Experiential
ModelsLogsInsights
Find us on Product HuntStar us on GitHubDocsSettings
Sign in
Continue with GoogleContinue with GitHub
or
Models

Gemini 3.7 Flash

gemini-3.7-flashby Geminirecommendednot ZDR
CompareOpen in Playground

Context

1.05M

Max output

66K

Input from

$0.38 / M

Output from

$1.88 / M

Fastest

60 tok/s

Released

Aug 2026

Waterfall

Status
Gemini via Experiential Cloudexperiential——96.4%1.05M66K$0.38≈$1.88≈cache$0.037≈—retainsactivemeasured

Supported parameters

Sampling

Temperature0–2Top-p0–1Stop sequences

Tools & structure

ToolsStructured output

Reasoning

Reasoninglow · medium · highDefaultmedium

Streaming

Streaming

Limits

Max output65,536

Sending an unsupported field? See error reference.

Gemini docs

Quickstart

I want you to route my LLM calls for "gemini-3.7-flash" through the Experiential gateway instead of
calling the provider directly. It speaks the OpenAI Chat Completions API, so this is a base-URL
and key swap. Please:

1. Point the client at https://api-pr-1338.preview.experientiallabs.ai/v1 as the base URL.
2. Authenticate with my Experiential API key from the EXPLABS_API_KEY environment variable. If
   it isn't set, stop and tell me to create one under Settings -> API keys and export it.
3. Use the model id "gemini-3.7-flash" exactly.
4. Update every place my code builds an LLM client for this model to use that base URL and key,
   leaving streaming and tool-calls as they are.
5. Make one test call and show me the reply plus the token usage, so we confirm it runs on my
   Experiential credits.

Tell me which files you changed.

Set EXPLABS_API_KEY to an organization API key before running your agent.

Benchmarks

Release notes
  • MMLU-Propublic leaderboard · Aug 202690.1%
  • SWE-bench Verifiedpublic leaderboard · Aug 202680.8%
  • AIME 2025public leaderboard · Aug 202693.1%
  • LMArena EloLMArena · Aug 20261490
  • Terminal-Benchvendor reported · Aug 202685.8