Gemini 3.5 Flash Lite
Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
- Input / output price
- $0.30 / $2.50 per 1M
- Context
- 1M tokens
- Released
- Jul 21, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/gemini-3.5-flash-lite | $0.30/M | $2.50/M |
Google Gemini AI google_gemini_ai/gemini-3.5-flash-lite | $0.30/M | $2.50/M |
Inference.net inference_net/gemini-3.5-flash-lite | $0.30/M | $2.50/M |
Perplexity perplexity/gemini-3.5-flash-lite | $0.30/M | $2.50/M |
OpenRouter openrouter/gemini-3.5-flash-lite | $0.30/M | $2.50/M |
Is a provider down? Perplexity status, OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.30 per 1M
- Average output
- $2.50 per 1M
- Average cache read
- $0.03 per 1M
- Average cache write
- $0.03 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 better155tokens/sacross providers
Time to first token
Lower is better0.8sacross providers
Response latency
Lower is better1.5sacross providers
Benchmarks
The Respan Index plus 21 published scores from 7 sources, each linked to where it was published.
29.9/ 100
Respan Index#93 of 176
- 93Gemini 3.5 Flash-Lite29.9
- 92Muse Glimmer30.0
- 94Qwen3.5 397B-A17B29.5
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench CodingLiveBench | 76.1% | LiveBench | Oct 5, 2026 |
| WeirdMLHåvard Tveit Ihle | 39% | Håvard Tveit Ihle | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Toolathlon-VerifiedHKUST | 57.1% | HKUST | Jul 30, 2026 |
| LiveBench Agentic CodingLiveBench | 45.3% | LiveBench | Oct 5, 2026 |
| APEX-AgentsMercor | 29.3% | Mercor | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA DiamondEpoch AI | 83.3% | Epoch AI | Oct 5, 2026 |
| LiveBench ReasoningLiveBench | 60.2% | LiveBench | Oct 5, 2026 |
| LiveBench Data AnalysisLiveBench | 53.2% | LiveBench | Oct 5, 2026 |
| Chess PuzzlesEpoch AI | 21% | Epoch AI | Oct 28, 2026 |
| Mystery Game PuzzlesEpoch AI | 19% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench MathematicsLiveBench | 73.7% | LiveBench | Oct 5, 2026 |
| OTIS Mock AIME 2024-2025Epoch AI | 71.1% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tiers 1-3 v2Epoch AI | 26% | Epoch AI | Oct 5, 2026 |
| FrontierMath Tier 4 v2Epoch AI | 0% | Epoch AI | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench LanguageLiveBench | 71.8% | LiveBench | Oct 5, 2026 |
| LiveBench Instruction FollowingLiveBench | 67.2% | LiveBench | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1455 Elo · #60 of 191 | LMArena | Nov 19, 2026 |
| LMArena WebDevLMArena | 1432 Elo · #81 of 124 | LMArena | Nov 19, 2026 |
| LMArena VisionLMArena | 1266 Elo · #30 of 91 | LMArena | Nov 19, 2026 |
How Gemini compares: Claude vs Gemini, Gemini vs GPT, Gemini vs Grok
Compare Gemini 3.5 Flash Lite: Gemini 3.5 Flash-Lite vs Gemini 3.1 Flash-Lite, Gemini 3.5 Flash-Lite vs Gemini 4 Neon, Gemini 3.5 Flash-Lite vs Gemini 4 Carbon, Gemini 3.5 Flash-Lite vs Gemini 4 Hydrogen, Gemini 3.5 Flash-Lite vs Gemini 4 Argon, Gemini 3.5 Flash-Lite vs Gemini 3.8 Flash
Apps
Use Gemini 3.5 Flash Lite 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 Lite FAQ
Short answers, built from the data on this page.
Gemini 3.5 Flash Lite is a model from Google Gemini AI, released on Jul 21, 2026. Gemini 3.5 Flash Lite is a high-efficiency model from Google with upgraded agentic capabilities. It is suited for subagents that execute focused tasks within complex, multi-agent workflows.
On the Respan gateway, Gemini 3.5 Flash Lite costs $0.30 per 1M input tokens and $2.50 per 1M output tokens on every provider, after gateway discounts.
Gemini 3.5 Flash Lite is available through 5 providers: Concentrate, Google Gemini AI, Inference.net, Perplexity, and OpenRouter.
Gemini 3.5 Flash Lite 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-lite". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Gemini 3.5 Flash Lite scores 29.9 out of 100 on the Respan Index v1.1, ranking #93 of 176 models. By category: Coding 6.0, Agents 44.0, Reasoning 25.6, Knowledge & language 32.0, and Human preference 52.0. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Gemini 3.5 Flash Lite has 21 published benchmark scores, including LiveBench Coding 76.1%, Toolathlon-Verified 57.1%, and GPQA Diamond 83.3%. 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.