openrouter

Google: Gemini 3.7 Flash

google/gemini-3.7-flash
Context

1M

Input

text, file, image, audio, video

Output

text

Tool calling

Supported

About this model

Gemini 3.7 Flash is a frontier-class Google Flash model focused on high-performance reasoning, coding, multimodal understanding, tool use, and agentic execution with the latency and cost characteristics of the Flash family.

Input modalities

text

Accepted as model input

file

Accepted as model input

image

Accepted as model input

audio

Accepted as model input

video

Accepted as model input

Providers

Available routing options for this model through OneInfer.

Available

Input tokens

$0.750 / 1M tokens

Output tokens

$3.750 / 1M tokens

Routing

OneInfer optimized

Pricing

Current OneInfer pricing for this model.

UsagePrice
Input tokens$0.750 / 1M tokens
Output tokens$3.750 / 1M tokens
Cached input tokens$0.075 / 1M tokens

Performance

Published evaluation results associated with this model.

Overall Intelligence

Artificial Analysis Intelligence Index56

Coding

FrontierCode 1.1 Main43.6
DeepSWE v1.165.3
Code Arena (Elo)1588
Terminal-bench 2.185.8

Agentic

Terminal-bench 3.014.9
AutomationBench30.4
OSWorld-2.047.9
Agent's Last Exam26.3

Knowledge Work

GDPVal-AA v2 (Elo)1525
Harvey LAB-AA90.7
GDP.pdf34

Multimodal

CharXiv Reasoning (No tools)84.5
CharXiv Reasoning (With tools)88.7
LVBench85.4

Long Context

GDM-MRCR v2 (8-needle) 128K97

Reasoning

HLE-Verified53.6

Scientific Reasoning

BioMysteryBench (Human solvable)87.1
BioMysteryBench (Human difficult)43.5
LABBench282.1

API example

curl https://api.oneinfer.ai/v1/ula/chat/completions \
  -H "Authorization: Bearer $JWT_TOKEN" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/gemini-3.7-flash",
    "messages": [
      { "role": "user", "content": "Hello!" }
    ]
  }'