Gemini 3.8 Flash
google/gemini-3.8-flash
Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning.
Key facts
- Input price
- $0.825 / 1M tokens
- Output price
- $4.12 / 1M tokens
- Context window
- 1M tokens
- Max output
- 66K tokens
- Accepts
- Text, Images, Files, Audio, Video
- Returns
- Text
Example: 1,000 requests with 1,000 input and 500 output tokens each would cost about $2.89 (1M input tokens × $0.825 + 0.5M output tokens × $4.12). Estimate your own usage.
Prices are the provider’s own per-token rates with zero markup, from our price list as of Oct 18, 2026. If a call has extra provider charges (images, audio, web search, cached prompts), you pay the reported cost.
Call it from your code
curl https://api.tokenctr.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENCENTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "google/gemini-3.8-flash", "messages": [{"role": "user", "content": "Hello!"}]}'Works with any OpenAI-compatible SDK: set the base URL to https://api.tokenctr.com/v1. Quickstart
Benchmarks
Artificial Analysis
- Intelligence index
- 40.9
- Coding index
- 76.3
- Agentic index
- 40.2
Design Arena
| Category | Rank | Elo | Win rate |
|---|---|---|---|
| Agents: Godot game dev | 5 | 1273 | 53% |
| Agents: Mobile apps | 6 | 1233 | 54.4% |
| Models: SVG | 7 | 1292 | 54.6% |
| Agents: Full-stack | 11 | 1244 | 48.1% |
| Agents: Web apps | 11 | 1231 | 46.1% |
| Models: ASCII art | 11 | 1272 | 52.9% |
| Models: UI components | 11 | 1319 | 53.9% |
| Models: Websites | 13 | 1303 | 50% |
| Models: Code | 15 | 1306 | 50.3% |
| Models: Game dev | 17 | 1308 | 51% |
| Agents: Slides (python-pptx) | 19 | 1178 | 39.8% |
| Models: 3D | 19 | 1295 | 49.9% |
| Models: Data visualization | 28 | 1263 | 50.2% |
| Agents: Android native | 31 | 1080 | 33.9% |
Source: Artificial Analysis indexes and Design Arena results as published in OpenRouter’s model data, fetched Oct 15, 2026. Higher is better. Not measured by TokenCenter. See all rankings.