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
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
6 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/gemini-3.5-flash | $1.50/M | $9.00/M |
DeepInfra deepinfra/gemini-3.5-flash | $1.50/M | $9.00/M |
Google Gemini AI google_gemini_ai/gemini-3.5-flash | $1.50/M | $9.00/M |
Inference.net inference_net/gemini-3.5-flash | $1.50/M | $9.00/M |
Perplexity perplexity/gemini-3.5-flash | $1.50/M | $9.00/M |
OpenRouter openrouter/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.
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 better105tokens/sacross providers
Time to first token
Lower is better2.5sacross providers
Response latency
Lower is better9.1sacross providers
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
- 58Gemini 3.5 Flash44.3
- 57Qwen3.8-Flash-Next44.6
- 59Mistral Large 444.1
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| SWE-bench VerifiedEpoch AI | 79.3% | Epoch AI | Oct 5, 2026 |
| LiveBench CodingLiveBench | 78.2% | LiveBench | Oct 5, 2026 |
| Terminal-bench 2.1Google | 76.2% | May 19, 2026 | |
| WeirdMLHåvard Tveit Ihle | 62.6% | Håvard Tveit Ihle | Oct 5, 2026 |
| SWE-Bench Pro (Public)Google | 55.1% | May 19, 2026 | |
| DeepSWE v1.1Datacurve | 36.1% | Datacurve | Oct 5, 2026 |
| Terminal-Bench 4.0Vals AI | 6.1% | Vals AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MCP AtlasGoogle | 83.6% | May 19, 2026 | |
| OSWorld-VerifiedGoogle | 78.4% | May 19, 2026 | |
| Toolathlon-VerifiedHKUST | 67.3% | HKUST | Jun 30, 2026 |
| LiveBench Agentic CodingLiveBench | 49% | LiveBench | Oct 5, 2026 |
| APEX-AgentsMercor | 27.5% | Mercor | Oct 5, 2026 |
| Vending-Bench 2Andon Labs | 5396.42 · #33 of 67 | Andon Labs | Oct 5, 2026 |
| GDPVal-AAGoogle | 1656 Elo | May 19, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 92.8% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 82% | LiveBench | Oct 5, 2026 |
| SimpleBenchSimpleBench | 76.7% | SimpleBench | May 20, 2026 |
| ARC-AGI-2Google | 72.1% | May 19, 2026 | |
| LiveBench Data AnalysisLiveBench | 64.9% | LiveBench | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 45% | Epoch AI | Oct 28, 2026 |
| Humanity's Last Exam (full set, text + MM)Google | 40.2% | May 19, 2026 | |
| Mystery Game PuzzlesEpoch AI | 32% | Epoch AI | Oct 5, 2026 |
| EBR-benchEpoch AI | 4.8% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| OTIS Mock AIME 2024-2025Epoch AI | 95.6% | Epoch AI | Oct 5, 2026 |
| AIME 2026MathArena | 95% | MathArena | Sep 17, 2026 |
| LiveBench MathematicsLiveBench | 88.2% | LiveBench | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 62.8% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 26.8% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 84.6% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 75.6% | LiveBench | Oct 5, 2026 |
| SimpleQA VerifiedEpoch AI | 66.2% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena WebDevLMArena | 1500 Elo · #64 of 123 | LMArena | Nov 18, 2026 |
| LMArena EloLMArena | 1478 Elo · #30 of 187 | LMArena | Nov 18, 2026 |
| LMArena VisionLMArena | 1282 Elo · #20 of 89 | LMArena | Nov 9, 2026 |
How Gemini compares: Claude vs Gemini, Gemini vs GPT, Gemini vs Grok
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.