Model Pricing

Prices below are upstream provider costs. Your actual bill is the displayed price x 1.05. Token prices are per 1 million tokens.

For the full model list and real-time pricing, visit chuizi.ai/models.

OpenAI

ModelInput ($/1M)Output ($/1M)Context Window
GPT-4.1$2.00$8.001M
GPT-4.1-mini$0.40$1.601M
GPT-4.1-nano$0.10$0.401M
GPT-4o$2.50$10.00128K
GPT-4o-mini$0.15$0.60128K
o3$2.00$8.00200K
o4-mini$1.10$4.40200K

Anthropic

ModelInput ($/1M)Output ($/1M)Context Window
Claude Opus 4-6$15.00$75.00200K
Claude Sonnet 4-6$3.00$15.00200K
Claude Haiku 4-5$1.00$5.00200K

Anthropic models support prompt caching. The cache_read price is approximately 10% of the input price. See Cache Discount Pricing for details.

Google

ModelInput ($/1M)Output ($/1M)Context Window
Gemini 2.5 Pro$1.25$10.001M
Gemini 2.5 Flash$0.15$0.601M
Gemini 2.0 Flash$0.10$0.401M

DeepSeek

ModelInput ($/1M)Output ($/1M)Context Window
DeepSeek V3.2$0.28$0.42128K
DeepSeek R1$0.55$2.19128K
DeepSeek Chat$0.28$0.42128K

DeepSeek models automatically enable disk caching. cache_read saves approximately 90% of the input cost.

Image Generation (Per-Request Billing)

ModelPrice/RequestNotes
Imagen 4.0$0.040Google image generation
DALL-E 3 (1024x1024)$0.040OpenAI image generation
DALL-E 3 (1024x1792)$0.080High resolution
Nova Canvas$0.040AWS image generation
GPT-Image-1 (1024x1024)$0.040OpenAI next-gen image generation

Audio Models

Text-to-Speech (TTS)

ModelPriceUnit
GPT-4o-mini-tts$0.015Per 1M characters
tts-1$0.015Per 1M characters
tts-1-hd$0.030Per 1M characters

Speech-to-Text

ModelPriceUnit
gpt-4o-transcribe$0.00006Per second of audio
Whisper-1$0.00010Per second of audio

Embedding Models

ModelPrice ($/1M tokens)
text-embedding-3-small$0.02
text-embedding-3-large$0.13

More Models

The table above covers the most popular models. Chuizi.AI supports 221 models in total, including Qwen, GLM, Kimi, MiniMax, Meta Llama, Mistral, Cohere, and more.

View all 221 models with live pricing →

Pricing Notes

  • All prices above are upstream provider costs. Actual billing = displayed price x 1.05
  • Prices may change as upstream providers adjust their rates. Use GET /v1/models for real-time pricing
  • Many models support prompt caching, which can significantly reduce your actual costs
  • All amounts are in USD. The dashboard also displays CNY reference prices

Next Steps

Model Pricing — Chuizi AI Docs | Chuizi AI