Gemini 3.1 Pro Preview API pricing
Google Gemini charges $2 per million input tokens and $12 per million output tokens for Gemini 3.1 Pro Preview (gemini-3.1-pro-preview), and $0.2 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.008, or $0.004 through the batch API.
Gemini 3.1 Pro Preview price per million tokens
| Token type | Standard | Batch API |
|---|---|---|
| Input | $2 | $1 |
| Cached input | $0.2 | $0.2 |
| Output | $12 | $6 |
API model id: gemini-3.1-pro-preview. Gemini 3.1 Pro Preview supports a 1.05M-token context window, up to 65.5K output tokens, image input, tool calling and reasoning.
What Gemini 3.1 Pro Preview costs per request
| Request | 1 request | 1,000 requests | 1M requests |
|---|---|---|---|
| Short chat message (300 in, 200 out) | $0.003 | $3.00 | $3,000.00 |
| Typical request (1K in, 500 out) | $0.008 | $8.00 | $8,000.00 |
| Long document summary (20K in, 1K out) | $0.052 | $52.00 | $52,000.00 |
| Coding agent step (50K in, 2K out) | $0.12 | $124.00 | $124,000.00 |
At standard rates. A token is about 4 characters of English text, so 1,000 tokens is roughly 750 words. Google Gemini counts tokens with its own tokenizer, so the same text can be a different number of tokens.
How Gemini 3.1 Pro Preview compares
- For a typical request, Gemini 3.1 Pro Preview is cheaper than 23% of the other models on apicost.app.
- GPT-5.6 Terra from OpenAI costs $2 input and $12 output per million tokens, so a typical request is $0.008: about the same price as Gemini 3.1 Pro Preview.
- Claude Sonnet 5 from Anthropic costs $2 input and $10 output per million tokens, so a typical request is $0.007: 1.1× cheaper than Gemini 3.1 Pro Preview.
- DeepSeek V4 Pro from DeepSeek costs $1.32 input and $3.96 output per million tokens, so a typical request is $0.0033: 2.4× cheaper than Gemini 3.1 Pro Preview.
Gemini 3.1 Pro Preview price history
Gemini 3.1 Pro Preview has cost $2 per million input tokens and $12 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Every LLM API price increase, cut, new and retired model, dated: LLM API price changes.
Models with a similar price
| Model | Provider | Input / 1M | Cached input / 1M | Output / 1M | Typical request |
|---|---|---|---|---|---|
| GPT-6 Sol | OpenAI | $2 | $0.2 | $10 | $0.007 |
| GPT-6.1 Sol | OpenAI | $2 | $0.1 | $10 | $0.007 |
| Claude Sonnet 5 | Anthropic | $2 | $0.2 | $10 | $0.007 |
| Claude Sonnet 5.5 | Anthropic | $2 | $0.1 | $10 | $0.007 |
| Gemini 4 Argon | Google Gemini | $2 | $0.1 | $10 | $0.007 |
| GPT-4o | OpenAI | $2.5 | $1.25 | $10 | $0.0075 |
| GPT-5.6 Terra | OpenAI | $2 | $0.2 | $12 | $0.008 |
| GPT-5.2 | OpenAI | $1.75 | $0.175 | $14 | $0.00875 |
Other Google Gemini models
- Gemini 2.5 Flash $0.3 / $2.5
- Gemini 2.5 Flash Lite $0.1 / $0.4
- Gemini 2.5 Pro $1.25 / $10
- Gemini 3 Flash Preview $0.5 / $3
- Gemini 3.1 Flash Lite $0.25 / $1.5
- Gemini 3.5 Flash $1.5 / $9
- Gemini 3.5 Flash Lite $0.3 / $2.5
- Gemini 3.6 Flash $0.75 / $3.75
- Gemini 3.7 Flash $0.75 / $3.75
- Gemini 3.8 Flash $0.75 / $3.75
- Gemini 4 Argon $2 / $10
- Gemini 4 Carbon $2 / $10
- Gemini 4 Hydrogen $1.5 / $7.5
- Gemini Omni 1.1 Flash $1.5 / $9
- Gemini Omni 1.2 Flash $1.5 / $9
Every Google Gemini model side by side, with batch, caching and long-context prices: Gemini API pricing (Google). Ways to pay less: batch API, prompt caching, the cheapest models.
Questions and answers
How much does the Gemini 3.1 Pro Preview API cost?
Google Gemini charges $2 per million input tokens and $12 per million output tokens for Gemini 3.1 Pro Preview (gemini-3.1-pro-preview), and $0.2 per million cached input tokens. A typical request of 1,000 input and 500 output tokens costs $0.008, or $0.004 through the batch API.
Has the Gemini 3.1 Pro Preview API price changed?
No. Gemini 3.1 Pro Preview has cost $2 per million input tokens and $12 per million output tokens since apicost.app started tracking prices on October 22, 2026.
Is there a cheaper way to use Gemini 3.1 Pro Preview?
Yes. The Google Gemini batch API runs requests within 24 hours for $1 per million input tokens and $6 per million output tokens. Prompt caching lowers the price of repeated input to $0.2 per million tokens.
What is the context window of Gemini 3.1 Pro Preview?
Gemini 3.1 Pro Preview accepts up to 1,048,576 input tokens, roughly 786,000 words of English, and writes up to 65,536 output tokens per response. Filling the whole context window once costs $2.10 in input tokens.
Is Gemini 3.1 Pro Preview cheaper than GPT-5.6 Terra?
They cost about the same. GPT-5.6 Terra from OpenAI costs $2 input and $12 output per million tokens, so a typical request is $0.008: about the same price as Gemini 3.1 Pro Preview.
Source: Google Gemini pricing, via the LiteLLM price list.