Model API prices
Every model TopxAI serves with its fixed USD price per 1M tokens, per image or per second on each route: shared pool, official line and private deployment, next to the provider's list price.
LLM API price calculator · What a month of requests costs on every text model and route
| Model | Vendor | Lowest-priced route |
|---|---|---|
Claude Fable 5.2 claude-fable-5-2 | Anthropic | $4 input / $20 output per 1M tokens |
Claude Opus 5.5 claude-opus-5-5 | Anthropic | $2 input / $10 output per 1M tokens |
Claude Sonnet 5.5 claude-sonnet-5-5 | Anthropic | $1 input / $5 output per 1M tokens |
GPT-6 Astra gpt-6-astra | OpenAI | $5 input / $25 output per 1M tokens |
GPT-6.1 Sol gpt-6.1-sol | OpenAI | $1 input / $5 output per 1M tokens |
GPT-6.1 Terra gpt-6.1-terra | OpenAI | $0.5 input / $2.5 output per 1M tokens |
GPT Image 2.6 Flare gpt-image-2.6-flare | OpenAI | from $0.03 per image |
GPT Image 2.6 Sunburst gpt-image-2.6-sunburst | OpenAI | from $0.03 per image |
Grok 4.7 grok-4.7 | xAI | $1 input / $3 output per 1M tokens |
Grok Imagine Video 1.5 grok-imagine-video-1.5 | xAI | from $0.05 per second |
GLM-5.3-Abliterated GLM-5.3-Abliterated | Zhipu AI (private deployment) | $3 input / $6 output per 1M tokens |
GLM-5.3-Flash-Abliterated GLM-5.3-Flash-Abliterated | Zhipu AI (private deployment) | $0.36 input / $1.5 output per 1M tokens |
deepseek-flash-Abliterated deepseek-flash-Abliterated | DeepSeek (private deployment) | $0.42 input / $1.5 output per 1M tokens |
Kimi K3.1 Pro kimi-k3.1-pro | Moonshot AI (private deployment) | $0.5 input / $5 output per 1M tokens |
deepseek-flash-fast deepseek-flash-fast | DeepSeek (private deployment) | $0.02 input / $0.16 output per 1M tokens |
Jev 1.14.0 jev-1.14.0 | TypeSafe | $0.055 per 1M input tokens, output free |
Every route
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, per second by resolution. Shared pool routes are 50% of the provider's list price, official line routes 90%; the GLM, Kimi and DeepSeek models are privately deployed, each line at fixed prices.
| Model | Route | Price (USD) |
|---|---|---|
| claude-fable-5-2 | Official line | $7.2 input / $36 output per 1M tokens |
| claude-fable-5-2 | Shared pool | $4 input / $20 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-6.1-terra | Official line | $0.9 input / $4.5 output per 1M tokens; from 272,001 input tokens the whole request bills $1.8 input / $6.75 output |
| gpt-6.1-terra | Shared pool | $0.5 input / $2.5 output per 1M tokens; from 272,001 input tokens the whole request bills $1 input / $3.75 output |
| gpt-image-2.6-flare | Image | $0.03 per 1K image / $0.05 per 2K image / $0.2 per 4K image |
| gpt-image-2.6-sunburst | Image | $0.03 per 1K image / $0.05 per 2K image / $0.2 per 4K 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 | $3 input / $6 output per 1M tokens; Backup deployment (only if the main deployment fails): $4 input, $7 output, $0.4 cache read |
| GLM-5.3-Flash-Abliterated | Private deployment | $0.36 input / $1.5 output per 1M tokens |
| deepseek-flash-Abliterated | Private deployment | $0.42 input / $1.5 output per 1M tokens; Backup deployment (only if the main deployment fails): $1.3 input, $2.6 output, $0.15 cache read |
| kimi-k3.1-pro | Private deployment | $0.5 input / $5 output per 1M tokens; Backup deployment (only if the main deployment fails): $2.4 input, $12 output, $0.24 cache read, $2.4 cache write |
| deepseek-flash-fast | Private deployment | $0.02 input / $0.16 output per 1M tokens |
| jev-1.14.0 | Official line | $0.055 input / $0 output per 1M tokens; Backup deployment (only if the main deployment fails): $0.058 input, $0 output, $0.058 cache read |
Get an API key · Docs · Blog · About TopxAI