New Sign up free, 10 calls on us. Up to $1, no card needed.

Gemini 3.1 Pro

Released 2026-02-19

chatVisionCodeTool callingReasoningimagePrompt caching

Gemini 3.1 Pro (preview) is Google's refined iteration of the Gemini 3 Pro line, and its model page highlights better thinking, improved token efficiency, and a more grounded, factually consistent experience; the DeepMind model card calls it Google's most advanced model for complex tasks.

Input
text image video audio $2/M
Output
text $12/M
Audio input
$4/M
Cache read
$0.2/M
Context
1M
vs GPT-4o
~60% cheaper
Knowledge cutoff
2025-01

Benchmarks

Above averageNo peer higher28 / 636 / 63
Gemini 3.1 Pro other models measured peer average no peer scored higher
SWE-Bench Pro
54.2%
WenetSpeech test-net (CER)
9.52%
GeneBench Pro
3.1%
OSWorld-Verified
64%
GDPval-AA v2 Elo · 642-1861
962.3
GPQA Diamond
94.3%
BrowseComp
85.9%
BabyVision
55.9%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 60 comparable models

Input$2/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$12/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.2/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 1,048,576
Max output (vendor spec) 65,536
Knowledge cutoff 2025-01

Prompt caching

How it caches automatic + explicit
Min prefix 4,096

Thinking

Vendor control thinkingLevel
Accepted values low · medium · high (minimal is not supported)
Default high applied when the request sets nothing
Can be turned off No
Thinking behaviour The only Gemini 3 tier with no minimal level, and Google states outright that thinking cannot be disabled for 3.1 Pro; thinking tokens bill as output tokens and thought signatures must be returned for function calling.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image + video + audio → text
  • 1,048,576-token input
  • Search/Maps grounding and code execution supported
  • image generation NOT supported despite gateway capability tag

per Google official docs ↗

One prompt, measured through the gateway

PROMPT Explain to a CFO, in exactly three sentences, why our LLM bill doubled after we enabled reasoning. CHECK exactly 3 sentences

Gemini 3.1 Pro passed · 3 sentences

Enabling the AI's reasoning capability forces the model to generate a massive amount of invisible "thought" tokens to logically work through complex problems before delivering its final answer. Because our vendor's pricing model charges us for total computational effort—including all of these hidden background tokens—our billable usage effectively doubled per request. While this directly increases our upfront software expenses, we are trading this higher compute cost for a drastic reduction in expensive downstream errors and manual human rework.

out 1412 tok (+1318 thinking) latency 12.7 s

Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.

PROMPT This function is supposed to return the longest run of consecutive equal items, but callers report it is off by one on single-element inputs and misses runs that end at the last index. Fix it and explain the bug in one paragraph. CHECK fix passes tests

Gemini 3.1 Pro passed · 8/8 cases

```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The original function initializes `cur` and `best` to 0 and only increments `cur` when two adjacent elements are equal. This effectively counts the number of *matching consecutive pairs* (or transitions) rather than the actual number of *elements* in the run, causing all calculated lengths to be […]

out 4092 tok (+3933 thinking) latency 31.1 s

Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.

PROMPT Extract a JSON object with fields {company, quarter, revenue_usd_m, growth_pct, guidance} from this text. Use null for anything not stated; add no other fields. CHECK valid JSON, schema exact

Gemini 3.1 Pro passed · 5/5 fields, guidance "withheld"

```json { "company": "Meridian Robotics", "quarter": "September", "revenue_usd_m": 412, "growth_pct": "11 and change", "guidance": "withheld" } ```

out 1806 tok (+1743 thinking) latency 14.1 s

Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.

PROMPT Write a 120-word product announcement for an API gateway feature that caches prompts across providers. Forbidden words: "seamless", "unlock", "game-changer", "revolutionize", "empower". Exactly one sentence must be a question. CHECK 120 words, 0 banned words

Gemini 3.1 Pro passed · 120 words, 0 banned, 1 question

We are excited to announce universal prompt caching for our API gateway. Handling multiple AI models usually means paying for redundant prompts across various platforms. Why should you pay twice for identical queries? Now, our gateway automatically stores and retrieves exact prompt matches regardless of the backend provider you select. This reduces latency and significantly cuts your inference costs. Whether you route a request to one service today or a different vendor tomorrow, our intelligent caching layer intercepts the call and serves the saved response instantly. Developers can configure cache expiration times and specify matching criteria directly in the control panel. Experience faster response times and optimized resource usage starting today. Upgrade your software client to version two right now.

out 4060 tok (+3929 thinking) latency 28.6 s

Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.

Use Gemini 3.1 Pro in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="gemini-3.1-pro-preview",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Gemini 3.1 Pro

  • Google names its best uses as agentic performance, advanced coding, long-context and multimodal understanding, algorithmic development, tool-based agents, and multi-step execution that demands precise tool usage.
  • It accepts text, image, video, audio, and PDF input in a 1,048,576-token context window with 65,536 output tokens, and supports function calling, structured outputs, code execution, Search and Maps grounding, URL context, context caching, and the Batch API; computer use and the Live API are not supported.
  • Thinking is controlled by thinking_level, and the Pro line accepts only low, medium, and high, with none of the minimal setting the Flash models offer, defaulting to high; reasoning cannot be disabled, so budget for thinking tokens billed at the output rate on every request, and return the thought signatures Gemini 3 issues if you want multi-turn continuity.
  • A gemini-3.1-pro-preview-customtools variant prioritizes developer-defined tools, and the earlier gemini-3-pro-preview identifier has been retired in favour of this one.
  • Synthorai fronts it with an OpenAI-compatible chat completions API.

FAQ

Is the Gemini 3.1 Pro API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $2/M input tokens, that credit alone covers roughly 62 requests of ~8K tokens against Gemini 3.1 Pro.

What is Gemini 3.1 Pro best at?

Better thinking and improved token efficiency; optimized for software engineering and agents; custom-tools variant prioritizes developer-defined tools. See the About section for the full picture from the vendor's own release notes.

How much does Gemini 3.1 Pro cost?

Gemini 3.1 Pro costs $2 per million input tokens and $12 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.2/M.

Does Gemini 3.1 Pro support prompt caching?

Yes: automatic caching is on by default, with an explicit mode for guaranteed savings. Cached input tokens bill at $0.2/M vs $2/M uncached; prompts need a 4,096-token stable prefix to cache. Prompt caching guide →

How do I get access to Gemini 3.1 Pro?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="gemini-3.1-pro-preview", and you're done. One API key covers every model on the gateway.

What is Gemini 3.1 Pro's knowledge cutoff?

Gemini 3.1 Pro's knowledge cutoff is 2025-01, per the vendor's official documentation (as of 2026-07-09).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →