Google

Gemini 3.5 Flash

Fast Gemini model balancing multimodal reasoning, tool use, and cost

google/gemini-3.5-flash

Context

1M

Output

65.5K

Released

2026-05-19

Knowledge cutoff

2025-01

Types

InputTextImageAudioVideoPDF
OutputText

Reasoning

Supported

Tool use

Supported

Structured output

Supported

Attachments

Supported

Open weights

—

Provider pricing

Kilo Gateway
InTextImageAudioVideoPDF
OutText
Price
$0.75 / $4.50
Context
1M
Status
Stable
CommandCode
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Eden AI
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
FastRouter
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Impossibl
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Merge Gateway
InTextImageAudioPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
NanoGPT
InTextImageAudioVideo
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
NEAR AI Cloud
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Ofox
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
OpenRouter
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
OrcaRouter
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Prime Inference
InTextImageAudioVideo
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Tempr Gateway
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Vercel AI Gateway
InTextImagePDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
ZenMux
InTextImageAudioVideoPDF
OutText
Price
$1.50 / $9.00
Context
1M
Status
Stable
Poe
InTextImageVideo
OutText
Price
$1.52 / $9.09
Context
1M
Status
Stable

Benchmarks

  • Terminal-Bench

    76.2 · success rate

  • SWE-Bench Pro

    55.1 · resolve rate

  • MCP Atlas

    83.6 · success rate

  • Toolathlon

    56.5 · success rate

  • OSWorld-Verified

    78.4 · success rate

  • MMMU Pro

    83.6 · accuracy

  • CharXiv Reasoning

    84.2 · accuracy

  • Humanity's Last Exam

    40.2 · accuracy

  • ARC-AGI-2

    72.1 · accuracy

  • GDPval-AA

    1656 · Elo

From the same lab