Skip to content

Models

Official prices, key limits, and available groups for every public model. Open any model for its full spec.

Claude

13

Native Anthropic-protocol models that work directly with Claude Code and the Messages API.

GPT Image

5

Billed per token; the only image family with mask-based partial edits, and it can output transparent backgrounds.

GPT

27

Native Codex and OpenAI SDK models, available on both Responses and Chat Completions.

Gemini Image

6

Generates by aspect ratio, takes up to 14 reference images, billed per delivered image.

Gemini

16

Works over OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages (tool calling on all three); one API key covers the whole Flash, Lite, and Pro lineup.

US Region

5

US Region IDs, callable through Chat Completions, Responses and Anthropic Messages.

GLM

3

1M context with thinking always on; available on both Chat Completions and Responses.

Kimi

2

Qwen

5

All five models have a 1M context window and one group covers them all; qwen4-max outputs up to 262,144 tokens with thinking on, the others 131,072.

DeepSeek

5

1M-context reasoning models; thinking can be turned on or off, and prefix completion is supported.

Tencent Hunyuan

2

Doubao Seed

7

ByteDance Doubao Seed chat models. All seven sit in one group, read images, call tools, and work over all three protocols.

Grok Imagine

1

Per-second text-to-video with optional reference images, 1–15 seconds long.

Grok Imagine

3

Priced per image, two tiers (1k / 2k), up to 2 reference images for edits.

Grok

6

Context up to 2M with reasoning always on; available on both Chat Completions and Responses.

Seedream

4

Priced per image, synchronous only, 1 image per request; well suited to large 2K–4K images.

Seedance 超分版

2

Seedance generated at a lower resolution and upscaled with AI to 1080p / 4K, priced below native 1080p / 4K; suited to high-resolution batch production.

Seedance

10

Text-to-video and multimodal-reference video; the overseas 2.0 standard models are the only ones that support 4K.

Kling Image

7

Async image generation with up to 10 reference images, plus dedicated models for image-to-image, multi-image reference, and outpainting.

Kling

14

Billed per second; covers first and last frames, subject reference, motion control, avatars, and lip sync.

Midjourney

1

Always 4 images per task; aspect ratio and style parameters go in the prompt.

MiniMax Speech

2

Synchronous text to speech, billed per character, with official voices and voice cloning.

Doubao Speech

3

ByteDance Doubao Speech: text to speech, or audio with tone and sound effects from a scene description; the whole clip is returned synchronously.

MiniMax Hailuo

4

24 FPS video with native stereo audio; dialogue and narration are generated with the picture.

Wan · HappyHorse

4

Wan and HappyHorse: native task API, billed per second, up to 30 seconds long.

Prices are official prices in USD. Actual charge = official price × group multiplier; see Usage in the console for exact charges.