New Gemini flash lane bringing frontier-style multimodal reasoning to cheaper runs
Specification
google listing
Context
1M
Max output
66K
Released
2025-12-17
Knowledge cutoff
2025-01
Retires
—
Open weights
no
Input
text, image, video, audio, pdf
Output
text
Price
US dollars per million tokens · google list price
Input
$0.50
Output
$3.00
Cache read
$0.05
Cache write
$0.0833
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | vertex_ai | $0.25 |
| Batch output | vertex_ai | $1.50 |
| Priority input | vertex_ai | $0.90 |
| Priority output | vertex_ai | $5.40 |
Batch input is 50% below the interactive input price at the same listing.
Rate limits
as listed
Requests per minute
2,000
Tokens per minute
800,000
Quality
10 benchmarks · 2 sources
Composite
84th
percentile of 334 scored models
Rank
53 / 334
±0.05 sd
Evidence
10 × 2
3 or more benchmarks, from 2 or more sources
Effort range
2.8
points between effort settings
coding82nd1/3 bench
reasoning91st3/4 bench
math70th5/7 bench
knowledge90th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| high | 92nd | 6 |
| low | 74th | 1 |
| minimal | 71st | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Chess Puzzles | 40.0 ±4.9 | high | Epoch AI | 2026-08-06 |
| ↳ | 38.0 ±4.9 | default | Epoch AI | 2025-12-17 |
| Settings differ by 2.0 points on this benchmark. | ||||
| SimpleQA Verified | 66.8 ±1.5 | high | Epoch AI | 2026-08-27 |
| OTIS Mock AIME 2024-2025 | 95.6 ±3.1 | high | Epoch AI | 2026-08-06 |
| ↳ | 92.8 ±3.5 | default | Epoch AI | 2025-12-17 |
| Settings differ by 2.8 points on this benchmark. | ||||
| FrontierMath-v1 | 47.8 ±16.3 | default · 2 runs | Epoch AI | 2025-12-17 |
| GPQA diamond | 89.4 ±2.2 | high | Epoch AI | 2026-08-06 |
| ↳ | 83.2 ±1.9 | default | Epoch AI | 2025-12-17 |
| Settings differ by 6.2 points on this benchmark. | ||||
| SWE-Bench verified | 75.8 | high · mini-SWE-agent | SWE-bench | — |
| ↳ | 75.4 ±2.0 | default | Epoch AI | 2026-02-18 |
| Sources and settings disagree by 0.4 points. Both figures stand. | ||||
| Mystery Game Puzzles | 26.0 ±4.4 | low | Epoch AI | 2026-08-05 |
| ↳ | 25.0 ±4.4 | minimal | Epoch AI | 2026-08-05 |
| ↳ | 20.0 ±4.0 | high | Epoch AI | 2026-08-05 |
| Settings differ by 6.0 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 51.2 ±3.0 | default | Epoch AI | 2026-06-11 |
| FrontierMath-Tier-4-2025-07-01 | 2.1 ±2.9 | default · 2 runs | Epoch AI | 2025-12-17 |
| FrontierMath-Tier-4-v2 | 17.1 ±5.9 | default | Epoch AI | 2026-06-11 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 35 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| googlevendor | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| qihang-ai | $0.07 | $0.43 | — | — | 1M | 66K | — |
| kilo | $0.25 | $1.50 | $0.025 | $0.0417 | 1M | 66K | — |
| poe | $0.40 | $2.40 | $0.04 | — | 1M | 66K | — |
| 302ai | $0.50 | $3.00 | — | — | 1M | 66K | — |
| abacus | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| aihubmix | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| crossmodel | $0.50 | $3.00 | $0.05 | $0.50 | 1M | 66K | — |
| databricks | $0.50 $0.625 | $3.00 $3.75 | $0.05 $0.0625 | $0.625 | 1M | 66K | — |
| edenai | $0.50 | $3.00 | $0.05 | $0.0833 | 1M | 66K | — |
| frogbot | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| gemini | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| gmi · gmi | $0.50 | $3.00 | — | — | 1M | 66K | — |
| google-vertex | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| jiekou | $0.50 | $3.00 | — | — | 1M | 66K | — |
| llmgateway | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| llmgateway-providers · google-ai-studio | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| llmgateway-providers · google-vertex | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| merge-gateway | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| nano-gpt | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| neon | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| ofox | $0.50 | $3.00 | $0.05 | $1.00 | 1M | 66K | — |
| opencode | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| openrouter | $0.50 | $3.00 | $0.05 | $0.0833 | 1M | 66K 66K | — |
| opper | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| orcarouter | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| perplexity | $0.50 | $3.00 | $0.05 | — | — | — | — |
| perplexity-agent | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| pioneer | $0.50 | $3.00 | $0.05 | $0.0833 | 1M | 65K | — |
| vercel | $0.50 | $3.00 | $0.05 | — | 1M | 65K | — |
| vertex_ai | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| vertex_ai-language-models | $0.50 | $3.00 | $0.05 | — | 1M | 66K | — |
| zenmux | $0.50 | $3.00 | $0.05 | $1.00 | 1M | 64K | — |
| venice | $0.70 | $3.75 | $0.07 | — | 256K | 66K | — |
| anyapi | — | — | — | — | 1M | 66K | — |
More from Google
most-hosted first