generated image links are valid for 24 hours, please save them promptly
- [Seedream-4.0 Image Generation](https://docs.apimart.ai/en/api-reference/images/seedream-4/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports multiple generation modes including text-to-image, image-to-image, and image editing - Generated image links are valid for 24 hours, please save them promptly
- [Seedream-5.0-Lite Image Generation](https://docs.apimart.ai/en/api-reference/images/seedream-5-lite/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports multiple generation modes including text-to-image, image-to-image, and sequential image generation - Supports 2K / 3K resolution with PNG / JPEG output formats - Generated image links are valid for 72 hours, please sav…
- [wan2.7 Image Generation & Editing](https://docs.apimart.ai/en/api-reference/images/wan2.7-image/generation.md): - Wan2.7 image series: supports text-to-image, image editing, interactive editing, sequential generation, and multi-image reference - Asynchronous processing mode — submit a task and poll for results using the returned task_id - Supports 1K / 2K / 4K resolution; wan2.7-image-pro supports up to 4K fo…
- [Z-Image-Turbo Image Generation](https://docs.apimart.ai/en/api-reference/images/z-image-turbo/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Lightweight and fast image generation, supports Chinese and English - Supports 1K/2K resolution tiers, supports smart prompt rewriting
- [Get Task Status](https://docs.apimart.ai/en/api-reference/tasks/status.md): - Query the execution status and result of an asynchronous task - Real-time status updates and progress tracking - Retrieve generation results when tasks are completed - Multi-language support (zh/en/ko/ja)
- [Gemini Native Format](https://docs.apimart.ai/en/api-reference/texts/gemini/quickstart.md): - Call Gemini models using Google Native API format - Synchronous processing mode with real-time response - Minimal parameters for quick start
- [General Chat API (Default Streaming)](https://docs.apimart.ai/en/api-reference/texts/general/chat-completions.md): - Unified chat API interface supporting all text generation models - Select different AI models via the model parameter - Compatible with OpenAI Chat Completions API format
- [General Chat API (Default Non-Streaming)](https://docs.apimart.ai/en/api-reference/texts/general/chat-completions-nostream.md): - Unified chat API interface supporting all text generation models - Select different AI models via the model parameter - Compatible with OpenAI Chat Completions API format - Non-streaming output, returns complete response at once
- [Claude Messages API](https://docs.apimart.ai/en/api-reference/texts/general/claude-messages.md): - Fully compatible with Claude Messages API format - Supports multi-turn conversations and single queries - Supports multimodal content including text and images
- [OpenAI Multimodal Responses API](https://docs.apimart.ai/en/api-reference/texts/openai/responses.md): - Fully compatible with OpenAI Responses API format - Supports multimodal input with text and images - Supports tool extensions: web search, file search, function calling, remote MCP
- [Upload Image](https://docs.apimart.ai/en/api-reference/uploads/images.md): Upload an image to get a URL for use with image/video generation APIs
- [doubao-seedance-1-5-pro Video Generation](https://docs.apimart.ai/en/api-reference/videos/doubao-seedance-1-5-pro/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame/last frame) - Supports audio generation - Supports landscape, portrait, and square aspect ratios
- [doubao-seedance-2.0 Video Generation](https://docs.apimart.ai/en/api-reference/videos/doubao-seedance-2-0/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame/last frame) - Supports reference video, reference audio, audio-enabled video - Supports landscape, portrait, square, ultra-wide, and adaptive aspect ratios
- [doubao-seedance-1-0-pro Video Generation](https://docs.apimart.ai/en/api-reference/videos/doubao/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame/last frame/reference) - Supports landscape, portrait, and square aspect ratios
