LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Gemini 3.1 Pro Preview

google·google/gemini-3.1-pro-preview·BETA·Closed·gemini-pro series
Reasoning-first Gemini preview for agentic coding and complex problem solving

Specs & pricing

Input / output per 1M tokens
Official price·Google
$2.00 / $12.00
Blended $4.50 · Cache read $0.20
Lowest paid·Infer by Flow7Gateway
$1.18 / $5.30
Blended $2.21 · 2.5× spread
Context
1,048,576
Output limit
65,536
Knowledge cutoff
2025-01
Released / updated
2026-02-19 / 2026-02-19
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImageVideoAudioPDF

Gemini 3.1 Pro Preview by google is offered by 46 providers on this page. Public prices are shown for 45 of them. Its official list price is $2.00 per 1M input tokens and $12.00 per 1M output tokens. The lowest paid channel is Infer by Flow7 at $1.18 / $5.30 per 1M, about 2.0× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Median output speed is 137 tokens per second, with 23.66s to the first token.

The context window is 1,048,576 tokens at the reference host, but hosts report different limits, from 199,999 to 1,048,576, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, Video, Audio, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed137 tok/s
TTFT23.66 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 46 providers45 with public prices

  • ProviderInput / Output
  • Infer by Flow7Gateway
    infer/gemini-3.1-pro-preview:low-cost
    $1.18 / $5.30
    Cache read $0.12Context 199,999 ⚠Output limit 65,536
  • KenariGateway
    gemini-3-1-pro
    $1.20 / $7.14
    Cache read $0.12Context 1,048,576Output limit 65,536
  • VertexOfficialCloud
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536beta
  • GoogleOfficialFirst-party
    gemini-pro-latest
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
  • GoogleOfficialFirst-party
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
  • Perplexity AgentGateway
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
  • CrossModelGateway
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
  • LLM GatewayGateway
    $2.00 / $12.00
    tiered >200K: $4.00
    Cache read $0.20Context 1,048,576Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Infer by Flow7
infer/gemini-3.1-pro-preview:low-cost
Gateway$1.18$5.30$0.12$1.33199,999 ⚠65,536
Kenari
gemini-3-1-pro
Gateway$1.20$7.14$0.12$0.221,048,57665,536
VertexOfficialCloud$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536beta
GoogleOfficial
gemini-pro-latest
First-party$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536
GoogleOfficialFirst-party$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536
Perplexity AgentGateway$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536
CrossModelGateway$2.00
tiered >200K: $4.00
$12.00$0.20$2.001,048,57665,536
LLM GatewayGateway$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536
LLM GatewayGateway$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536
LLM GatewayGateway$2.00
tiered >200K: $4.00
$12.00$0.20—1,048,57665,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = mediumeffort = higheffort = xhigheffort = maxeffort = noneeffort = minimal

Interleaved thinking (reasoning between tool calls) is declared by 3 of 46 providers.

6 / 46 providers expose no reasoning control (reasoning_options: []).

Audio token pricing6 of 46 providers

ProviderAudio inAudio out
Databricks$2.001.0×—
OpenRouter$2.001.0×—
Eden AI$2.001.0×—
Eden AI$2.001.0×—
Ofox$2.001.0×—
OrcaRouter$2.001.0×—

Audio tokens are priced on a separate scale from text tokens, so these are not comparable with the text prices above. The multiplier compares each price with the same provider's text price for the same direction.

Experimental modes1 items

ModeProviderInputOutputCache readCache write
fastDatabricks$3.60$21.60$0.36—

Your usage cost

Common scenarios
1Infer by Flow7$373.80
2Kenari$467.40
3Vertex · Official$784.00
4Google · Official$784.00
5Google · Official$784.00
6Perplexity Agent$784.00
Switch to Infer by Flow7 to save $410.20/mo (52%)
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$12.00$02026-08-052026-11-15
2026-11-15Input list $2.00Output list $12.00Min blended $2.21

Benchmark18 items

NameConditionsScoreMetricSource
SWE-Bench Pro—54.2resolve rateSource ↗
Terminal-Benchharness: Terminus-2 · v2.170.3success rateSource ↗
SWE-Bench Prodataset: public46.1resolve rateSource ↗
SWE-Atlas Codebase QnAharness: Mini-SWE-Agent13.5scoreSource ↗
SWE-Atlas Refactoringharness: Gemini CLI33.81scoreSource ↗
SWE-Atlas Test Writingharness: Mini-SWE-Agent29.84scoreSource ↗
Artificial Analysis Coding Agent Indexharness: Gemini CLI · variant: high43average pass@1Source ↗
SWE-Atlas Codebase QnAharness: Gemini CLI · variant: high45.6pass@1Source ↗
SWE-Bench Proharness: Gemini CLI · variant: high · dataset: hard-aa15.1pass@1Source ↗
Terminal-Benchharness: Gemini CLI · variant: high · v2.168.3pass@1Source ↗
GPQA Diamond—94.3accuracySource ↗
Humanity's Last Examdataset: full set, text + MM44.4accuracySource ↗
ARC-AGI-2—77.1accuracySource ↗
MMMU Provariant: no tools80.5accuracySource ↗
MCP Atlas—78.2success rateSource ↗
OSWorld-Verified—76.2success rateSource ↗
CharXiv Reasoningvariant: no tools83.3accuracySource ↗
GDPval-AA—1314EloSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Artificial Analysis evaluations23 items

GPQA Diamond94.1%
Humanity's Last Exam47.0%
HLE-Diamond31.4%
MMMU-Pro82.4%
CritPt17.7%
SciCode58.7%
Terminal-Bench Hard53.8%
Terminal-Bench 2.173.8%
Terminal-Bench 4.04.0%
τ²-Bench Telecom95.6%
τ³-Bench Banking21.4%
AutomationBench-AA35.4%
APEX-Agents-AA32.0%
AA-AnalystAgent41.3%
EnterpriseOps-Gym-AA42.2%
ITBench-AA30.3%
AA-Briefcase457
GDPval-AA799
GDP.pdf17.8%
AA-LCR82.0%
MLCR-AA11.1%
IFBench77.1%
Harvey LAB-AA0.0%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Gemini Pro Latestsame series—Gemini 3.5 Live Translate Previewsame series$3.50 / $21.00Nano Banana Prosame series$2.00 / $12.00GLM-5.3cheaper alternative$1.40 / $4.40GLM-5.3-Flashcheaper alternative$0.15 / $0.50DeepSeek V4.1 Flash 1017cheaper alternative$0.15 / $0.60GLM-5.2cheaper alternative$1.40 / $4.40Gemini 3.1 Flash Lite Previewsame lab$0.25 / $1.50Gemini 3.1 Pro Preview Custom Toolssame lab$2.00 / $12.00
Data partly from models.dev (MIT) · Google official docs ↗