Input
- Official Google
- $2
- Here (−50%)
- $1
gemini-3.1-pro-preview
Gemini 3.1 Pro Preview API — price per token
Gemini 3.1 Pro Preview is Google's Pro-tier reasoning model — the strongest Gemini for hard reasoning and long-horizon agentic work, with long-context rates above 200K input tokens.
Pricing per 1M tokens
| Rate | Official Google | Here (−50%) |
|---|---|---|
| Input | $2 | $1 |
| Cached input | $0.2 | $0.1 |
| Output | $12 | $6 |
| Long-context input (>200K) | $4 | $2 |
| Long-context output (>200K) | $18 | $9 |
Cached input
- Official Google
- $0.2
- Here (−50%)
- $0.1
Output
- Official Google
- $12
- Here (−50%)
- $6
Long-context input (>200K)
- Official Google
- $4
- Here (−50%)
- $2
Long-context output (>200K)
- Official Google
- $18
- Here (−50%)
- $9
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1M tokens. Max output: 64K tokens.
Best for
- The hardest reasoning, planning and review work.
- Long-horizon agentic tasks with tool use.
- Deep document and codebase analysis in the 1M-token window.
Good to know
- Requests above 200K input tokens bill at long-context rates — $4/$18 per 1M (2× input, 1.5× output) on the whole request.
- Cached input bills at 10% of input; caching is automatic on repeated prefixes.
How to use Gemini 3.1 Pro Preview
Create a free account, generate one key, and point any Gemini-compatible tool at https://gemini.api.apitoken.sale with model ID gemini-3.1-pro-preview — the native /v1beta/models/gemini-3.1-pro-preview:generateContent surface works, authenticated with x-goog-api-key. New accounts include $10 of API usage at official prices — enough to test the model before topping up.
Frequently asked questions
How much does the Gemini 3.1 Pro Preview API cost?
Officially $2 per 1M input tokens and $12 per 1M output tokens, with cached input at $0.20; above 200K input tokens the whole request bills at $4/$18. On apiToken.sale the flat 50% discount applies to every call — $1/$6, or $2/$9 at long-context rates.
What is the model ID for Gemini 3.1 Pro Preview?
gemini-3.1-pro-preview. Use it unchanged with the Google GenAI SDK or any Gemini-compatible tool pointed at https://gemini.api.apitoken.sale, with the key sent as x-goog-api-key.
Gemini 3.1 Pro Preview or 3.6 Flash?
3.6 Flash covers most workloads at a lower token price; route the hardest reasoning and longest-horizon runs to 3.1 Pro Preview. Both run on the same key, balance and endpoint.
Run Gemini 3.1 Pro Preview on the native Gemini API at a flat 50% off — instant key, prepaid balance, card or crypto.