- [Grok Imagine 1.0 Video Generation](https://docs.apimart.ai/en/api-reference/videos/grok-imagine/generation.md): - Async processing mode, returns task ID for subsequent queries - High-quality AI video generation, supports text-to-video and image-to-video - Flexible aspect ratio and quality options for different creative needs
- [HappyHorse 1.0 Video Generation](https://docs.apimart.ai/en/api-reference/videos/happyhorse-1.0/generation.md): - Alibaba Cloud Bailian HappyHorse 1.0 video generation model (unified entry, single-model auto-routing) - Auto-routes by parameters: T2V (prompt only) / I2V (first_frame_image) / R2V (image_urls) / EDIT (video_url) - Supports 720P/1080P resolutions and any integer duration from 3 to 15 seconds - Bi…
- [Kling 2.6 Video Generation](https://docs.apimart.ai/en/api-reference/videos/kling-v2-6/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame/first-last frame control) - Supports standard mode (720P) and professional mode (1080P) - Professional mode supports automatic audio generation and voice selection
- [Kling v3 Omni Video Generation](https://docs.apimart.ai/en/api-reference/videos/kling-v3-omni/generation.md): - Async processing mode, returns task ID for subsequent queries - Unified text-to-video/image-to-video interface with image reference syntax - Supports standard mode (720P) and professional mode (1080P) - Reference images in prompts using image_N syntax - Supports generating videos with audio (mutua…
- [Kling v3 Video Generation](https://docs.apimart.ai/en/api-reference/videos/kling-v3/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame/first-last frame control) - Supports standard mode (720P) and professional mode (1080P) - Text-to-video supports 15-second duration - Supports generating videos with audio
- [Kling Video O1 Video Generation](https://docs.apimart.ai/en/api-reference/videos/kling-video-o1/generation.md): - Reasoning-enhanced model for highest quality video generation - Async processing mode, returns task ID for subsequent queries - Unified text-to-video/image-to-video interface with image reference syntax - Supports standard mode (720P) and professional mode (1080P) - Reference images in prompts usi…
- [MiniMax-Hailuo-2.3 Video Generation](https://docs.apimart.ai/en/api-reference/videos/minimax-hailuo-2.3/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame image) - Supports 6s and 10s duration, 768p/1080p resolution - Supports 15 camera movement commands, prompt auto-optimization, and watermark control
- [MiniMax-Hailuo-02 Video Generation](https://docs.apimart.ai/en/api-reference/videos/minimax-hailuo/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video (first frame/last frame) - Supports 5 and 10 second durations, multiple resolutions available - Supports automatic prompt optimization and watermark control
- [SkyReels V4 Video Generation](https://docs.apimart.ai/en/api-reference/videos/skyreels-v4/generation.md): - Two model tiers: Fast (speed-optimized) and Std (quality-optimized) - Three modes auto-routed by request fields: Text-to-Video (T2V), Image-to-Video (I2V), Multimodal Reference (Omni) - 480p / 720p / 1080p resolution, 3 ~ 15 seconds duration - Advanced features: first/end/key frame, reference imag…
- [Sora2 Preview Video Generation](https://docs.apimart.ai/en/api-reference/videos/sora-2/generation-preview.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video and other generation modes - Generated video links are valid for 72 hours, please save them promptly
- [VEO3 Video Generation](https://docs.apimart.ai/en/api-reference/videos/veo3/generation.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports multiple generation modes including text-to-video and image-to-video - Generated video links are valid for 24 hours, please save them promptly
- [VEO3 Official Video Generation](https://docs.apimart.ai/en/api-reference/videos/veo3/generation-official.md): - Asynchronous processing mode, returns task ID for subsequent queries - Supports text-to-video and image-to-video (first frame / first & last frame control) - Supports 720P and 1080P resolution - Supports 4/6/8 second video duration - Supports audio track generation - Supports person generation pol…
