Reasoning-first Gemini preview for agentic coding and complex problem solving
Specification
google listing
Context
1M
Max output
66K
Released
2026-02-19
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
$2.00
Output
$12.00
Cache read
$0.20
Cache write
$0.375
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | vertex_ai-language-models | $1.00 |
| Batch output | vertex_ai-language-models | $6.00 |
| Priority input | vertex_ai-language-models | $3.60 |
| Priority output | vertex_ai-language-models | $21.60 |
Batch input is 50% below the interactive input price at the same listing.
Long-context price tiers
the rate above each context threshold
| Above | Price | $/M |
|---|---|---|
| 200K | Cache read | $0.40 |
| 200K | Cache write | $0.25 |
| 200K | Input | $4.00 |
| 200K | Output | $18.00 |
Rate limits
as listed
Requests per minute
2,000
Tokens per minute
800,000
Quality
12 benchmarks · 2 sources
Composite
86th
percentile of 334 scored models
Rank
48 / 334
±0.06 sd
Evidence
12 × 2
3 or more benchmarks, from 2 or more sources
Effort range
2.7
points between effort settings
coding18th1/3 bench
reasoning92nd4/4 bench
math85th5/7 bench
knowledge99th1/1 bench
general68th1/1 bench
By reasoning effort
every setting placed on the same scale as the leaderboard
| Setting | Composite | Benchmarks behind it |
|---|---|---|
| high | 92nd | 7 |
| medium | 88th | 1 |
| low | 83rd | 1 |
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| Chess Puzzles | 55.0 ±5.0 | default | Epoch AI | 2026-02-19 |
| ↳ | 49.0 ±5.0 | high | Epoch AI | 2026-08-06 |
| Settings differ by 6.0 points on this benchmark. | ||||
| SimpleQA Verified | 73.5 ±1.4 | high | Epoch AI | 2026-08-10 |
| FrontierMath-v1 | 62.9 ±2.8 | default · 2 runs | Epoch AI | 2026-02-19 |
| GPQA diamond | 94.4 ±1.6 | high | Epoch AI | 2026-08-06 |
| ↳ | 94.1 ±1.7 | default | Epoch AI | 2026-02-20 |
| Settings differ by 0.3 points on this benchmark. | ||||
| OTIS Mock AIME 2024-2025 | 95.6 ±3.1 | default | Epoch AI | 2026-02-20 |
| ↳ | 95.6 ±3.1 | high | Epoch AI | 2026-08-06 |
| Mystery Game Puzzles | 34.0 ±4.8 | high | Epoch AI | 2026-07-27 |
| ↳ | 32.0 ±4.7 | medium | Epoch AI | 2026-08-06 |
| ↳ | 29.0 ±4.6 | low | Epoch AI | 2026-08-06 |
| Settings differ by 5.0 points on this benchmark. | ||||
| FrontierMath-Tiers-1-3-v2 | 59.6 ±2.9 | default | Epoch AI | 2026-06-11 |
| LiveBench | 78.0 | high · 23 runs | LiveBench | 2026-06-25 |
| FrontierMath-Tier-4-2025-07-01 | 8.3 ±5.4 | default · 2 runs | Epoch AI | 2026-02-19 |
| FrontierMath-Tier-4-v2 | 26.8 ±7.0 | default | Epoch AI | 2026-06-11 |
| EBR-bench | 14.3 | default | Epoch AI | 2026-06-25 |
| MirrorCode | 8.9 ±4.6 | high | Epoch AI | 2026-08-10 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 41 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| googlevendor | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| kenari | free | free | — | — | 1M | 66K | — |
| kilo | $1.00 | $6.00 | $0.10 | $0.1875 | 1M | 66K | — |
| 302ai | $2.00 | $12.00 | — | — | 1M | 66K | — |
| abacus | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| aihubmix | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| auriko | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| crossmodel | $2.00 | $12.00 | $0.20 | $2.00 | 1M | 66K | — |
| daoxe | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| databricks | $2.00 $2.50 | $12.00 $15.00 | $0.20 $0.25 | $2.50 | 1M | 66K | — |
| deepinfra | $2.00 | $12.00 | — | — | 1M | — | — |
| edenai | $2.00 | $12.00 | $0.20 | $0.375 | 1M | 66K | — |
| fastrouter | $2.00 | $12.00 | — | — | 1M | 66K | — |
| frogbot | $2.00 | $12.00 | $0.20 | — | 1M | 64K | — |
| gemini | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| google-vertex | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| impossibl | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| llmgateway | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| llmgateway-providers · google-ai-studio | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| llmgateway-providers · google-vertex | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| llmgateway-providers · quartz | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| merge-gateway | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| nano-gpt | $2.00 | $12.00 | $0.20 | $0.375 | 1M | 66K | — |
| neon | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| ofox | $2.00 | $12.00 | $0.20 | $4.50 | 1M | 66K | — |
| opencode | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| openrouter | $2.00 | $12.00 | $0.20 | $0.375 | 1M | 66K | — |
| opper | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| orcarouter | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| perplexity | $2.00 | $12.00 | $0.20 | — | — | — | — |
| perplexity-agent | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| pioneer | $2.00 | $12.00 | $0.20 | $0.375 | 1M | 64K | — |
| poe | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| requesty | $2.00 | $12.00 | $0.20 | $4.50 | 1M | 66K | — |
| vercel | $2.00 | $12.00 | $0.20 | — | 1M | 64K | — |
| vertex_ai | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| vertex_ai-language-models | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| vivgrid | $2.00 | $12.00 | $0.20 | — | 1M | 66K | — |
| zenmux | $2.00 | $12.00 | $0.20 | $4.50 | 1M | 64K | — |
| venice | $2.50 | $15.00 | $0.50 | $0.50 | 1M | 33K | — |
| snowflake-cortex | — | — | — | — | 1M | 66K | — |
More from Google
most-hosted first