LinkModel API Documentation

Use this page for model selection. Use the API Reference for exact schema, enum values, defaults, and live requests. You can also fetch the current visible catalog from GET https://api.linkmodel.ai/v1/models; this endpoint does not require a Bearer API key. See the List models API reference.

Image models

OpenAI

Model	Best for	Endpoint
`gpt-image-2.6-flare`	Image generation and editing from text and image inputs	`POST /images/generations`
`gpt-image-2.6-sunburst`	Image generation and editing from text and image inputs	`POST /images/generations`
`gpt-image-2.5-sunburst`	Precision editing and production workflows	`POST /images/generations`
`gpt-image-2.5-flare`	Fast image generation and editing	`POST /images/generations`
`gpt-image-2`	OpenAI image generation workflows	`POST /images/generations`

Bytedance

Model	Best for	Endpoint
`seedream-5.0-lite`	Lower-cost image workflows	`POST /images/generations`
`seedream-5.0-pro`	Pro-quality image generation	`POST /images/generations`
`seedream-4.5`	Higher-quality image generation and editing	`POST /images/generations`
`seedream-4.0`	General image generation and editing	`POST /images/generations`

Google

Model	Best for	Endpoint
`gemini-nano-banana-2.1`	Image generation and conversational editing with 1K–4K output	`POST /images/generations`
`gemini-3.1-flash-lite-image`	Lightweight image generation	`POST /images/generations`
`gemini-3.1-flash-image`	Fast image generation and editing	`POST /images/generations`
`gemini-3-pro-image`	Advanced image generation and editing	`POST /images/generations`
`gemini-2.5-flash-image`	Fast image generation and editing	`POST /images/generations`

Grok

Model	Best for	Endpoint
`grok-imagine-image-2.0`	Image generation, local editing, and multi-image composition	`POST /images/generations`

Video models

Bytedance

For the Volcengine-compatible task interface, see Seedance · Volcengine API. The endpoints below use the unified API.

Model	Best for	Endpoint
`seedance-2-5`	Multimodal video generation with synchronized audio	`POST /videos/generations`
`seedance-2-0-mini`	Lightweight, high-volume video generation	`POST /videos/generations`
`seedance-2-0-fast`	Low-latency multimodal video generation	`POST /videos/generations`
`seedance-2-0`	Controllable text-to-video and image-to-video	`POST /videos/generations`

Google

Model	Best for	Endpoint
`gemini-omni-1.2-flash`	Video generation and editing with synchronized audio	`POST /videos/generations`
`gemini-omni-flash-preview`	Multimodal video generation and conversational editing	`POST /videos/generations`

Alibaba

Model	Best for	Endpoint
`happyhorse-1.0`	Image-to-video and video generation workflows	`POST /videos/generations`
`wan2.6`	High-quality video generation	`POST /videos/generations`
`wan3.0-video`	Up to 30-second audiovisual generation with synchronized audio	`POST /videos/generations`

Kling

Model	Best for	Endpoint
`Kling4.0`	Audiovisual generation with multimodal references	`POST /videos/generations`
`kling-v3`	High-quality video with strong visual consistency	`POST /videos/generations`

MiniMax

Model	Best for	Endpoint
`MiniMax-H3`	Text-to-video and image-to-video generation	`POST /videos/generations`
`MiniMax-Hailuo-2.3`	Newer Hailuo video generation	`POST /videos/generations`
`MiniMax-Hailuo-02`	Hailuo video generation	`POST /videos/generations`

Audio models

Model	Best for	Endpoint
`eleven_v4`	Expressive text-to-speech, up to 10,000 Unicode characters per request	`POST /api/v1/audio-generation`
`eleven_v3`	Expressive text-to-speech, up to 5,000 Unicode characters per request	`POST /api/v1/audio-generation`

Create an audio task with a voice ID and an idempotency key, then poll GET /api/v1/query/audio-generation for the result. These audio paths use https://api.linkmodel.ai as the base URL. See Audio pricing for character-cost billing.

Chat models

OpenAI

Model	Best for	Endpoints
`gpt-6.1-terra`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-6.1-sol`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-6-luna`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`, `POST /decisions`
`gpt-6-sol`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-6-astra`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.6-sol`	GPT chat, reasoning, and Codex workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.6-luna`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.6-terra`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.5`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.4-mini`	Lower-latency GPT chat workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.4`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.4-pro`	Higher-capability GPT chat workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5.2`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`
`gpt-5`	GPT chat and reasoning workflows	`POST /chat/completions`, `POST /messages`, `POST /responses`

Google

Model	Best for	Endpoints
`gemini-4-argon`	Gemini pro chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`gemini-3.8-flash`	Fast Gemini chat workflows	`POST /chat/completions`, `POST /messages`
`gemini-3.1-pro-preview`	Gemini pro preview chat workflows	`POST /chat/completions`, `POST /messages`
`gemini-3.5-flash`	Fast Gemini chat workflows	`POST /chat/completions`, `POST /messages`
`gemini-3.1-flash-lite`	Lightweight Gemini chat workflows	`POST /chat/completions`, `POST /messages`
`gemini-3-flash-preview`	Gemini preview chat workflows	`POST /chat/completions`, `POST /messages`
`gemini-2.5-flash`	Fast Gemini chat workflows	`POST /chat/completions`, `POST /messages`

