Google: Gemini 3.5 Flash-Lite
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↓ lowerOutput $2.50 → $1.25
- ↓ lowerInput $0.3 → $0.15
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| tokenstatgemini/gemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | 1.0M | |
| models.devcheapestgoogle/gemini-3.5-flash-lite | Kilo Gateway | $0.15 | $1.25 | $0.015 | 1.0M |
| OpenRoutergoogle/gemini-3.5-flash-lite:batch | OpenRouter | $0.15 | $1.25 | $0.015 | 1.0M |
| models.devgemini-3.5-flash-lite | AIHubMix | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | Cloudflare | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | CommandCode | $0.3 | $2.50 | $0.03 | 1M |
| models.devgoogle/gemini-3.5-flash-lite | Eden AI | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | $0.3 | $2.50 | $0.03 | 1.0M | |
| models.devgoogle/gemini-3.5-flash-lite | Impossibl | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | Merge Gateway | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | NanoGPT | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | Ofox | $0.3 | $2.50 | $0.03 | 1.0M |
| OpenRoutergoogle/gemini-3.5-flash-lite | OpenRouter | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | OrcaRouter | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | Standard Compute | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | Tempr Gateway | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle/gemini-3.5-flash-lite | Vercel AI Gateway | $0.3 | $2.50 | $0.03 | 1M |
| models.devgemini-3.5-flash-lite | 302.AI | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | Abacus | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | Google Vertex AI | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgoogle-ai-studio/gemini-3.5-flash-lite | LLM Gateway | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | DevPass (LLM Gateway) | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3-5-flash-lite | Neon | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | OpenCode | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | Opper | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini-3.5-flash-lite | Requesty | $0.3 | $2.50 | $0.03 | 1.0M |
| models.devgemini/gemini-3.5-flash-lite | CrossModel | $0.3 | $2.50 | $0.03 | 1.0M |
| LiteLLMgemini-3.5-flash-lite | N/A | $0.3 | $2.50 | $0.03 | N/A |
| LiteLLMgemini/gemini-3.5-flash-lite | N/A | $0.3 | $2.50 | $0.03 | N/A |
| LiteLLMperplexity/google/gemini-3.5-flash-lite | N/A | $0.3 | $2.50 | $0.03 | N/A |
| LiteLLMvertex_ai/gemini-3.5-flash-lite | N/A | $0.3 | $2.50 | $0.03 | N/A |
| models.devgoogle/gemini-3.5-flash-lite | Poe | $0.303 | $2.53 | $0.0303 | 1.0M |
| models.devgemini-3.5-flash-lite | Cortecs | $0.33 | $2.75 | $0.033 | 1.0M |
| LiteLLMdatabricks-gemini-3-5-flash-lite | N/A | $0.375 | $3.13 | $0.0375 | N/A |
| LiteLLMdatabricks/databricks-gemini-3-5-flash-lite | N/A | $0.375 | $3.13 | $0.0375 | N/A |
| models.devgemini-3-5-flash-lite | Venice AI | $0.375 | $3.13 | $0.0375 | 1M |
| LiteLLMkyma/gemini-3.5-flash-lite | N/A | $0.405 | $3.38 | $0.0405 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- In: text
- In: image
- In: video
- In: audio
- In: pdf
- In: file
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence22.2i
- AA coding49.3i
- AA agentic14.3i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.