Google's proven reasoning model for coding, math, and multimodal analysis
Specification
google listing
Context
1M
Max output
66K
Released
2025-06-17
Knowledge cutoff
2025-01
Retires
2026-10-20
Open weights
no
Input
text, image, audio, video, pdf
Output
text
Price
US dollars per million tokens · google list price
Input
$1.25
Output
$10.00
Cache read
$0.125
Cache write
$0.375
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Batch input | vertex_ai-language-models | $0.625 |
| Batch output | vertex_ai-language-models | $5.00 |
| Priority input | vertex_ai-language-models | $2.25 |
| Priority input | gemini | $1.25 |
| Priority output | vertex_ai-language-models | $18.00 |
| Priority output | gemini | $10.00 |
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 | $0.25 |
| 200K | Cache write | $0.25 |
| 200K | Input | $2.50 |
| 200K | Output | $15.00 |
Rate limits
as listed
Requests per minute
2,000
Tokens per minute
800,000
Quality
8 benchmarks · 2 sources
Composite
57th
percentile of 334 scored models
Rank
145 / 334
±0.06 sd
Evidence
8 × 2
3 or more benchmarks, from 2 or more sources
Effort range
4.0
points between effort settings
coding41st1/3 bench
reasoning83rd2/4 bench
math42nd5/7 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| GPQA diamond | 85.3 ±2.1 | default | Epoch AI | 2025-11-16 |
| OTIS Mock AIME 2024-2025 | 84.2 ±4.8 | default | Epoch AI | 2025-11-16 |
| Chess Puzzles | 20.0 ±4.0 | default | Epoch AI | 2025-12-08 |
| FrontierMath-v1 | 27.1 ±2.0 | default · 2 runs | Epoch AI | 2025-11-24 |
| SWE-Bench verified | 57.6 ±2.3 | default | Epoch AI | 2026-02-13 |
| ↳ | 53.6 | default · mini-SWE-agent | SWE-bench | — |
| Sources and settings disagree by 4.0 points. Both figures stand. | ||||
| FrontierMath-Tier-4-2025-07-01 | 2.1 ±0.0 | default · 2 runs | Epoch AI | 2025-07-03 |
| FrontierMath-Tiers-1-3-v2 | 24.6 ±2.6 | default | Epoch AI | 2026-06-11 |
| FrontierMath-Tier-4-v2 | 0.0 ±0.0 | 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 38 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| googlevendor | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| poe | $0.87 | $7.00 | $0.087 | — | 1.1M | 66K | — |
| jiekou | $1.125 | $9.00 | — | — | 1M | 66K | — |
| 302ai | $1.25 | $10.00 | — | — | 1M | 66K | — |
| abacus | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| aihubmix | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| auriko | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| crossmodel | $1.25 | $10.00 | $0.125 | $1.25 | 1M | 66K | — |
| databricks | $1.25 | $10.00 | $0.125 | $1.25 | 1M | 66K | — |
| deepinfra | $1.25 | $10.00 | — | — | 1M | 1M | — |
| fastrouter | $1.25 | $10.00 | $0.31 | — | 1M | 66K | — |
| frogbot | $1.25 | $10.00 | $0.31 | — | 1M | 66K | — |
| gemini | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| google-vertex | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| helicone | $1.25 | $10.00 | $0.3125 | $1.25 | 1M | 66K | — |
| impossibl | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| kilo | $1.25 | $10.00 | $0.125 | $0.375 | 1M | 66K | — |
| llmgateway | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| llmgateway-providers · google-ai-studio | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| llmgateway-providers · google-vertex | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| merge-gateway | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| modelis | $1.25 | $10.00 | — | — | 1M | 66K | — |
| nano-gpt | $1.25 | $10.00 | $0.125 | $0.375 | 1M | 66K | — |
| nearai | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| oci · oci | $1.25 | $10.00 | — | — | 1M | 66K | — |
| ofox | $1.25 | $10.00 | $0.125 | $4.50 | 1M | 66K | — |
| openrouter | $1.25 | $10.00 | $0.125 | $0.375 | 1M | 66K 66K | — |
| orcarouter | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| perplexity-agent | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| sap-ai-core | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| vercel | $1.25 | $10.00 | $0.125 | — | 1M | 66K | — |
| vertex_ai-language-models | $1.25 | $10.00 | $0.125 | — | 1M | 66K | 2026-10-20 |
| zenmux | $1.25 | $10.00 | $0.31 | $4.50 | 1M | 64K | — |
| cortecs | $1.495 | $9.964 | $0.242 | $0.434 | 1M | 66K | — |
| vercel_ai_gateway · vercel-ai-gateway | $2.50 | $10.00 | — | — | 1M | 66K | — |
| anyapi | — | — | — | — | 1M | 66K | — |
| github_copilot · github-copilot | — | — | — | — | 128K | 64K | — |
| qiniu-ai | — | — | — | — | 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 | $0.125 |
| 2026-09-06 | openrouter | Cache read | $0.125 |
| 2026-09-02 | openrouter | Cache write | $0.375 |
| 2026-09-06 | openrouter | Cache write | $0.375 |
More from Google
most-hosted first