Low-latency Gemini model for high-volume multimodal and agent workloads
Specification
google listing
Context
1M
Max output
66K
Released
2026-05-07
Knowledge cutoff
2025-01
Retires
2027-05-07
Open weights
no
Input
text, image, video, audio, pdf
Output
text
Price
US dollars per million tokens · google list price
Input
$0.25
Output
$1.50
Cache read
$0.025
Cache write
$0.0833
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | vertex_ai-language-models | $0.125 |
| Batch output | vertex_ai-language-models | $0.75 |
| Priority input | databricks | $0.5625 |
| Priority input | vertex_ai-language-models | $0.45 |
| Priority output | databricks | $3.375 |
| Priority output | vertex_ai-language-models | $2.70 |
Batch input is 50% below the interactive input price at the same listing.
Rate limits
as listed
Requests per minute
15
Tokens per minute
250,000
Quality
3 benchmarks · 1 source
Composite
44th
percentile of 344 scored models
Rank
193 / 344
±0.07 sd
Evidence
3 × 1
one source, or fewer than 3 benchmarks
Effort range
8.1
points between effort settings
reasoning74th1/4 bench
math30th2/7 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| high | 66th | 3 |
| low | 44th | 3 |
| minimal | 40th | 3 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| GPQA diamond | 81.8 ±2.7 | high | Epoch AI | 2026-08-06 |
| ↳ | 74.2 ±3.1 | low | Epoch AI | 2026-08-06 |
| ↳ | 73.7 ±3.1 | minimal | Epoch AI | 2026-08-06 |
| Settings differ by 8.1 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 80.0 ±6.0 | high | Epoch AI | 2026-08-06 |
| ↳ | 44.4 ±7.5 | low | Epoch AI | 2026-08-06 |
| ↳ | 37.8 ±7.3 | minimal | Epoch AI | 2026-08-06 |
| Settings differ by 42.2 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 27.7 ±2.7 | high | Epoch AI | 2026-08-30 |
| ↳ | 22.5 ±2.5 | low | Epoch AI | 2026-08-30 |
| ↳ | 21.4 ±2.4 | minimal | Epoch AI | 2026-08-28 |
| Settings differ by 6.3 points on this benchmark. | ||||
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 | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| kilo | $0.125 | $0.75 | $0.0125 | $0.0417 | 1M | 66K | — |
| 302ai | $0.25 | $1.50 | $0.03 | — | 1M | 66K | — |
| abacus | $0.25 | $1.50 | $0.025 | $1.00 | 1M | 66K | — |
| aihubmix | $0.25 | $1.50 | $0.025 | $1.00 | 1M | 66K | — |
| cloudflare-ai-gateway | $0.25 | $1.50 | $0.03 | — | 1M | 66K | — |
| commandcode | $0.25 | $1.50 | $0.03 | — | 1M | 66K | — |
| databricks | $0.25 $0.3125 | $1.50 $1.875 | $0.025 $0.0312 | $0.3125 | 1M | 66K | — |
| deepinfra | $0.25 | $1.50 | — | — | 1M | 1M | — |
| edenai | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| gemini | $0.25 | $1.50 | $0.025 | — | 1M | 66K | 2026-05-25 2027-05-07 |
| google-vertex | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| impossibl | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| llmgateway | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| llmgateway-providers · google-ai-studio | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| llmgateway-providers · google-vertex | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| merge-gateway | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| nano-gpt | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| nearai | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| neon | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| ofox | $0.25 | $1.50 | $0.025 | $1.00 | 1M | 66K | — |
| openrouter | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| orcarouter | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| perplexity | $0.25 | $1.50 | $0.025 | — | — | — | — |
| requesty | $0.25 | $1.50 | $0.025 | $0.0833 | 1M | 66K | — |
| sap-ai-core | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| tempr | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| vercel | $0.25 | $1.50 | $0.03 | — | 1M | 65K | — |
| vertex_ai-language-models | $0.25 | $1.50 | $0.025 | — | 1M | 66K | 2027-05-07 |
| vivgrid | $0.25 | $1.50 | $0.025 | $1.00 | 1M | 66K | — |
| zenmux | $0.25 | $1.50 | $0.025 | — | 1M | 66K | — |
| poe | $0.2525 | $1.5152 | — | — | 1M | 66K | — |
| aimlapi | $0.2645 | $1.587 | $0.0265 | $0.0882 | 1M | 66K | — |
| cortecs | $0.272 | $1.631 | $0.025 | $0.082 | 1M | 66K | — |
| kenari | $0.2857 | $1.7143 | $0.0286 | $0.0857 | 1M | 66K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | openrouter | Cache read | $0.025 |
| 2026-10-10 | openrouter | Cache read | $0.025 |
| 2026-09-02 | openrouter | Cache write | $0.0833 |
| 2026-09-19 | openrouter | Cache write | $0.0833 |
| 2026-10-10 | openrouter | Cache write | $0.0833 |
| 2026-09-02 | kenari | Input | free |
| 2026-10-22 | kenari | Input | $0.2857 |
| 2026-09-02 | openrouter | Input | $0.25 |
| 2026-10-10 | openrouter | Input | $0.25 |
| 2026-09-02 | poe | Input | $0.25 |
| 2026-10-15 | poe | Input | $0.2525 |
| 2026-09-02 | kenari | Output | free |
| 2026-10-22 | kenari | Output | $1.7143 |
| 2026-09-02 | openrouter | Output | $1.50 |
| 2026-10-10 | openrouter | Output | $1.50 |
| 2026-09-02 | poe | Output | $1.50 |
| 2026-10-15 | poe | Output | $1.5152 |
| 2026-10-13 | aimlapi | Cache read | $0.0344 |
| 2026-10-23 | aimlapi | Cache read | $0.0265 |
| 2026-10-13 | aimlapi | Input | $0.3438 |
| 2026-10-23 | aimlapi | Input | $0.2645 |
| 2026-10-13 | aimlapi | Output | $2.0631 |
| 2026-10-23 | aimlapi | Output | $1.587 |
| 2026-10-21 | aimlapi | Cache write | $0.1146 |
| 2026-10-23 | aimlapi | Cache write | $0.0882 |
More from Google
most-hosted first