- [VEO3 Video Remix](https://docs.apimart.ai/en/api-reference/videos/veo3/remix.md): - Extend generated videos by continuing from 8 seconds to 15 seconds - Asynchronous processing mode, returns task ID for subsequent queries - Generated video links are valid for 24 hours, please save them promptly
- [Vidu Q3(pro/turbo) Video Generation](https://docs.apimart.ai/en/api-reference/videos/vidu-q3-pro/generation.md): - Async processing mode, returns task ID for subsequent queries - Supports text-to-video, image-to-video, first-last frame video generation - Supports 540p / 720p / 1080p resolution - Duration range 1-16 seconds, audio enabled by default
- [Vidu Q3(mix/standard) Reference-to-Video](https://docs.apimart.ai/en/api-reference/videos/vidu-q3/generation.md): - Async processing mode, returns task ID for subsequent queries - Upload 1-7 reference images + text prompt to generate short videos containing reference subjects - Supports 540p / 720p / 1080p resolution - Duration range 1-16 seconds, suitable for character consistency and style continuation
- [wan2.5-preview Video Generation](https://docs.apimart.ai/en/api-reference/videos/wan2.5/generation.md): - Wanxiang 2.5 preview video generation model - Supports Text-to-Video and Image-to-Video - Supports 480p/720p/1080p resolution, 5 or 10 seconds duration - Supports auto prompt extension, auto audio and custom audio
- [Wan2.6 Video Generation](https://docs.apimart.ai/en/api-reference/videos/wan2.6/generation.md): - Alibaba Cloud Wanxiang video generation model - Supports Text-to-Video and Image-to-Video - Supports 720p/1080p resolution, 5/10/15 seconds duration - Supports automatic prompt extension and audio generation
- [wan2.6-i2v-flash Image-to-Video](https://docs.apimart.ai/en/api-reference/videos/wan2.6/i2v-flash-generation.md): - Wanxiang 2.6 fast image-to-video model - Generates smooth video from first-frame image and text prompts - Supports audio/silent toggle, multi-shot narration, custom audio - Supports 720p/1080p resolution, 2-15 seconds duration - Supports video effect templates
- [Wan2.7-R2V Reference-to-Video](https://docs.apimart.ai/en/api-reference/videos/wan2.7-r2v/generation.md): - Alibaba Cloud Wanxiang 2.7 reference-to-video model - Generate a new video with consistent style, characters, and scenes based on one or more reference images/videos - Supports character consistency, style transfer, and multi-asset combination - Supports reference voice (reference_voice) to contro…
- [Wan2.7-VideoEdit Video Editing](https://docs.apimart.ai/en/api-reference/videos/wan2.7-videoedit/generation.md): - Alibaba Cloud Wanxiang 2.7 video editing model - AI editing based on existing videos: style transfer, content replacement, element addition - Optionally accepts reference images to specify target style or appearance - Supports keeping the original video duration or customizing the output duration
- [Wan2.7 Video Generation](https://docs.apimart.ai/en/api-reference/videos/wan2.7/generation.md): - Alibaba Cloud Wanxiang 2.7 video generation model (unified entry) - Automatically routed based on parameters: Text-to-Video / Image-to-Video (first frame, first-last frame, video continuation) - Supports 720P/1080P resolution, 2-15 seconds duration - Supports custom audio (background music in text…
- [Development Guide](https://docs.apimart.ai/en/development.md): Integrate the API into your application
- [FAQs](https://docs.apimart.ai/en/faqs.md): Frequently Asked Questions about using APIMart
- [Account Management](https://docs.apimart.ai/en/faqs/account-management.md): Account usage and technical support inquiries
- [Connection & Usage](https://docs.apimart.ai/en/faqs/connection-usage.md): Troubleshoot connection and usage issues with APIMart
- [Cost Optimization](https://docs.apimart.ai/en/faqs/cost-optimization.md): Practical tips for optimizing API call costs
- [Features & Capabilities](https://docs.apimart.ai/en/faqs/features.md): APIMart supported features and compatibility information
- [Security & Configuration](https://docs.apimart.ai/en/faqs/security-configuration.md): API key management and security configuration guide
- [APIMart — OpenAI-Compatible API Gateway (GPT-5, Claude, Gemini)](https://docs.apimart.ai/en/index.md): OpenAI-compatible API for GPT-5, Claude, Gemini. Multi-provider routing, transparent pricing, low latency. Enterprise SLA, SDK support, pay-as-you-go.
