Input / 1M tokens$10.00$3.00
Output / 1M tokens$50.00$14.60
Pricing
Every model VipAI routes, with the provider’s published list price beside ours, so the discount is something you can check rather than take on trust. Billed per token in USD, no subscription, credits never expire.
Live pricing · up to 99% off
Prices update in real time and move with upstream costs. Each request is billed at the discount in effect when it's made. All prices in USD per 1M tokens.
Input / 1M tokens$5.00$1.60
Output / 1M tokens$25.00$8.00
Input / 1M tokens$3.00$0.60
Output / 1M tokens$15.00$3.10
Input / 1M tokens$2.00$0.35
Output / 1M tokens$12.00$2.10
Input / 1M tokens$5.00$0.70
Output / 1M tokens$30.00$4.00
Input / 1M tokens$5.00$0.65
Output / 1M tokens$30.00$3.90
| Model | Context | Input (List) | Output (List) | Input (VipAI) | Output (VipAI) | Cache (VipAI) | Provider |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | 1M | $10.00 | $50.00 | $3.0070% off | $14.60 | $0.30 | Anthropic |
| Claude Opus 4.8 | 1M | $5.00 | $25.00 | $1.6068% off | $8.00 | $0.16 | Anthropic |
| Claude Sonnet 5 | 1M | $3.00 | $15.00 | $0.6080% off | $3.10 | $0.06 | Anthropic |
| Gemini 3.1 Pro (Preview) | 2M | $2.00 | $12.00 | $0.3583% off | $2.10 | $0.035 | |
| GPT-5.5 | 1M | $5.00 | $30.00 | $0.7086% off | $4.00 | $0.07 | OpenAI |
| GPT-5.6 Sol | 1M | $5.00 | $30.00 | $0.6587% off | $3.90 | $0.065 | OpenAI |
| Claude Fable 5.1 | 1M | $10.00 | $50.00 | $2.4076% off | $12.00 | — | Anthropic |
| Claude Haiku 4.5 | 200K | $1.00 | $5.00 | $0.3466% off | $1.70 | — | Anthropic |
| Claude Haiku 4.5 | 200K | $1.00 | $5.00 | $1.00 | $5.00 | $0.10 | Anthropic |
| Claude Opus 4.6 | 1M | $5.00 | $25.00 | $5.00 | $25.00 | $0.50 | Anthropic |
| Claude Opus 4.7 | 1M | $5.00 | $25.00 | $5.00 | $25.00 | $0.50 | Anthropic |
| Claude Opus 5 | 1M | $5.00 | $25.00 | $1.0579% off | $5.25 | — | Anthropic |
| Claude Opus 5.5 | 1M | $4.00 | $20.00 | $1.0474% off | $5.20 | — | Anthropic |
| Claude Sonnet 4.6 | 1M | $3.00 | $15.00 | $0.6080% off | $3.00 | — | Anthropic |
| DS DeepSeek Flash | 1M | $0.15 | $0.60 | $0.15 | $0.60 | $0.003 | DeepSeek |
| DS DeepSeek Flash (free) | 1M | $0.15 | $0.60 | $0.001599% off | $0.006 | $0 | DeepSeek |
| DS DeepSeek V4 Flash | 1M | $0.14 | $0.28 | $0.14 | $0.28 | $0.0028 | DeepSeek |
| DS DeepSeek V4 Flash (free) | 1M | $0.14 | $0.28 | $0.001499% off | $0.0028 | $0 | DeepSeek |
| DS DeepSeek V4 Flash Vision | 1M | $0.22 | $0.66 | $0.22 | $0.66 | $0.0044 | DeepSeek |
| DS DeepSeek V4 Pro | 1M | $0.43 | $0.87 | $0.55 | $1.10 | $0.0046 | DeepSeek |
| DS DeepSeek V4 Pro (0425) | 1M | $0.43 | $0.87 | $0.43 | $0.87 | $0.0036 | DeepSeek |
| GLM GLM-5.2 | 1M | $1.40 | $4.40 | $1.70 | $5.30 | $0.32 | GLM |
| GLM-5.3 | 1M | $1.40 | $4.40 | $1.40 | $4.40 | $0.26 | GLM |
| GLM-5.3 Flash | 1M | $0.70 | $2.20 | $0.70 | $2.20 | $0.13 | GLM |
| GLM-5.3 Flash (free) | 1M | $0.70 | $2.20 | $0.00799% off | $0.022 | $0.0013 | GLM |
| Gemini 3.1 Flash Image | 1M | $1.50 | $9.00 | $0.3080% off | $1.80 | — | |
| Gemini 3.5 Flash | 1M | $1.50 | $9.00 | $0.3080% off | $1.80 | — | |
| Gemini 3.5 Flash-Lite | 1M | $0.30 | $2.50 | $0.06977% off | $0.57 | — | |
| Gemini 3.6 Flash | 1M | $1.50 | $7.50 | $0.3279% off | $1.57 | — | |
| Gemini 3.7 Flash | 1M | $1.50 | $7.50 | $0.2881% off | $1.42 | — | |
| Gemini 3.8 Flash | 1M | $1.50 | $7.50 | $0.2782% off | $1.35 | — | |
| Kimi K3 | 1M | $3.00 | $15.00 | $0.7575% off | $3.75 | — | Moonshot |
| Kimi K3 (1M) | 1M | $3.00 | $15.00 | $0.7575% off | $3.75 | — | Moonshot |
| GPT-5.4 | 1M | $2.50 | $15.00 | $0.3586% off | $2.10 | $0.035 | OpenAI |
| GPT-5.4 mini | 1M | $0.75 | $4.50 | $0.1185% off | $0.66 | $0.011 | OpenAI |
| GPT-5.6 Luna | 1M | $1.00 | $6.00 | $0.1486% off | $0.80 | $0.014 | OpenAI |
| GPT-5.6 Terra | 1M | $2.50 | $15.00 | $0.3586% off | $2.00 | $0.035 | OpenAI |
| GPT-6 Luna | 1M | $0.10 | $0.50 | $0.01189% off | $0.055 | — | OpenAI |
| GPT-6 Sol | 1M | $2.00 | $10.00 | $0.2289% off | $1.10 | — | OpenAI |
| Grok 4.6 | 500K | $2.00 | $6.00 | $0.4080% off | $1.20 | $0.10 | xAI |
List prices are the providers' published rates; the VipAI column is what you pay. The six cards above are our most-used models — open the full catalogue for every model we route.
FAQ
How billing works
You are charged per million tokens, separately for input and output, at the rate shown in the table above. Prices move with upstream provider costs, and each request is billed at the rate in effect when it was made.
- Input and output are metered separately, so a model with expensive output costs more on a long completion than on a long prompt.
- Prompt cache reads are charged at the cache rate in the table, which is a fraction of the input rate on models that support it.
- Complimentary models — ids ending in
-free, plusjev— run at a promotional discount with a personal daily allowance and a shared platform capacity. Rate limits has the numbers. - No subscription. Buy credits when you want, spend them whenever; a balance that runs out stops requests rather than becoming a debt.
Why one message can produce several billing rows, and how cache is priced, is covered in billing questions. The request formats are in the API reference, and the full id list is in the model catalogue.