Claude, OpenAI, Grok, GLM, Kimi, DeepSeek and Jev through one API
Use Claude Fable 5.1, Sonnet 5.5 and Opus 5.5, GPT-6 Astra, GPT-6.1 Sol and GPT Image 2.5, Grok 4.7 and Grok Imagine Video 1.5, GLM-5.3-Abliterated, Kimi K3, DeepSeek V4.1 Flash and V4 Pro, and TypeSafe's Jev (System One) through one OpenAI- and Anthropic-compatible endpoint. Fixed USD prices per million tokens, per image or per second of video, prepaid credit and no stored conversation content.
Why TopxAI
- Explicit model choice. Choose your model and route. Know the price before the first request.
- One connection, seven providers. Use familiar OpenAI and Anthropic APIs with your existing tools.
- Zero retention. Prompts and completions are relayed, never stored.
- Clear usage-based pricing. Compare model prices and follow every charge in your usage log.
Models & pricing
Prices in USD: per 1M tokens for text (OpenAI and Grok models bill the whole request at a higher rate once the input context reaches their long-context threshold), per image by size for image generation, per second by resolution for video. Shared pool routes offer discounted rates; official line routes call the provider directly; GLM-5.3-Abliterated is a privately deployed fine-tuned model on its own line; DeepSeek bills the whole request at its peak rates when it is accepted during the provider's peak hours (09:00-12:00 and 14:00-18:00 Beijing time, 01:00-04:00 and 06:00-10:00 UTC, on working days) and at half that off-peak.
| Model | Route | Price (USD) |
|---|---|---|
| claude-fable-5-1 | Official line | $9 input / $45 output per 1M tokens |
| claude-fable-5-1 | Shared pool | $5 input / $25 output per 1M tokens |
| claude-opus-5-5 | Official line | $3.6 input / $18 output per 1M tokens |
| claude-opus-5-5 | Shared pool | $2 input / $10 output per 1M tokens |
| claude-sonnet-5-5 | Official line | $1.8 input / $9 output per 1M tokens |
| claude-sonnet-5-5 | Shared pool | $1 input / $5 output per 1M tokens |
| gpt-6-astra | Official line | $9 input / $45 output per 1M tokens; from 272,001 input tokens the whole request bills $18 input / $67.5 output |
| gpt-6-astra | Shared pool | $5 input / $25 output per 1M tokens; from 272,001 input tokens the whole request bills $10 input / $37.5 output |
| gpt-6.1-sol | Official line | $1.8 input / $9 output per 1M tokens; from 272,001 input tokens the whole request bills $3.6 input / $13.5 output |
| gpt-6.1-sol | Shared pool | $1 input / $5 output per 1M tokens; from 272,001 input tokens the whole request bills $2 input / $7.5 output |
| gpt-image-2.5-flare | Image | $0.03 per 1K image / $0.05 per 2K image |
| gpt-image-2.5-sunburst | Image | $0.03 per 1K image / $0.05 per 2K image |
| grok-4.7 | Official line | $1.8 input / $5.4 output per 1M tokens; from 200,000 input tokens the whole request bills $3.6 input / $10.8 output |
| grok-4.7 | Shared pool | $1 input / $3 output per 1M tokens; from 200,000 input tokens the whole request bills $2 input / $6 output |
| grok-imagine-video-1.5 | Official line | $0.05 per 480p / $0.1 per 720p / $0.2 per 1080p |
| GLM-5.3-Abliterated | Private deployment | $4 input / $7 output per 1M tokens |
| kimi-k3 | Official line | $2.4 input / $12 output per 1M tokens |
| deepseek-flash | Official line | $0.12 input / $0.48 output per 1M tokens |
| deepseek-v4-pro | Official line | $0.528 input / $1.584 output per 1M tokens |
| jev-1.13.0 | Official line | $0.04494 input / $0 output per 1M tokens |
Every model's price on its own page · Changelog
Get an API key · Docs · Blog · About TopxAI · Privacy Policy · User Agreement · Acceptable Use Policy