Simple, transparent pricing

Pay only for what you use. $1 free credit on signup. All rates are pulled live from the same database that bills your account.

Prices shown are live from our billing system

Inference API

Pay per token across all platform models. OpenAI-compatible endpoints, multi-region routing.

Language

Model	Input	Output	Notes
DeepSeek-V4-Flash	$0.49/1M	$1.42/1M	—
DeepSeek-V4-Pro	$0.91/1M	$2.72/1M	—
GLM-5.2	$1.00/1M	$3.00/1M	—
GLM-5.3	$1.25/1M	$4.30/1M	—
gpt-oss-20b	$0.20/1M	$0.28/1M	Context: 125K
Kimi-K3	$2.00/1M	$12.00/1M	—
Llama-3.1-8B-Instruct	$0.10/1M	$0.10/1M	Context: 125K
MiniMax-M3	$0.20/1M	$0.90/1M	—
qwen3-coder-30b-a3b-instruct	$0.10/1M	$0.30/1M	Context: 32K
qwen3.8-flash	$0.09/1M	$0.37/1M	—
qwen3.8-max	$1.90/1M	$5.70/1M	—

Vision

Model	Input	Output	Notes
Gemma-4-31B-IT	$0.50/1M	$0.50/1M	Context: 32K
qwen3-omni-30b-a3b-instruct	$0.40/1M	$0.80/1M	Context: 32K
qwen3-vl-8b-instruct	$0.15/1M	$0.50/1M	Context: 32K
Qwen3.6-27B	$0.30/1M	$0.60/1M	Context: 32K
Qwen3.6-35B-A3B	$0.40/1M	$0.40/1M	Context: 32K
Qwen3.8-27B	$0.30/1M	$0.60/1M	Context: 32K

Embedding

Model	Input	Output	Notes
Jina-Embeddings-V3	$0.02/1M	—	—
Jina-Embeddings-V4	$0.12/1M	—	—
qwen3-embedding-0.6b	$0.12/1M	—	—

Reranker

Model	Input	Output	Notes
BGE-Reranker-V2-M3	$0.03/1M	—	—

Image

Model	Input	Output	Notes
FLUX.2 Klein flux2-klein	—	$20.00/1M out tok	Tokens / item: 1,000
Qwen-Image	—	$30.00/1M out tok	Tokens / item: 1,000
Z-Image-Turbo	—	$10.00/1M out tok	Tokens / item: 1,000

Speech

Model	Input	Output	Notes
Fun-ASR-Nano	$0.05/1M in tok	—	Tokens / sec audio: 1,000
Kokoro-82M	—	$1.00/1M out tok	Tokens / sec audio: 100
Qwen3-ASR-1.7B qwen3-asr-1-7b	$0.05/1M in tok	—	Tokens / sec audio: 1,000
Qwen3-TTS	—	$2.00/1M out tok	Tokens / sec audio: 100
Whisper-Large-V3-Turbo	$0.10/1M in tok	—	Tokens / sec audio: 1,000

Video Generation

Priced by output resolution and whether you supply a reference video. Self-hosted models (Wan2.2, LTX) bill per second of generated video; upstream-metered models (Seedance) bill on actual tokens used — higher resolutions there have a lower per-token rate but consume far more tokens per second, so a 4K clip still costs more than the same clip at 720p.

Seedance 2.5

dreamina-seedance-2-5-260628

Billed per 1M tokens used

Resolution	Text / image input	With reference video
480p / 720p	$10.91/1M	$6.53/1M
1080p	$11.93/1M	$7.14/1M
4K	$4.00/1M	$2.40/1M

Seedance 2.0

ecolink-video-gen-2.0

Billed per 1M tokens used

Resolution	Text / image input	With reference video
480p / 720p	$7.14/1M	$4.39/1M
1080p	$7.85/1M	$4.79/1M
4K	$4.08/1M	$2.45/1M