Skip to main content

Gemini 3.5 Flash

Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.

Input / output price
$1.50 / $9.00 per 1M
Context
1M tokens
Released
May 19, 2026
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "google_gemini_ai/gemini-3.5-flash".

Read docs

Providers

6 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Concentrateconcentrate/gemini-3.5-flash
$1.50/M$9.00/M
DeepInfradeepinfra/gemini-3.5-flash
$1.50/M$9.00/M
Google Gemini AIgoogle_gemini_ai/gemini-3.5-flash
$1.50/M$9.00/M
Inference.netinference_net/gemini-3.5-flash
$1.50/M$9.00/M
Perplexityperplexity/gemini-3.5-flash
$1.50/M$9.00/M

Is a provider down? Perplexity status, OpenRouter status

Pricing

Averaged across 6 providers, in USD per 1M tokens after gateway discounts.

Average input
$1.50 per 1M
Average output
$9.00 per 1M
Average cache read
$0.15 per 1M
Average cache write
$0.02 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$1.50/MConcentrate, DeepInfra, Google Gemini AI, Inference.net, Perplexity, and OpenRouter

Throughput and latency

30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.

Output speed

Higher is better

105tokens/sacross providers

Faster than 79% of the other 588 models on the gateway

Time to first token

Lower is better

2.5sacross providers

Faster than 37% of the other 153 models on the gateway

Response latency

Lower is better

9.1sacross providers

Faster than 19% of the other 747 models on the gateway

Benchmarks

The Respan Index plus 36 published scores from 12 sources, each linked to where it was published.

44.3/ 100

Respan Index#58 of 175

175 ranked models. The shaded band is this model's 95% interval, 39.6 to 49.5. Qwen3.8-Flash-Next and Mistral Large 4 fall inside it, so the gap is within the margin of error.
Gemini 3.5 Flash by category: Coding 19.0, Agents 49.7, Reasoning 49.9, Knowledge & language 65.6, Human preference 54.0
  1. 58Gemini 3.5 Flash44.3
  2. 57Qwen3.8-Flash-Next44.6
  3. 59Mistral Large 444.1

Published scores

BenchmarkScore
SWE-bench VerifiedEpoch AI79.3%
LiveBench CodingLiveBench78.2%
Terminal-bench 2.1Google76.2%
WeirdMLHåvard Tveit Ihle62.6%
SWE-Bench Pro (Public)Google55.1%
DeepSWE v1.1Datacurve36.1%
Terminal-Bench 4.0Vals AI6.1%

Compare Gemini 3.5 Flash: Gemini 3.5 Flash vs Gemini 2.5 Flash, Gemini 3.5 Flash vs Gemini 3.6 Flash, Gemini 3.5 Flash vs Claude Haiku 4.5, Gemini 3.5 Flash vs Gemini 4 Argon, Gemini 3.5 Flash vs Gemini 4 Neon, Gemini 3.5 Flash vs Gemini 4 Carbon

Apps

Use Gemini 3.5 Flash in the tools you already run. Each guide points the app at the Respan gateway.

Setup guides for more apps are in the integration docs.

Gemini 3.5 Flash FAQ

Short answers, built from the data on this page.

Gemini 3.5 Flash is a model from Google Gemini AI, released on May 19, 2026. Gemini 3.5 Flash is Google's high-efficiency multimodal model, bringing near-Pro level coding and reasoning at Flash-tier cost and speed. It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs. Defaults to medium thinking effort for faster and more cost-efficient responses, with full support for thinking levels (minimal, low, medium, high) for fine-grained cost/performance trade-offs.

On the Respan gateway, Gemini 3.5 Flash costs $1.50 per 1M input tokens and $9.00 per 1M output tokens on every provider, after gateway discounts.

Gemini 3.5 Flash is available through 6 providers: Concentrate, DeepInfra, Google Gemini AI, Inference.net, Perplexity, and OpenRouter.

Gemini 3.5 Flash accepts up to 1M tokens of context on its largest provider route.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "google_gemini_ai/gemini-3.5-flash". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Gemini 3.5 Flash scores 44.3 out of 100 on the Respan Index v1.1, ranking #58 of 175 models. By category: Coding 19.0, Agents 49.7, Reasoning 49.9, Knowledge & language 65.6, and Human preference 54.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Gemini 3.5 Flash has 36 published benchmark scores, including SWE-bench Verified 79.3%, MCP Atlas 83.6%, and GPQA Diamond 92.8%. Each score links to where it was published; the data is collected by Respan.

Certified where it counts.

Built to meet the security and privacy standards that enterprise and healthcare teams require.

ISO 27001

The internationally recognized standard for information security management.

SOC 2

Secure, compliant management of your data across all of our systems.

GDPR

Operated under GDPR, the world's strictest standard for data privacy.

HIPAA

HIPAA compliant, with a BAA available for healthcare teams.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.