Gemini 3.7 Flash
Most intelligent workhorse model yet for coding and agents
Google has replaced this model with Gemini 4 Hydrogen.
Context window
1M
Input / 1M tokens
$0.75
Output / 1M tokens
$3.75
Provider
Google deprecated gemini-3.7-flash on October 8, 2026 (Gemini API changelog). API requests to it route to gemini-3.8-flash, which has the same price: $0.75/$3.75 per 1M through December 31, 2026, then $1.50/$7.50 from January 1, 2027. · Data verified 2026-11-08
Gemini 3.7 Flash is a refinement of the 3.6 architecture with algorithmic improvements focused on software engineering, knowledge work, and web development workflows. It delivers substantial gains in coding benchmarks (DeepSWE, FrontierCode) and autonomous agent capabilities at an introductory price of $0.75/1M input tokens through December 31, 2026. Google deprecated it on October 8, 2026, eight weeks after launch: Gemini 3.8 Flash replaced it, and API requests to gemini-3.7-flash are now routed to gemini-3.8-flash.
How to access it
No longer selectable in Google AI Studio. Since October 8, 2026, API requests to gemini-3.7-flash are routed to gemini-3.8-flash; Google says the endpoint is not shutting down and keeps routing to the replacement. Call gemini-3.8-flash directly.
Strengths
- ✓Strong coding performance with significant benchmark improvements
- ✓Better at multi-step planning and autonomous agent execution
- ✓Improved debugging and issue resolution capabilities
- ✓50% introductory pricing discount through year-end
- ✓1M token context window for long-document processing
Best for developers who...
When to choose it (and when not to)
Reach for Gemini 3.7 Flash when...
- →Only when existing code still calls gemini-3.7-flash; those requests are now served by Gemini 3.8 Flash
Look elsewhere if...
- ✕Any new project: call gemini-3.8-flash directly
- ✕Work that depends on 3.7 Flash behavior, since requests are now answered by Gemini 3.8 Flash
How to use it
- ›Use its improved instruction-following for multi-step tasks
- ›Use for iterative debugging and code refinement workflows
- ›Test against 3.6 Flash to verify cost-per-task improvements before migration
Quickstart
Pythonfrom google import genai
client = genai.Client() # reads GEMINI_API_KEY
interaction = client.interactions.create(
model="gemini-3.8-flash",
input="Summarize this support ticket in two sentences: ...",
)
print(interaction.output_text)Requests to gemini-3.7-flash now route to Gemini 3.8 Flash, so new code should use gemini-3.8-flash.
API model id: gemini-3.7-flash
Benchmarks
| Benchmark | Score | Notes |
|---|---|---|
| DeepSWE v1.1 | 65.3% | Up from 49.0% for Gemini 3.6 Flash |
| FrontierCode 1.1 Main | 43.6% | Up from 34.4% for Gemini 3.6 Flash |
| AutomationBench | 30.4% | Up from 17.0% for Gemini 3.6 Flash |
| WebDev Arena | 1588 Elo | Up from 1538 for Gemini 3.6 Flash |
| GDP.pdf | 34.0% | Up from 22.0% for Gemini 3.6 Flash |
Source: Google Official Announcement
Compare Gemini 3.7 Flash
Compare Gemini 3.7 Flash with any other model
Build a comparison →All model comparisons →