LLM Reference

Gemini 3.5 Flash

Released
2026-05-19
Last refreshed
2026-06-29
Status
Researched 21d ago
ProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionJSON / Tool use

Gemini 3.5 Flash is worth evaluating for coding, rag, and agents when its provider route and context window match the workload.

Use it for

  • Teams evaluating coding, rag, and agents
  • Workloads that can use a 1.05m context window
  • Buyers comparing 4 tracked provider routes

Do not use it for

  • Workloads where another current model has stronger sourced task evidence
Specifications
Released
2026-05-19
Context
1.05m
Max output
65,536
Architecture
Decoder Only
Knowledge cutoff
2025-01
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Weights
Not released
Code
Unknown
Training
Pretrained
Created by

Pioneering artificial intelligence research.

London, United Kingdom
Founded 2014
Website
Pricing
Output / 1M
$9.00
Input / 1M
$1.50

Cheapest of 4 routes · GCP Vertex AI · cache read $0.150

About

Gemini 3.5 Flash is Google DeepMind's generally available Flash model for sustained frontier-level performance on agentic and coding tasks. It supports multimodal inputs, native thinking, tool and function calling, structured outputs, code execution, search grounding, batch processing, and long contexts up to 1M tokens.

Gemini 3.5 Flash is a proprietary model in the Gemini 3.5 family. The structured metadata tracks a 1.05m-token context window, multimodal input, audio, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Google AI Studio, GCP Vertex AI, Vercel AI Gateway, and 1 more, with the cheapest tracked route listed at $1.5 input and $9 output per 1M tokens. Headline tracked benchmarks include MMMU Pro 88.3, SWE-bench Pro 55.1, and Terminal-Bench 76.2.

Top use-case fit: coding, agents, and build tasks

Coding

Q/$ D

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Q/$ D

1 relevant benchmark in the decision map.

Provider price ladder

Compare all 4

Compare API pricing across 4 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MBatch in / outCacheRoute
GCP Vertex AI$1.50$9.00$0.750 / $4.50read $0.150
Serverless
Google AI Studio$1.50$9.00$0.750 / $4.50read $0.150
Serverless
OpenRouter$1.50$9.00--
Serverless
Vercel AI Gateway$1.50$9.00-read $0.150
Serverless

Available via routers & gateways(13)

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt CachingBatch APIAudio

Benchmark peer barsfor Coding

Benchmark scores(13)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
MMMU Pro88.3Vals.ai standardized CoT harness, 4-option, Pass@1, temp=0https://www.vals.ai/benchmarks/mmmu
SWE-bench Pro55.1SWE-bench Pro Public (pass@1)https://deepmind.google/models/model-cards/gemini-3-5-flash/
Terminal-Bench76.2https://deepmind.google/technologies/gemini/flash/
Massive Multi-discipline Multimodal Understanding83.6https://deepmind.google/technologies/gemini/flash/
HumanEval92.0https://o-mega.ai/articles/gemini-3-5-flash-benchmarks-cost-and-guide
ARC-AGI-272.1ARC-AGI-2 (accuracy%)https://benchlm.ai/benchmarks/arcAgi2
Google-Proof Q&A92.2GPQA Diamond (accuracy)https://www.nxcode.io/resources/news/gemini-3-5-flash-complete-guide-benchmarks-pricing-api-2026
Humanity's Last Exam40.2HLE (accuracy)https://deepmind.google/models/model-cards/gemini-3-5-flash/
MCP-Atlas83.6MCP-Atlas (accuracy%)https://benchlm.ai/benchmarks/mcpAtlas
SWE-bench Verified78.0SWE-bench Verified (pass@1)https://techjacksolutions.com/ai-brief/gemini-35-flash-launches-at-io-2026-what-googles-agentic-cod/
Terminal-Bench 2.076.2Terminal-Bench 2.0 (accuracy%)https://benchlm.ai/benchmarks/terminalBench2
CursorBench49.8CursorBench 3.1https://cursor.com/evals
GeneBench-Pro8.1highhttps://cdn.openai.com/pdf/21938268-21af-442f-af93-3b2249afb241/genebench-pro.pdf

Migration checks

No linked migration route is available for this model yet.

API versions

gemini-3.5-flash

Compare Gemini 3.5 Flash with other models

Frequently asked questions

What is the context window of Gemini 3.5 Flash?

Gemini 3.5 Flash has a context window of 1.05m tokens.

What is the max output of Gemini 3.5 Flash?

Gemini 3.5 Flash can generate up to 65,536 output tokens.

How much does Gemini 3.5 Flash cost?

Gemini 3.5 Flash is available at $1.5/1M input tokens through Google AI Studio.

When was Gemini 3.5 Flash released?

Gemini 3.5 Flash was released on 2026-05-19.

Which providers offer Gemini 3.5 Flash?

Gemini 3.5 Flash is available from 4 providers: Google AI Studio, GCP Vertex AI, Vercel AI Gateway, OpenRouter.

What benchmarks has Gemini 3.5 Flash been tested on?

Gemini 3.5 Flash has been evaluated on 13 benchmarks, including MMMU Pro, SWE-bench Pro, Terminal-Bench, Massive Multi-discipline Multimodal Understanding, HumanEval.