openrouter

Google: Gemini 3.8 Flash

Unmapped
Context

1M

Input

text, file, image, video, audio

Output

text

Tool calling

Supported

About this model

Gemini 3.8 Flash is Google's most intelligent Flash model, engineered for long-horizon software engineering, autonomous agents, complex enterprise workflows, advanced reasoning, and multimodal understanding. Building on Gemini 3.7 Flash, it delivers substantial improvements across coding, agentic tasks, and critical multi-step reasoning while retaining Flash-level speed and cost efficiency. It supports a 1M-token context window, configurable thinking levels, function calling, computer use, code execution, search grounding, structured outputs, file search, and URL context.

Input modalities

text

Accepted as model input

file

Accepted as model input

image

Accepted as model input

video

Accepted as model input

audio

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.

Coding

DeepSWE v1.173.7
Terminal-bench 2.189.4

Knowledge Work

GDPVal-AA v21545

Professional

Vals Finance Agent v261.4
Harvey's Legal Agent Benchmark10

Agentic

Terminal-bench 4.019.1
OSWorld-2.059

Document Understanding

GDP.PDF35

Reasoning

CharXiv Reasoning86.2

Video Understanding

LVBench (agentic)87.8
LVBench (static)87.1

Multidisciplinary

HLE-Verified54.9

Scientific Research

BioMysteryBench88.8
LABBench286.2

Bioinformatics

BioMysteryBench Human Difficult56.5

API Guide

Refer Documentation
  1. 1

    Generate your access token

    Use your API key to generate the JWT access token required by the Models API.

  2. 2

    Add the JWT token

    Copy the generated JWT token and replace JWT_TOKEN in the example below.

  3. 3

    Check your credits

    If your balance is too low, before calling the model.

  4. 4

    Run the API example

    Choose your preferred language, copy the example, and send your first model request.

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