Models
Official prices, key limits, and available groups for every public model. Open any model for its full spec.
Claude
10Native Anthropic-protocol models that work directly with Claude Code and the Messages API.
- claude-sonnet-5Claude Sonnet 51M tokens$3 / $15/ 1M tokens
- claude-sonnet-4-6Claude Sonnet 4.61M tokens$3 / $15/ 1M tokens
- claude-opus-5-5Claude Opus 5.51M tokens$4 / $20/ 1M tokens
- claude-opus-5Claude Opus 51M tokens$5 / $25/ 1M tokens
- claude-opus-4-8Claude Opus 4.81M tokens$5 / $25/ 1M tokens
- claude-opus-4-7Claude Opus 4.71M tokens$5 / $25/ 1M tokens
- claude-opus-4-6Claude Opus 4.61M tokens$5 / $25/ 1M tokens
- claude-haiku-4-5-20251001Claude Haiku 4.5200K tokens$1 / $5/ 1M tokens
- claude-fable-5-1Claude Fable 5.11M tokens$10 / $50/ 1M tokens
- claude-fable-5Claude Fable 51M tokens$10 / $50/ 1M tokens
GPT Image
3Billed per token; the only image family with mask-based partial edits, and it can output transparent backgrounds.
GPT
10Native Codex and OpenAI SDK models, available on both Responses and Chat Completions.
- gpt-6-solGPT-6 Sol1M tokens$2 / $10/ 1M tokens
- gpt-6-lunaGPT-6 Luna1M tokens$0.10 / $0.50/ 1M tokens
- gpt-6-astraGPT-6 Astra1M tokens$10 / $50/ 1M tokens
- gpt-5.6-terraGPT 5.6 Terra1M tokens$2.50 / $15/ 1M tokens
- gpt-5.6-solGPT 5.6 Sol1M tokens$5 / $30/ 1M tokens
- gpt-5.5GPT 5.5400K tokens$5 / $30/ 1M tokens
- gpt-5.4-miniGPT 5.4 Mini128K tokens$0.75 / $4.50/ 1M tokens
- gpt-5.4GPT 5.4272K tokens$2.50 / $15/ 1M tokens
- gpt-5.3-codex-sparkGPT 5.3 Codex Spark128K tokens$1.75 / $14/ 1M tokens
- codex-auto-reviewCodex Auto Review (GPT-5.3-Codex)128K tokens$1.75 / $14/ 1M tokens
Gemini
1The only model that returns video synchronously: one request returns an MP4, no polling.
Gemini Image
5Generates by aspect ratio, takes up to 14 reference images, billed per delivered image.
- gemini-3.1-flash-lite-imageGemini 3.1 Flash Lite Image1K$0.0336/ image
- gemini-3.1-flash-image-previewGemini 3.1 Flash Image Preview1K · 2K$0.0672/ image
- gemini-3.1-flash-imageGemini 3.1 Flash Image1K · 2K$0.0672/ image
- gemini-3-pro-imageGemini 3 Pro Image1K · 2K · 4K$0.1344from / image
- gemini-2.5-flash-imageGemini 2.5 Flash Image1K$0.0387/ image
Gemini
13OpenAI Chat Completions compatible; one API key covers the whole Flash, Lite, and Pro lineup.
- gemini-3.8-flashGemini 3.8 Flash1M tokens$0.75 / $3.75/ 1M tokens
- gemini-3.7-flashGemini 3.7 Flash$0.75 / $3.75/ 1M tokens
- gemini-3.6-flashGemini 3.6 Flash$0.75 / $3.75/ 1M tokens
- gemini-3.5-flash-liteGemini 3.5 Flash Lite$0.30 / $2.50/ 1M tokens
- gemini-3.5-flashGemini 3.5 Flash$1.50 / $9/ 1M tokens
- gemini-3.1-pro-preview-customtoolsGemini 3.1 Pro Preview Custom Tools$2 / $12/ 1M tokens
- gemini-3.1-pro-previewGemini 3.1 Pro Preview$2 / $12/ 1M tokens
- gemini-3.1-flash-lite-previewGemini 3.1 Flash Lite Preview$0.25 / $1.50/ 1M tokens
- gemini-3.1-flash-liteGemini 3.1 Flash Lite$0.25 / $1.50/ 1M tokens
- gemini-3-flash-previewGemini 3 Flash Preview$0.50 / $3/ 1M tokens
- gemini-2.5-proGemini 2.5 Pro$1.25 / $10/ 1M tokens
- gemini-2.5-flash-liteGemini 2.5 Flash Lite$0.10 / $0.40/ 1M tokens
- gemini-2.5-flashGemini 2.5 Flash$0.30 / $2.50/ 1M tokens
GLM
21M context with thinking always on; available on both Chat Completions and Responses.
Qwen
5All five models have a 1M context window and 131,072 max output, and one group covers them all.
DeepSeek
31M-context reasoning models; thinking can be turned on or off, and prefix completion is supported.
Grok Imagine
1Per-second text-to-video with optional reference images, 1–15 seconds long.
Grok Imagine
3Priced per image, two tiers (1k / 2k), up to 2 reference images for edits.
Grok
5Context up to 2M with reasoning always on; available on both Chat Completions and Responses.
Seedream
3Priced per image, synchronous only, 1 image per request; well suited to large 2K–4K images.