- [Using APIMart in AnythingLLM](https://docs.apimart.ai/en/integrations/chat/anythingllm.md): Detailed guide on how to configure and use APIMart API service in AnythingLLM. This guide will help you configure APIMart API in AnythingLLM to build private AI knowledge bases and conversation systems.
- [Using APIMart in ChatBox](https://docs.apimart.ai/en/integrations/chat/chatbox.md): Detailed guide on how to configure and use APIMart API service in ChatBox desktop client. This guide will help you configure APIMart API in ChatBox to access rich AI model resources.
- [Using APIMart in Cherry Studio](https://docs.apimart.ai/en/integrations/chat/cherry-studio.md): Detailed guide on how to configure and use APIMart API service in Cherry Studio desktop client. This guide will help you configure APIMart API in Cherry Studio to access rich AI model resources.
- [Using APIMart in Claude Code](https://docs.apimart.ai/en/integrations/dev-tool/claude-code.md): A detailed guide on configuring and using APIMart API services in Claude Code CLI, enabling you to access multiple AI models for assisted programming with simple configuration.
- [Integrate APIMart with Cline in VSCode](https://docs.apimart.ai/en/integrations/dev-tool/cline.md): A detailed guide on how to configure APIMart API service using the Cline extension in Visual Studio Code. This guide will help you use APIMart's AI models through Cline for code development, debugging, and optimization in VSCode.
- [Using APIMart in Cursor](https://docs.apimart.ai/en/integrations/dev-tool/cursor.md): Detailed guide on how to configure and use APIMart API service in Cursor AI code editor. This guide will help you configure APIMart API in Cursor to access rich AI model resources for code development.
- [Using APIMart with Gemini CLI](https://docs.apimart.ai/en/integrations/dev-tool/gemini.md): Comprehensive guide on configuring APIMart API service in Gemini CLI command-line tool. This guide helps you use various AI models through APIMart via command line, including Gemini, GPT, and Claude series.
- [Using APIMart in Dify](https://docs.apimart.ai/en/integrations/platform/dify.md): Detailed guide on how to configure and use APIMart API service in Dify LLMOps platform. This guide will help you configure APIMart API in Dify to build powerful AI applications.
- [Using APIMart in Immersive Translate](https://docs.apimart.ai/en/integrations/platform/immersive-translate.md): Detailed guide on how to configure and use APIMart API service in the Immersive Translate browser extension. This guide will help you set up APIMart API in Immersive Translate for high-quality AI translation services.
- [OpenClaw Manager Deployment Guide](https://docs.apimart.ai/en/integrations/platform/openclaw-manager.md): A visual tool for one-click deployment and management of OpenClaw AI bot gateways, supporting Telegram, Feishu, and Discord platforms, powered by GPT-5, Claude, Gemini and more AI models via APIMart API.
- [OpenClaw Manager — Feishu Channel Setup](https://docs.apimart.ai/en/integrations/platform/openclaw-manager-feishu.md): Step-by-step guide on creating and configuring a Feishu bot in OpenClaw Manager, including enterprise app creation, permission setup, event subscription, and pairing code binding.
- [OpenClaw Manager — Telegram Channel Setup](https://docs.apimart.ai/en/integrations/platform/openclaw-manager-telegram.md): Step-by-step guide on creating and configuring a Telegram bot in OpenClaw Manager, including BotFather bot creation, credential setup, and pairing code binding.
- [Quick Start](https://docs.apimart.ai/en/quickstart.md): Quickly start using our API services

## OpenAPI Specs

- [openapi](https://docs.apimart.ai/api-reference/openapi.json)