Fast Gemini model balancing multimodal reasoning, tool use, and cost
Specification
google listing
Context
1M
Max output
66K
Released
2026-07-21
Knowledge cutoff
2026-03
Retires
—
Open weights
no
Input
text, image, video, audio, pdf
Output
text
Price
US dollars per million tokens · google list price
Input
$0.75
Output
$3.75
Cache read
$0.075
Cache write
$0.0417
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | vertex_ai | $0.375 |
| Batch output | vertex_ai | $1.875 |
| Priority input | vertex_ai | $1.35 |
| Priority output | vertex_ai | $6.75 |
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
8 benchmarks · 2 sources
Composite
84th
percentile of 334 scored models
Rank
54 / 334
±0.08 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
8.1
points between effort settings
reasoning92nd3/4 bench
math71st3/7 bench
knowledge89th1/1 bench
general39th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| low | 89th | 4 |
| minimal | 88th | 4 |
| high | 87th | 8 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Chess Puzzles | 43.0 ±5.0 | low | Epoch AI | 2026-08-07 |
| ↳ | 40.0 ±4.9 | high | Epoch AI | 2026-08-02 |
| ↳ | 35.0 ±4.8 | minimal | Epoch AI | 2026-08-07 |
| Settings differ by 8.0 points on this benchmark. | ||||
| SimpleQA Verified | 66.2 ±1.5 | high | Epoch AI | 2026-08-27 |
| GPQA diamond | 94.1 ±1.4 | high | Epoch AI | 2026-08-02 |
| ↳ | 86.4 ±2.4 | low | Epoch AI | 2026-08-06 |
| ↳ | 85.9 ±2.5 | minimal | Epoch AI | 2026-08-07 |
| Settings differ by 8.2 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 94.2 ±3.1 | high | Epoch AI | 2026-08-02 |
| ↳ | 82.2 ±5.8 | low | Epoch AI | 2026-08-07 |
| ↳ | 80.0 ±6.0 | minimal | Epoch AI | 2026-08-07 |
| Settings differ by 14.2 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 59.0 ±2.9 | high | Epoch AI | 2026-08-02 |
| Mystery Game Puzzles | 30.0 ±4.6 | high | Epoch AI | 2026-08-05 |
| ↳ | 25.0 ±4.4 | minimal | Epoch AI | 2026-08-05 |
| ↳ | 23.0 ±4.2 | low | Epoch AI | 2026-08-05 |
| Settings differ by 7.0 points on this benchmark. | ||||
| LiveBench | 74.5 | high · 23 runs | LiveBench | 2026-06-25 |
| FrontierMath-Tier-4-v2 | 21.9 ±6.5 | high | Epoch AI | 2026-08-02 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 30 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| googlevendor | $0.75 | $3.75 | $0.075 | — | 1M | 66K | — |
| kenari | free | free | — | — | 1M | 66K | — |
| kilo | $0.375 | $1.875 | $0.0375 | $0.0208 | 1M | 66K | — |
| cortecs | $0.75 | $3.75 | $0.075 | $0.038 | 1M | 66K | — |
| crossmodel | $0.75 | $3.75 | $0.075 | $0.75 | 1M | 66K | — |
| edenai | $0.75 | $3.75 | $0.075 | $0.0417 | 1M | 66K | — |
| gemini | $0.75 | $3.75 | $0.075 | — | 1M | 66K | — |
| github-copilot | $0.75 | $3.75 | $0.075 | — | 1M | 64K | — |
| google-vertex | $0.75 | $3.75 | $0.075 | — | 1M | 66K | — |
| llmgateway | $0.75 | $3.75 | $0.075 | $0.0833 | 1M | 66K | — |
| llmgateway-providers · google-ai-studio | $0.75 | $3.75 | $0.075 | $0.0833 | 1M | 66K | — |
| llmgateway-providers · google-vertex | $0.75 | $3.75 | $0.075 | $0.0833 | 1M | 66K | — |
| nano-gpt | $0.75 | $3.75 | $0.075 | $0.0417 | 1M | 66K | — |
| ofox | $0.75 | $3.75 | $0.075 | $0.0415 | 1M | 66K | — |
| openrouter | $0.75 | $3.75 | $0.075 | $0.0417 | 1M | 66K | — |
| vercel | $0.75 | $3.75 | $0.075 | — | 1M | 64K | — |
| vertex_ai | $0.75 | $3.75 | $0.075 | — | 1M | 66K | — |
| vertex_ai-language-models | $0.75 | $3.75 | $0.075 | — | 1M | 66K | — |
| venice | $0.9375 | $4.6875 | $0.0938 | — | 1M | 66K | — |
| 302ai | $1.50 | $7.50 | — | — | 1M | 66K | — |
| abacus | $1.50 | $7.50 | $0.15 | — | 1M | 66K | — |
| impossibl | $1.50 | $7.50 | $0.15 | — | 1M | 66K | — |
| merge-gateway | $1.50 | $7.50 | $0.15 | — | 1M | 66K | — |
| neon | $1.50 | $7.50 | $0.15 | — | 1M | 66K | — |
| opencode | $1.50 | $7.50 | $0.15 | — | 1M | 66K | — |
| orcarouter | $1.50 | $7.50 | $0.15 | — | 1M | 66K | — |
| perplexity | $1.50 | $7.50 | $0.15 | — | — | — | — |
| pioneer | $1.50 | $7.50 | $0.15 | $1.50 | 1M | 64K | — |
| requesty | $1.50 | $7.00 | $0.15 | — | 1M | 66K | — |
| databricks | $1.875 | $9.375 | $0.1875 | $1.875 | 1M | 66K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | crossmodel | Cache read | $0.15 |
| 2026-09-05 | crossmodel | Cache read | $0.075 |
| 2026-09-02 | openrouter | Cache read | $0.075 |
| 2026-09-06 | openrouter | Cache read | $0.075 |
| 2026-09-02 | crossmodel | Cache write | $1.50 |
| 2026-09-05 | crossmodel | Cache write | $0.75 |
| 2026-09-02 | crossmodel | Input | $1.50 |
| 2026-09-05 | crossmodel | Input | $0.75 |
| 2026-09-02 | openrouter | Input | $0.75 |
| 2026-09-06 | openrouter | Input | $0.75 |
| 2026-09-02 | crossmodel | Output | $7.50 |
| 2026-09-05 | crossmodel | Output | $3.75 |
| 2026-09-02 | openrouter | Output | $3.75 |
| 2026-09-06 | openrouter | Output | $3.75 |
More from Google
most-hosted first