Seedance
14Text-to-video and multimodal-reference video; the overseas 2.0 standard models are the only ones that support 4K.
- dreamina-seedance-2-5-260628Seedance 2.5 HC (Overseas)480p · 720p · 1080p$6.40from / 1M tokens
- dreamina-seedance-2-0-mini-hcSeedance 2.0 Mini (hc)480p · 720p$2.10from / 1M tokens
- dreamina-seedance-2-0-mini-epSeedance 2.0 Mini (ep)480p · 720p$2.10from / 1M tokens
- dreamina-seedance-2-0-mini-260615Seedance 2.0 Mini (260615)480p · 720p$2.10from / 1M tokens
- dreamina-seedance-2-0-hcSeedance 2.0 (hc)480p · 720p · 1080p · 4K$2.40from / 1M tokens
- dreamina-seedance-2-0-fast-hcSeedance 2.0 Fast (hc)480p · 720p$3.30from / 1M tokens
- dreamina-seedance-2-0-fast-epSeedance 2.0 Fast (ep)480p · 720p$3.30from / 1M tokens
- dreamina-seedance-2-0-fast-260128Seedance 2.0 Fast (260128)480p · 720p$3.30from / 1M tokens
- dreamina-seedance-2-0-epSeedance 2.0 (ep)480p · 720p · 1080p · 4K$2.40from / 1M tokens
- dreamina-seedance-2-0-260128Seedance 2.0 (260128)480p · 720p · 1080p · 4K$2.40from / 1M tokens
- doubao-seedance-2-5-260628-aSeedance 2.5 (Doubao 260628-a)480p · 720p · 1080p$6.18from / 1M tokens
- doubao-seedance-2-0-mini-260615-aSeedance 2.0 Mini (Doubao 260615-a)480p · 720p$0.824from / 1M tokens
- doubao-seedance-2-0-fast-260128-aSeedance 2.0 Fast (Doubao 260128-a)480p · 720p$2.43from / 1M tokens
- doubao-seedance-2-0-260128-aSeedance 2.0 (Doubao 260128-a)480p · 720p · 1080p$4.12from / 1M tokens
Kling Image
7Async image generation with up to 10 reference images, plus dedicated models for image-to-image, multi-image reference, and outpainting.
- kling-image-v3-omniKling Image 3.0 Omni1K · 2K · 4K$0.0294from / image
- kling-image-v3Kling Image 3.01K · 2K$0.0294/ image
- kling-image-v2-1-multi-refKling Image 2.1 (multi-reference)1K · 2K$0.0588from / image
- kling-image-v2-1-i2iKling Image 2.1 (image-to-image)1K · 2K$0.0294/ image
- kling-image-v2-1Kling Image 2.1 (text-to-image)1K · 2K$0.0147/ image
- kling-image-o1Kling Image O11K · 2K · 4K$0.0294from / image
- kling-image-expandKling Image Expand1K$0.0294/ image
Kling
13Billed per second; covers first and last frames, subject reference, motion control, avatars, and lip sync.
- kling-v3-turboKling 3.0 Turbo720p · 1080p · 2K · 4K$0.1176from / second
- kling-v3-omniKling 3.0 Omni720p · 1080p · 2K · 4K$0.0882from / second
- kling-v3-motion-controlKling 3.0 Motion Control720p · 1080p · 2K · 4K$0.1324from / second
- kling-v3Kling 3.0720p · 1080p · 2K · 4K$0.0882from / second
- kling-v2-6-motion-controlKling 2.6 Motion Control720p · 1080p$0.0735from / second
- kling-v2-6Kling 2.6720p · 1080p · 2K · 4K$0.0441from / second
- kling-v2-5-turboKling 2.5 Turbo720p · 1080p$0.0441from / second
- kling-v2-1Kling 2.1720p · 1080p · 2K · 4K$0.0588from / second
- kling-v2-0Kling 2.0720p · 1080p · 2K · 4K$0.0588from / second
- kling-v1-6Kling 1.6720p · 1080p · 2K · 4K$0.0588from / second
- kling-o1Kling O1720p · 1080p · 2K · 4K$0.0882from / second
- kling-lip-syncKling Lip SyncLip sync$0.0147/ second
- kling-avatarKling Avatar720p · 1080p$0.0588from / second
Midjourney
1Always 4 images per task; aspect ratio and style parameters go in the prompt.
MiniMax Speech
2Synchronous text to speech, billed per character, with official voices and voice cloning.
MiniMax Hailuo
224 FPS video with native stereo audio; dialogue and narration are generated with the picture.
Wan · HappyHorse
4Wan and HappyHorse: native task API, billed per second, up to 30 seconds long.
- wan3.0-videoWan 3.0 Omni-Reference Video480p · 720p · 1080p$0.0441from / second
- happyhorse-1.1-t2vHappyHorse 1.1 Text-to-Video480p · 720p · 1080p$0.0662from / second
- happyhorse-1.1-r2vHappyHorse 1.1 Reference-to-Video480p · 720p · 1080p$0.0662from / second
- happyhorse-1.1-i2vHappyHorse 1.1 Image-to-Video (first frame)480p · 720p · 1080p$0.0662from / second
Prices are official prices in USD. Actual charge = official price × group multiplier; see Usage in the console for exact charges.