Gemini 3.7 Flash
Gemini 3.7 Flash is the high-efficiency, cost-effective powerhouse of the Gemini 3 family.
text + image + video + file → text · made by Google
$0.75→$3.75per Mtok in / out
DeepInfra · 11 sellers
Free
Offered at no charge, which is not the same as cheap: a free lane carries a rate limit and can be withdrawn. The prices above are what you pay when it is not available to you.
Sold by 26 ways
| Seller | Lane | Rate |
|---|---|---|
| Google api | free | $0per Mtok in$0per Mtok outai.google.dev · read 2026-09-16 |
| Google 0 ways | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached | |
| Google apinot on the seller's list today | batch | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cachedai.google.dev · read 2026-08-24 |
| Google Vertex AI cloud | batch | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cachedcloud.google.com · read 2026-08-24 |
| Google Vertex AI cloud | flex | $0.38per Mtok in$1.88per Mtok outraw.githubusercontent.com · read 2026-09-16 |
| Google 0 ways | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached | |
| Google apinot on the seller's list today | standard | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedai.google.dev · read 2026-08-24 |
| Google Vertex AI cloud | standard | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$3.75per Mtok out, reasoningcloud.google.com · read 2026-08-24 |
| Google Vertex AI cloud | priority | $1.35per Mtok in$6.75per Mtok out$0.14per Mtok cachedraw.githubusercontent.com · read 2026-09-16 |
| Nous Research 2 ways | $0.75per Mtok in$3.75per Mtok out$0.000001per image$0.075per Mtok cached$0.042per Mtok cache write | |
| Nous Research aggregator | batch | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.042per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12 |
| Nous Research aggregator | standard | $0.75per Mtok in$3.75per Mtok out$0.000001per image$0.075per Mtok cached$0.042per Mtok cache writeinference-api.nousresearch.com · read 2026-09-12 |
| OpenRouter 8 ways | $0.75per Mtok in$3.75per Mtok out$0.000001per image$0.075per Mtok cached$0.042per Mtok cache write | |
| OpenRouter aggregator | batch | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-09-03 |
| OpenRouter aggregator | google-ai-studio/flex | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.021per Mtok cache writeopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | google-vertex/global/flex | $0.38per Mtok in$1.88per Mtok out$0.037per Mtok cached$0.021per Mtok cache writeopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | standard | $0.75per Mtok in$3.75per Mtok out$0.000001per image$0.075per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | google-ai-studio | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/global | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cached$0.042per Mtok cache writeopenrouter.ai · read 2026-08-29 |
| OpenRouter aggregator | google-ai-studio/priority | $1.35per Mtok in$6.75per Mtok out$0.14per Mtok cached$0.075per Mtok cache writeopenrouter.ai · read 2026-08-25 |
| OpenRouter aggregator | google-vertex/global/priority | $1.35per Mtok in$6.75per Mtok out$0.14per Mtok cached$0.075per Mtok cache writeopenrouter.ai · read 2026-08-29 |
| Requesty aggregatornot on the seller's list today | vertex eu | $0.66per Mtok in$3.3per Mtok out$0.066per Mtok cachedrouter.requesty.ai · read 2026-08-25 |
| Requesty aggregator | vertex | $0.82per Mtok in$4.12per Mtok out$0.083per Mtok cachedrouter.requesty.ai · read 2026-09-16 |
| DeepInfra aggregator | standard | $0.75per Mtok in$3.75per Mtok outapi.deepinfra.com · read 2026-08-25 |
| ElectronHub aggregator | standard | $0.75per Mtok in$3.75per Mtok outapi.electronhub.ai · read 2026-09-16 |
| GitHub Copilot aggregator | standard | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedmodels.dev · read 2026-09-16 |
| Vercel AI Gateway aggregator | standard | $0.75per Mtok in$3.75per Mtok out$0.075per Mtok cachedvercel.com · read 2026-08-25 |
| Vercel AI Gateway aggregatornot on the seller's list today | sandbox | $0.75per Mtok in$3.75per Mtok outvercel.com · read 2026-08-25 |
| Venice AI aggregator | standard | $0.94per Mtok in$4.69per Mtok out$0.094per Mtok cachedmodels.dev · read 2026-09-16 |
| Inference.net aggregator | standard | $1.5per Mtok in$7.5per Mtok out$0.15per Mtok cachedapi.inference.net · read 2026-09-16 |
