GoogleVerified Active: September 18, 2026
Gemini 3.1 ProAPI Pricing & Specifications
Google's premier reasoning and multimodal intelligence engine with 1M native context and 200K tiered pricing.
đ Core Specifications & Pricing Rates
Standard Input
$2.00 / 1M tokens
Standard Output
$12.00 / 1M tokens
Cached Input
$0.5000 / 1M tokens
Context Window
1M (1,048,576 tokens)
Max Output Tokens
8,192 tokens
Supported Capabilities:â Visionâ Function Calling / Toolsâ JSON Modeâ Deep Reasoning
⥠Tiered Context Threshold: For prompts > 200K tokens, input rate steps up to $4.00/1M, output steps up to $18.00/1M, cached read steps up to $1.00/1M.
đĻ Asynchronous Batch API Supported: Official provider documentation offers a 50% discount on non-streaming 24h batch requests.
Live Workload Cost Estimator: Gemini 3.1 Pro
Adjust token volumes to simulate your exact monthly API bill.
âšī¸ Context Tier Threshold: Standard rate is $2.00 in / $12.00 out (â¤200K). Requests exceeding 200K tokens reprice to $4.00 in / $18.00 out / $1.00 cached per 1M.
Estimated 60% repeated context
Estimated Total Monthly Cost
Compare All Models in Calculatorâ$161.25/ month
$0.00645 per API request(Saves $33.75/mo with caching)
đĄ Estimated Monthly Workload Scenarios
Multimodal Video Analysis
$260.00/mo5,000 video frame and transcript queries (20,000 input, 1,000 output)
5,000 requests âĸ 20000 in / 1000 out
âī¸ Head-to-Head Competitor Comparisons
Gemini 3.1 Pro vs. Claude Sonnet 5
Gemini 3.1 Pro is 33% cheaper on input ($2 vs $3) and 20% cheaper on output ($12 vs $15) with native video reasoning.
1.5x cheaper inputView Claude Sonnet 5 â
đ Historical Price Changes & Updates
2026-06-15
Gemini 3.1 Pro serving as primary production Pro model across Google Cloud.
đ Verified Primary Sources
All pricing, token limits, and capabilities are cross-checked against official provider documentation and live API endpoints.