Gemini

Gemini 3.8 Flash

Long-horizon agents at Flash speed

InputAudioFileImageTextVideoOutputText

API formatOpenAI

Google's Flash model for long-horizon software engineering, autonomous agents, and complex enterprise workflows.

gemini-3.8-flash

Input price$0.65625per million tokens

Output price$3.28125per million tokens

Cache read$0.065625per million tokens

Context window1.0M tokensMaximum context per request

Max output65.5K

BillingPer token

HealthNo dataNo performance samples in the last hour

Model details

Capabilities, benchmarks, and typical use

Gemini 3.8 Flash accepts text, images, video, audio, and PDF documents and produces text. It supports up to 1,048,576 input tokens and 65,536 output tokens, with thinking at low, medium, and high levels, function calling, structured outputs, caching, code execution, computer use, file search, Google Search and Maps grounding, and URL context. Image generation, audio generation, and the Live API are not supported. Feature availability depends on the configured provider channel. Specifications: https://ai.google.dev/gemini-api/docs/models/gemini-3.8-flash . Display reference prices are maintained by the operator; actual pricing comes from new-api.

Million-token input

Accepts up to 1,048,576 input tokens and produces up to 65,536 output tokens.

Multimodal understanding

Analyzes text, images, video, audio, and PDF documents with text output.

Agent tools

Supports thinking, function calling, structured outputs, code execution, search grounding, and caching.