Measured 45 standings
| Place | Board | Metric | Score |
|---|---|---|---|
| 3rdof 313 | GPQA Diamond | mean_score (high) | 94.823 |
| 4thof 161 | Dtbench — Epoch AI | Accuracy (high) | 96.8 |
| 5thof 13 | Rli — Epoch AI | Score | 5 |
| 6thof 9 | Frontierswe — Epoch AI | Score (high) | 20.261 |
| 7thof 80 | Simpleqa verified — Epoch AI | mean_score (high) | 69.2 |
| 8thof 168 | Scicode — Epoch AI | Score (medium) | 57.87 |
| 9thof 40 | Design Arena · agenticgamedev (agents) | Elo | 1235 |
| 9thof 55 | Design Arena · androidnative (agents) | Elo | 1256 |
| 9thof 152 | Design Arena · dataviz (models) | Elo | 1331 |
| 9thof 30 | Frontiercode — Epoch AI | Main score | 0.436 |
| 10thof 63 | Design Arena · mobileapps (agents) | Elo | 1262 |
| 10thof 39 | Gdp pdf — Epoch AI | GDP.pdf score (high) | 0.238 |
| 11thof 127 | Mystery game puzzles — Epoch AI | mean_score (high) | 37 |
| 11thof 64 | Proofbench — Epoch AI | Accuracy | 58 |
| 12thof 155 | Design Arena · gamedev (models) | Elo | 1352 |
| 12thof 402 | LMArena · Text | Score (Elo) (high) | 1490 |
| 13thof 162 | Design Arena · website (models) | Elo | 1315 |
| 14thof 147 | Design Arena · 3d (models) | Elo | 1339 |
| 14thof 123 | Lmca — Epoch AI | Score (high) | 50.38 |
| 14thof 121 | Webdev arena — Epoch AI | Arena Score (high) | 1587.04 |
| 15thof 222 | Chess puzzles — Epoch AI | mean_score (high) | 47 |
| 15thof 156 | Design Arena · codecategories (models) | Elo | 1324 |
| 16thof 106 | Frontiermath tiers 1 3 v2 — Epoch AI | mean_score (high) | 71.579 |
| 19thof 184 | Artificial Analysis · Coding Index | Index | 76.1 |
| 19thof 150 | Design Arena · uicomponent (models) | Elo | 1315 |
| 19thof 62 | Design Arena · webapps (agents) | Elo | 1238 |
| 20thof 128 | LMArena · WebDev | Score (Elo) (high) | 1587 |
| 22ndof 232 | ARC-AGI-2 (Semi-Private) | Score (%) (high) | 84.58 |
| 22ndof 227 | Arc agi 2 — Epoch AI | Score (high) | 84.583 |
| 23rdof 230 | ARC-AGI-1 (Semi-Private) | Score (%) (high) | 95.5 |
| 23rdof 244 | Arc agi — Epoch AI | Score (high) | 95.5 |
| 23rdof 64 | Design Arena · fullstack (agents) | Elo | 1224 |
| 23rdof 62 | Frontiermath tier 4 v2 — Epoch AI | mean_score (high) | 36.585 |
| 24thof 290 | OTIS Mock AIME 2024-2025 | mean_score (high) | 97.222 |
| 25thof 69 | Deepswe — Epoch AI | Pass@1 (medium) | 0.655 |
| 25thof 92 | Design Arena · asciiart (models) | Elo | 1265 |
| 27thof 216 | ARC-AGI-2 (Public Eval) | Score (%) (high) | 85.28 |
| 28thof 74 | Cursorbench — Epoch AI | Score (high) | 61.6 |
| 29thof 205 | ARC-AGI-1 (Public Eval) | Score (%) (high) | 96.62 |
| 36thof 302 | Artificial Analysis · Intelligence Index | Artificial Analysis Intelligence Index (medium) | 40 |
| 44thof 46 | LMArena · Agent | Net Improvement (%) | 0.6 |
| 45thof 143 | Artificial Analysis · Agentic Index | Index | 36.4 |
| 51stof 112 | Ale bench — Epoch AI | Performance (high) | 904.3 |
| 54thof 177 | Critpt — Epoch AI | Accuracy (high) | 14.286 |
| 72ndof 656 | Epoch capabilities index — Epoch AI | ECI Score (high) | 157.32 |
About
Gemini 3.7 Flash — a text model from Google, sold by 11 companies from $0.75 in and $3.75 out per million tokens, placed 3rd of 313 on GPQA Diamond.
It takes text, images, video and files and returns text, with a context window of 1,000,000 tokens. It was published in August 2026, trained on material up to March 2026. Its sellers say it can reason step by step and call a tool. The catalogue files it under reasoning, code and agents. Eleven companies sell it. The cheapest is $0.75 in and $3.75 out per million tokens at DeepInfra. Beside the standard rate there are separately routed, batch, flex, faster and regional lanes. It has been measured on 45 boards, and stands best at 3rd of 313 on GPQA Diamond.
Every current figure
- Maker
- Register
- model
- Takes
- text + image + video + file
- Returns
- text
- Context
- 1,000,000 tokens
- Published
- August 2026
- Knowledge to
- March 2026
- Licence
- not read
- Sellers
- 11
- Price
- $0.75 in and $3.75 out per million tokens — DeepInfra
- Boards
- 45
- Best place
- 3rd of 313 — GPQA Diamond
Known as 11 names
Gemini 3.7 Flash (high)Gemini 3.7 Flash (low)Gemini 3.7 Flash (medium)gemini-3.7-flash_highgemini-3.7-flash-highgoogle/gemini-3.7-flashgemini-3.7-flashgoogle/gemini-3.7-flash:batchvertex/gemini-3.7-flashvertex/gemini-3.7-flash@euGoogle: Gemini 3.7 Flash (batch)