Model comparison - Same provider, successor
Gemini 3.6 Flash vs Gemini 3.8 Flash
Gemini 3.6 Flash and Gemini 3.8 Flash are both Google models. Both list the same first-party API price: $0.75 per 1M input tokens and $3.75 per 1M output tokens. Gemini 3.6 Flash and Gemini 3.8 Flash both have a 1,048,576-token context window, and both return up to 65,536 output tokens per response. Gemini 3.6 Flash was released on July 21, 2026 and Gemini 3.8 Flash on September 2, 2026. Both are closed-weights models, available only through an API.
Last verified from each provider's pricing page. All sources
Side-by-side specs
| Spec | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| Provider | ||
| Input / 1M tokens | $0.75 | $0.75 |
| Output / 1M tokens | $3.75 | $3.75 |
| Cache read / 1M | $0.075 | $0.075 |
| Batch input / 1M | $0.375 | $0.375 |
| Batch output / 1M | $1.875 | $1.875 |
| Context window | 1,048,576 | 1,048,576 |
| Max output | 65,536 | 65,536 |
| Release date | ||
| Weights | Closed | Closed |
| API model id | gemini-3.6-flash | gemini-3.8-flash |
| AI Gateway id | google/gemini-3.6-flash | google/gemini-3.8-flash |
| Last verified |
Prices in USD per 1M tokens at each provider's standard first-party rate. A dash means the provider does not bill that item separately or no primary page states it.
What each costs in practice
The same three workloads every model page uses, worked from each model's standard list rates. Swap in your own token counts with the math on each model's page.
| Workload | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| One agent session1M input tokens and 100K output tokens, no caching. | $1.13 | $1.13 |
| A chat app10,000 requests a day at 2K input and 500 output tokens each. | $33.75$1,012.50 per 30-day month | $33.75$1,012.50 per 30-day month |
| The same session at a 90% cache hit90% of the input is read from the prompt cache. The one-time cache write premium is not included. | $0.5175 | $0.5175 |
Show the math
Gemini 3.6 Flash
- One agent sessionInput: 1M x $0.75 = $0.75Output: 0.1M x $3.75 = $0.375
- A chat appInput: 20M x $0.75 = $15.00Output: 5M x $3.75 = $18.75
- The same session at a 90% cache hitCached input: 0.9M x $0.075 = $0.0675Uncached input: 0.1M x $0.75 = $0.075Output: 0.1M x $3.75 = $0.375
Gemini 3.8 Flash
- One agent sessionInput: 1M x $0.75 = $0.75Output: 0.1M x $3.75 = $0.375
- A chat appInput: 20M x $0.75 = $15.00Output: 5M x $3.75 = $18.75
- The same session at a 90% cache hitCached input: 0.9M x $0.075 = $0.0675Uncached input: 0.1M x $0.75 = $0.075Output: 0.1M x $3.75 = $0.375
Benchmarks under the same setting
Only boards that list both models under the same run setting appear here, one row per board and setting, with each score exactly as the board shows it. Scores on different boards use different scales and are never combined.
| Board and setting | Gemini 3.6 Flash | Gemini 3.8 Flash |
|---|---|---|
| DeepSWE v1.1mini-swe-agent, high effort, Pass@1, v1.1 (113 tasks), best effort level shownOfficial leaderboard - deepswe.datacurve.ai | 47%±4% | 74%±1% |
| LMArena Text (Text Arena Overall)Text Arena Overall, default leaderboard view (8,834,211 votes, 416 models)Official leaderboard - arena.ai | 1483±4 | 1496±5 (Preliminary) |
Set them up in your tools
Step-by-step guides whose official docs list Gemini 3.6 Flash or Gemini 3.8 Flash by model id.
- Use Gemini in ClineLists Gemini 3.8 Flash and Gemini 3.6 Flash
- Use Gemini in ContinueLists Gemini 3.8 Flash and Gemini 3.6 Flash
- Use Gemini in CursorLists Gemini 3.8 Flash and Gemini 3.6 Flash
- Use Gemini in GooseLists Gemini 3.8 Flash and Gemini 3.6 Flash
- Use Gemini in Kilo CodeLists Gemini 3.8 Flash and Gemini 3.6 Flash
- Use Gemini in OpenCodeLists Gemini 3.8 Flash and Gemini 3.6 Flash
- Use Gemini in ZedLists Gemini 3.8 Flash and Gemini 3.6 Flash
Model pages
FAQ
How do Gemini 3.6 Flash and Gemini 3.8 Flash compare on price?
Both list the same first-party API price: $0.75 per 1M input tokens and $3.75 per 1M output tokens. For one agent session of 1M input and 100K output tokens with no caching, that is $1.13 on Gemini 3.6 Flash and $1.13 on Gemini 3.8 Flash. Prices are each provider's first-party list rates, verified October 17, 2026 and October 17, 2026.
What are the context windows of Gemini 3.6 Flash and Gemini 3.8 Flash?
Gemini 3.6 Flash and Gemini 3.8 Flash both have a 1,048,576-token context window, and both return up to 65,536 output tokens per response.
Are Gemini 3.6 Flash and Gemini 3.8 Flash open weights?
Gemini 3.6 Flash is closed-weights and is called through Google's API as gemini-3.6-flash. Gemini 3.8 Flash is closed-weights and is called through Google's API as gemini-3.8-flash.
More comparisons
- Gemini 3.8 Flash vs Mistral Large 4Similar price, same tier
- Gemini 3.6 Flash vs Gemini 3 Flash PreviewSame provider, successor
- Gemini 3.8 Flash vs GLM-5.3Similar price, same tier
- Gemini 3.8 Flash vs Grok Build 0.1Similar price, same tier
- Gemini 3.8 Flash vs Mistral Medium 3.5Similar price, same tier
- DeepSeek V4 Pro vs Gemini 3.8 FlashSimilar price, same tier
- Gemini 3.8 Flash vs GPT-5.4 MiniSimilar price, same tier
- Gemini 3.8 Flash vs Kimi K2.7 CodeSimilar price, same tier
Sources
Gemini 3.6 Flash verified from ai.google.dev; Gemini 3.8 Flash verified from ai.google.dev. This page is as current as the older of the two: .
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.