Anthropic

Model	Best for	Endpoints
`claude-fable-5-2`	General chat workflows	`POST /chat/completions`, `POST /messages`
`claude-haiku-5-5`	General chat workflows	`POST /chat/completions`, `POST /messages`
`claude-sonnet-5-5`	Claude Sonnet chat and coding workflows	`POST /chat/completions`, `POST /messages`
`claude-opus-5-5`	Claude Opus chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`claude-fable-5-1`	General chat workflows	`POST /chat/completions`, `POST /messages`
`claude-fable-5`	General chat workflows	`POST /chat/completions`, `POST /messages`
`claude-opus-5`	Claude Opus chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`claude-sonnet-5`	Claude Sonnet chat and coding workflows	`POST /chat/completions`, `POST /messages`
`claude-opus-4-8`	Claude Opus chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`claude-opus-4-7`	Claude Opus chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`claude-sonnet-4-6`	Claude Sonnet chat and coding workflows	`POST /chat/completions`, `POST /messages`
`claude-opus-4-6`	Claude Opus chat and reasoning workflows	`POST /chat/completions`, `POST /messages`

MiniMax

Model	Best for	Endpoints
`minimax-m2.7`	MiniMax chat workflows	`POST /chat/completions`, `POST /messages`

DeepSeek

Model	Best for	Endpoints
`DeepSeek-V4.1-Flash-1017`	Fast DeepSeek chat workflows	`POST /chat/completions`, `POST /messages`
`deepseek-v4-pro`	DeepSeek reasoning and coding workflows	`POST /chat/completions`, `POST /messages`
`deepseek-v4-flash`	Fast DeepSeek chat workflows	`POST /chat/completions`, `POST /messages`

Moonshot

Model	Best for	Endpoints
`kimi-k3.1-pro`	Kimi chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`kimi-k3`	Kimi chat and reasoning workflows	`POST /chat/completions`, `POST /messages`
`kimi-k2.6`	Kimi chat and reasoning workflows	`POST /chat/completions`, `POST /messages`

Z.ai

Model	Best for	Endpoints
`glm-5.3-flash`	GLM chat and coding workflows	`POST /chat/completions`, `POST /messages`
`glm-5.3`	GLM chat and coding workflows	`POST /chat/completions`, `POST /messages`
`glm-5.2`	GLM chat and coding workflows	`POST /chat/completions`, `POST /messages`
`glm-5.1`	GLM chat and coding workflows	`POST /chat/completions`, `POST /messages`

Grok

Model	Best for	Endpoints
`grok-4.6`	General chat workflows	`POST /chat/completions`, `POST /messages`
`grok-4.5`	General chat workflows	`POST /chat/completions`, `POST /messages`

Chat endpoints

Endpoint	Format	Use when
`POST /chat/completions`	OpenAI-compatible	Your app already uses the OpenAI Chat Completions format.
`POST /messages`	Anthropic-compatible	Your app already uses the Anthropic Messages format.
`POST /responses`	OpenAI Responses-compatible	You are configuring Codex with a GPT-series LinkModel chat model.
`POST /decisions`	OpenAI Decisions-compatible	You need classification, routing, or scoring with `gpt-6-luna`.
`POST /v1beta/models/{model}:generateContent`	Gemini-native multimodal	You need Gemini-native video or file input through `fileData`.

For Decisions, OpenAI uses standard GPT-6 Luna input and cache rates and does not charge for output tokens. This exception does not change Luna output pricing on other endpoints. See Chat pricing for LinkModel model rates and the official Decisions pricing rules.

Selection guide

Goal	Start with
Fast image experimentation	`gpt-image-2.5-flare`, `gemini-2.5-flash-image`, or `seedream-5.0-lite`
Higher-quality image output	`gpt-image-2.5-sunburst`, `seedream-5.0-pro`, or `seedream-4.5`
Text-to-video scenes	`kling-v3` or `seedance-2-0`
Image-to-video animation	`kling-v3`, `seedance-2-0`, or `happyhorse-1.0`
OpenAI-compatible chat integration	`POST /chat/completions`
Anthropic-compatible chat integration	`POST /messages`
Codex model provider	`gpt-6.1-sol` or `gpt-5.6-sol` with `POST /responses`
Understand an uploaded video	Video understanding with Gemini using a compatible Google Gemini model

Open the API Reference tab and select a model to inspect its required fields, defaults, and response schema.

Overview

Guides

FAQ

Models

Image models

OpenAI

Bytedance

Google

Grok

Video models

Bytedance

Google

Alibaba

Kling

MiniMax

Audio models

Chat models

OpenAI

Google

Anthropic

MiniMax

DeepSeek

Moonshot

Z.ai

Grok

Chat endpoints

Selection guide

Next

​Image models

​OpenAI

​Bytedance

​Google

​Grok

​Video models

​Bytedance

​Google

​Alibaba

​Kling

​MiniMax

​Audio models

​Chat models

​OpenAI

​Google

​Anthropic

​MiniMax

​DeepSeek

​Moonshot

​Z.ai

​Grok

​Chat endpoints

​Selection guide

​Next

Image models

OpenAI

Bytedance

Google

Grok

Video models

Bytedance

Google

Alibaba

Kling

MiniMax

Audio models

Chat models

OpenAI

Google

Anthropic

MiniMax

DeepSeek

Moonshot

Z.ai

Grok

Chat endpoints

Selection guide

Next