benchrGemini 3.5 Flash
Google · mid-tier. Coding agents at speed.
The published record
Every number below was read from the provider's own documentation on the date shown. benchr does not restate a figure it has not seen published.
- API identifier
gemini-3.5-flash- Context window
- 1,048,576tokensSource
- Maximum output
- 65,536tokensSource
- Input
- $1.50per 1M tokensSource
- Output
- $9.00per 1M tokensSource
- Cached input
- $0.15per 1M tokensSource
- Released
- May 19, 2026Source
- License
- Proprietary
Availability GA (stable).
Record verified July 30, 2026
What the record says
Released at Google I/O (May 19, 2026), GA. Google's live pricing page checked 2026-07-30 lists standard $1.50/$9, batch $0.75/$4.50, cached input $0.15 plus cache-storage charges, and a free API tier. The launch blog publishes only the four agentic/coding/multimodal benchmarks above; no official SWE-bench Verified or GPQA figure is published for 3.5 Flash, so those fields are null. No universal latency figure is recorded.
What benchr has documented it doing
Capabilities in the benchr ledger that name this model. Documented means a provider says it works and benchr recorded where. Verified means benchr ran it.
1 capabilities name this model. All 1 are officially supported by the provider; benchr has run 0 of them itself.
What has moved
Entries in the change ledger that affect this model, newest first.
Released
Gemini 3.5 Flash GA since May 19, 2026 (Google I/O). $1.50/$9.00. Source: ai.google.dev/pricing
Which one to use
The rest of the family, with the two numbers that usually decide it. The current model is marked.
| Models | Input | Output | Context window |
|---|---|---|---|
| Gemini 3.5 Flash-Lite | $0.3 | $2.50 | 1,048,576 |
| Gemini 3.6 Flash | $0.75 | $3.75 | 1,048,576 |
| Gemini 3.7 Flash | $0.75 | $3.75 | 1,048,576 |
| Gemini 3.8 Flash | $0.75 | $3.75 | 1,048,576 |
| Gemini 3.5 Flash This page | $1.50 | $9.00 | 1,048,576 |
| Gemini 3.1 Pro | $2.00 | $12.00 | 1M |
benchr's read
Worth it for
- Coding agents at speed
- Parallel agent execution
- Multimodal tasks
- Default frontier-quality model
Look elsewhere if
- You need the deepest single-call reasoning — use Gemini 3.1 Pro
Prices, limits, and identifiers above are provider facts. This section is benchr's judgement about them.
What benchr has written about it
Pieces that name this model, newest first. The ones written about this model come before the ones that mention it in passing.
What is not on this page
Stated rather than filled in.
- No first-token or tokens-per-second figure is recorded. benchr has not measured it and the provider does not publish one.
- benchr has not run any capability on this model itself. Everything in the capability section is documentation, not a test result.