Models & Pricing
Use leading chat, image, video and audio models through one API with transparent usage pricing.
Chat
8Claude Haiku 5.5
Anthropicclaude-haiku-5-5For high-volume, cost-sensitive tasks such as summaries, classification and customer support.
/ 1M tokens
- Input
- 0.054 – 0.28 USD
- Output
- 0.27 – 1.4 USD
- Cache read
- 0.0055 – 0.028 USD
Minimum per call: 0.000005 USD
Pricing follows the selected specifications
Claude Opus 5.5
Anthropicclaude-opus-5-5For complex, open-ended work requiring sustained judgment, including large coding projects and detailed analysis.
/ 1M tokens
- Input
- $1.9
- Output
- $9.5
- Cache read
- $0.11
Minimum per call: 0.000005 USD
Claude Sonnet 5.5
Anthropicclaude-sonnet-5-5A balanced choice for everyday work, debugging, document drafting and iterative problem solving.
/ 1M tokens
- Input
- $0.95
- Output
- $4.75
- Cache read
- $0.06
Minimum per call: 0.000005 USD
DeepSeek V4.1 Flash 1017
DeepSeekdeepseek-v4.1-flash-1017A lightweight model for coding, reasoning and everyday questions, using the October 17 update.
- Input
- 0.3USD
- Output
- 1.2USD
gemini-3.8-flash
GoogleText generation for questions, writing and summaries, with streaming replies.
/ 1M tokens
- Input
- $0.21
- Output
- $1.05
- Cache read
- $0.021
Minimum per call: 0.000005 USD
gemini-4-argon
GoogleText generation for questions, writing and summaries, with streaming replies.
/ 1M tokens
- Input
- $0.66
- Output
- $3.3
- Cache read
- $0.033
Minimum per call: 0.000005 USD
GPT-6 Luna
OpenAIgpt-6-lunaAn efficient model for focused tasks at scale, such as classification, extraction and concise answers.
/ 1M tokens
- Input
- 0.027 – 0.1 USD
- Output
- 0.135 – 0.4 USD
- Cache read
- 0.0027 – 0.01 USD
Minimum per call: 0.000005 USD
Pricing follows the selected specifications
MiniMax M3.1 Flash
MiniMaxminimax-m3.1-flashDesigned for coding and multi-step tasks. Useful for code assistance and planning workflows.
/ 1M tokens
- Input
- $0.12
- Output
- $0.48
- Cache read
- $0.012
Minimum per call: 0.000005 USD