Complex coding or knowledge work
Start with Gemini 3.6 Flash.
Use repository tasks or document-analysis cases with acceptance tests, not a single benchmark.
Google model field guide · checked July 29, 2026
Gemini 3.6 Flash is the quality-first Flash choice.
Google positions 3.6 Flash as its workhorse for production agents. Use it when coding, document work, multimodal analysis, or multi-step tool use matters more than the lowest possible per-token price.
Provider record
Provider role
Workhorse Flash model for coding, knowledge work, multimodal tasks, and agentic workflows.
Published API price
$1.50 input and $7.50 output per million tokens at launch; verify the live pricing page.
Provider access
Gemini API, Google AI Studio, Android Studio, Gemini Enterprise, Antigravity, and the Gemini app at launch.
Flowith access
Not asserted here. The live Flowith workspace selector is the access authority.
Choose by workload, then run a pilot
High-volume classification or extraction
Benchmark Gemini 3.5 Flash-Lite first.
Compare accepted-output cost, tail latency, retries, and review effort.
Cyber vulnerability discovery
Do not assume normal API access to Flash Cyber.
Google limits it to governments and trusted partners through a CodeMender pilot.
Record output tokens, tool calls, retries, wall time, accepted results, and human review. A cheaper token is not cheaper if the workflow needs more loops or more correction.
Related decisions
Official sources
- Google launch announcement — model role, launch price, availability, and provider evaluations.
- Gemini 3.6 Flash model card — current model and safety details.
- Gemini API model guide — verify live identifiers, limits, lifecycle, and implementation details.
Gemini 3.6 Flash FAQ
What is Gemini 3.6 Flash?
Gemini 3.6 Flash is Google's July 2026 workhorse Flash model for coding, knowledge work, multimodal analysis, and agentic workflows.
How much does Gemini 3.6 Flash cost?
Google published launch pricing of $1.50 per million input tokens and $7.50 per million output tokens. Check the live Gemini API pricing page before budgeting.
Should I use Gemini 3.6 Flash or 3.5 Flash-Lite?
Start with 3.6 Flash when task quality and multi-step work dominate. Test 3.5 Flash-Lite for high-throughput, latency-sensitive work, then compare completed-task cost on your own acceptance set.
Is Gemini 3.6 Flash available in Flowith?
This page does not claim Flowith availability. Verify the current Flowith workspace model selector before designing a workflow.