Google · Released Feb 25, 2026

Gemini 3.1 Pro Preview Custom Tools

Gemini 3.1 Pro Preview Custom Tools is a variant of Gemini 3.1 Pro that improves tool selection behavior by preventing overuse of a general bash tool when more efficient third-party...

ReasoningVision
  • Top 35%SWE-bench Verified
Released
Feb 25 2026
Context window
1M 66K out
Input / 1M tokens
$2.00
Output / 1M tokens
$12.00

Where to run it

12 providers compared

Cheapest: Google AI Studio, NanoGPT, Kilo Gateway +7 more at $2.00 / $12.00 per 1M input / output tokens — 40% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
Google AI Studio $2.00 $12.00 $0.201M66K100%24h Cheapest
NanoGPT $2.00 $12.00 $0.201M66K— Cheapest
Kilo Gateway $2.00 $12.00 $0.201M66K— Cheapest
AIHubMix $2.00 $12.00 $0.201M66K— Cheapest
Vertex $2.00 $12.00 $0.201M66K— Cheapest
Google $2.00 $12.00 $0.201M66K— Cheapest
Neon $2.00 $12.00 $0.201M66K— Cheapest
Tempr Gateway $2.00 $12.00 $0.201M66K— Cheapest
Merge Gateway $2.00 $12.00 $0.201M66K— Cheapest
Eden AI $2.00 $12.00 $0.201M66K— Cheapest
AI/ML API $2.75 $16.50 $0.281.05M66K— +38%
OrcaRouter $4.00 $18.00 $0.401M66K— +67%

Value

Price vs. performance

6 models score higher for the same price or lesson SWE-bench Verified, e.g. Gemini 3.5 Flash.
31.0%48.5%66.0%83.5% $0.01$0.10$1.00$10.00$100.00 DeepSeek V4 Pro 0813 (DeepSeek) — 77.6% · $0.66/1M in GLM 5.2 (Z.ai) — 78.7% · $0.034/1M in Qwen3.7 Max (Qwen) — 77.3% · $1.48/1M in DeepSeek V4 Pro 0423 (DeepSeek) — 77.6% · $0.44/1M in Kimi K2.6 (Moonshot AI) — 76.6% · $0.65/1M in Claude Opus 4.7 (Anthropic) — 83.5% · $5.00/1M in GLM 5.1 (Z.ai) — 74.2% · $1.40/1M in Qwen3.6 Plus (Qwen) — 57.9% · $0.33/1M in GPT-5.4 (OpenAI) — 76.9% · $2.50/1M in GPT-5.3-Codex (OpenAI) — 74.8% · $1.75/1M in Claude Sonnet 4.6 (Anthropic) — 75.2% · $3.00/1M in GLM 5 (Z.ai) — 72.1% · $1.00/1M in Claude Opus 4.6 (Anthropic) — 78.7% · $5.00/1M in Kimi K2.5 (Moonshot AI) — 73.8% · $0.50/1M in GPT-5.2 (OpenAI) — 73.8% · $1.75/1M in Claude Opus 4.5 (Anthropic) — 76.6% · $5.00/1M in GPT-5.1 (OpenAI) — 68.0% · $1.25/1M in Claude Sonnet 4.5 (Anthropic) — 71.3% · $3.00/1M in GPT-5 (OpenAI) — 73.6% · $1.25/1M in GPT-5 Mini (OpenAI) — 64.7% · $0.25/1M in Claude Opus 4.1 (Anthropic) — 73.4% · $15.00/1M in o3 (OpenAI) — 62.3% · $2.00/1M in GPT-4.1 (OpenAI) — 48.5% · $2.00/1M in GPT-4o (2024-11-20) (OpenAI) — 31.0% · $2.50/1M in GPT-4o (2024-08-06) (OpenAI) — 31.0% · $2.50/1M in GPT-4o (OpenAI) — 31.0% · $2.50/1M in GPT-4o (2024-05-13) (OpenAI) — 31.0% · $5.00/1M in Gemini 3.5 Flash (Google) — 79.3% · $1.50/1M in Gemini 3 Flash Preview (Google) — 75.4% · $0.50/1M in Gemini 2.5 Pro (Google) — 57.6% · $1.25/1M in Gemini 2.5 Pro Preview 06-05 (Google) — 57.6% · $1.25/1M in Gemini 3.1 Pro Preview Custom Tools (Google) — 75.6% · $2.00/1M in Gemini 3.1 Pro Preview Custom Tools

Gemini 3.1 Pro Preview Custom Tools Other Google Other labs Value frontier · SWE-bench Verified vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

2 benchmark scores

BenchmarkScoreRankLeader
SWE-bench VerifiedSoftware engineering · Real GitHub issues fixed in Python repos 75.6% #11of 32 Claude Opus 4.783.5%
Vending-Bench 2Agents & computer use · Run a simulated vending business for a year (final balance) $3,774 #37of 61 GPT-6 Astra$15,515

Specs

Details

Model ID
google/gemini-3.1-pro-preview-customtools
Developer
Google
Release date
Feb 25, 2026 ·
Context window
1,048,576 tokens
Max output
65,536 tokens
API price
$2.00 / $12.00 per 1M input / output tokens
Providers
12
Input types
text, audio, image, video, file
Reasoning
Yes
Tool calling
Yes
Open weights
No
Free tier
No

Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.