Model
Gemini 3.6 Flash
Fast Gemini model balancing multimodal reasoning, tool use, and cost
Compare providers (sorted by listed input price)
23 of 24 providers publish a price for Gemini 3.6 Flash. The cheapest full-context option is Cortecs at $0.75/$3.75 per M — 2% below Vertex's own price. Kilo Gateway lists lower but caps context at 1.05M.
Best price history
Daily lowest published price across live providers. A lower line is better for the buyer.
- Best input /M
- $0.375▼ 50.0%
- Best output /M
- $1.88▼ 50.0%
- Provider coverage
- 28
- 26 at the start · 24 snapshots
Price badge
https://www.vaanalytics.in/badge/google/gemini-3.6-flash.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- new modelvia 302ai · Sep 9, 2026
- capabilityvia edenai · Sep 7, 2026
- name: Gemini 3.6 Flash (US) → Gemini 3.6 Flash (Vertex AI, US)
- capabilityvia edenai · Sep 7, 2026
- name: Gemini 3.6 Flash (EU) → Gemini 3.6 Flash (Vertex AI, EU)
- capabilityvia edenai · Sep 7, 2026
- name: Gemini 3.6 Flash → Gemini 3.6 Flash (Vertex AI)
- repricedvia crossmodel · Sep 5, 2026
- input: $1.50 → $0.75
- output: $7.50 → $3.75
- cache_read: $0.15 → $0.075
- cache_write: $1.50 → $0.75
- contextvia cortecs · Sep 2, 2026
- output: 1.05M → 66K tokens
Benchmarks
- SWE-Bench Pro ↗(resolve rate)report ↗Unclassified source58.7
- DeepSWE(resolve rate)report ↗Unclassified source49
- Terminal-Bench ↗(accuracy)report ↗Unclassified source78
- MLE-Bench(average position score)report ↗Unclassified source63.9
- GDPval-AA(Elo)report ↗Unclassified source1421
- OSWorld-Verified ↗(success rate)report ↗Unclassified source83
- CharXiv Reasoning(accuracy)report ↗Unclassified source85.2
- CharXiv Reasoning(accuracy)report ↗Unclassified source89.4
- GDM-MRCR(accuracy)report ↗Unclassified source91.8
- GDM-MRCR(accuracy)report ↗Unclassified source54
Scores a lab published about its own model are claims, not measurements. Rankings elsewhere on this site use independently measured scores only.
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.