Skip to main content

Gemini 3.1 Pro Preview

Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.

Input / output price
$2.00 / $12.00 per 1M
Context
1M tokens
Released
Aug 6, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "google_gemini_ai/gemini-3.1-pro-preview".

Read docs

Providers

5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/gemini-3.1-pro-preview
$2.00/M$12.00/M
Google Gemini AIgoogle_gemini_ai/gemini-3.1-pro-preview
$2.00/M$12.00/M
Inference.netinference_net/gemini-3.1-pro-preview
$2.00/M$12.00/M
Perplexityperplexity/gemini-3.1-pro-preview
$2.00/M$12.00/M
OpenRouteropenrouter/gemini-3.1-pro-preview
$2.00/M$12.00/M

Is a provider down? Perplexity status, OpenRouter status

Pricing

Averaged across 5 providers, in USD per 1M tokens after gateway discounts.

Average input
$2.00 per 1M
Average output
$12.00 per 1M
Average cache read
$0.20 per 1M
Average cache write
$0.13 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$2.00/MConcentrate, Google Gemini AI, Inference.net, Perplexity, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

394tokens/sacross providers

Faster than 91% of the other 596 models on the gateway

Time to first token

Lower is better

14sacross providers

Faster than 3% of the other 153 models on the gateway

Response latency

Lower is better

7.6sacross providers

Faster than 22% of the other 765 models on the gateway

Benchmarks

The Respan Index plus 38 published scores from 16 sources, each linked to where it was published.

43.6/ 100

Respan Index#61 of 176

176 ranked models. The shaded band is this model's 95% interval, 40.1 to 47.4. Mistral Large 4 and GLM-5.2 fall inside it, so the gap is within the margin of error.
Gemini 3.1 Pro Preview by category: Coding 14.7, Agents 53.4, Reasoning 45.8, Knowledge & language 72.5, Human preference 52.5
  1. 61Gemini 3.1 Pro Preview43.6
  2. 60Mistral Large 444.1
  3. 62GLM-5.243.4

Published scores

BenchmarkScore
LiveBench CodingLiveBench76.5%
SWE-bench VerifiedEpoch AI75.6%
WeirdMLHåvard Tveit Ihle72.1%
SWE-Bench ProOpenAI54.2%
GSO Opt@1GSO21.6%
DeepSWE v1.1Datacurve11.7%
MirrorCodeEpoch AI8.9%
Terminal-Bench 4.0Vals AI2.5%

Compare Gemini 3.1 Pro Preview: Gemini 3.1 Pro Preview vs Gemini 3 Pro Preview, Gemini 3.1 Pro Preview vs Claude Sonnet 5.5, Gemini 3.1 Pro Preview vs GPT-5.6 Luna, Gemini 3.1 Pro Preview vs GPT-6.1 Sol, Gemini 3.1 Pro Preview vs Gemini 4 Neon, Gemini 3.1 Pro Preview vs Gemini 4 Carbon

Apps

Use Gemini 3.1 Pro Preview in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Gemini 3.1 Pro Preview FAQ

Short answers, built from the data on this page.

Gemini 3.1 Pro Preview is a model from Google Gemini AI, released on Aug 6, 2026. Gemini 3.1 Pro Preview is Google’s frontier reasoning model, delivering enhanced software engineering performance, improved agentic reliability, and more efficient token usage across complex workflows.

On the Respan gateway, Gemini 3.1 Pro Preview costs $2.00 per 1M input tokens and $12.00 per 1M output tokens on every provider, after gateway discounts.

Gemini 3.1 Pro Preview is available through 5 providers: Concentrate, Google Gemini AI, Inference.net, Perplexity, and OpenRouter.

Gemini 3.1 Pro Preview accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemini-3.1-pro-preview". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Gemini 3.1 Pro Preview scores 43.6 out of 100 on the Respan Index v1.1, ranking #61 of 176 models. By category: Coding 14.7, Agents 53.4, Reasoning 45.8, Knowledge & language 72.5, and Human preference 52.5. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Gemini 3.1 Pro Preview has 38 published benchmark scores, including LiveBench Coding 76.5%, Toolathlon-Verified 61.1%, and GPQA Diamond 94.4%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.