Back to models
available
Google: Gemini Pro Latest
google/gemini-proPrices
- Input
$2.00 per 1M tokens
unverified · disputed- Input (>200k ctx)
$4.00 per 1M tokens
low- Input (batch)
$1.00 per 1M tokens
low- Input (cached read, >200k ctx)
$0.40 per 1M tokens
low- Input (cached read, flex)
$0.20 per 1M tokens
low- Input (cached read, priority, >200k ctx)
$0.72 per 1M tokens
low- Input (cached read, priority)
$0.36 per 1M tokens
low- Input (cached read)
$0.20 per 1M tokens
low- Input (flex)
$1.00 per 1M tokens
low- Input (priority, >200k ctx)
$7.20 per 1M tokens
low- Input (priority)
$3.60 per 1M tokens
low- Output
$12.00 per 1M tokens
unverified · disputed- Output (>200k ctx)
$18.00 per 1M tokens
low- Output (batch)
$6.00 per 1M tokens
low- Output (flex)
$6.00 per 1M tokens
low- Output (priority, >200k ctx)
$32.40 per 1M tokens
low- Output (priority)
$21.60 per 1M tokens
low- Web search (context size: high)
$0.014 per query
low- Web search (context size: low)
$0.014 per query
low- Web search (context size: medium)
$0.014 per query
low
Also available on
The same model, sold by someone else. The price above is the maker's own.
| Channel | What | Price |
|---|---|---|
| Google Vertex AI | Input | $2.00 per 1M tokens |
| Input (>200k ctx) | $4.00 per 1M tokens | |
| Input (audio) | $2.00 per 1M tokens | |
| Input (cache write, >200k ctx) | $0.25 per 1M tokens | |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read, >200k ctx) | $0.40 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Output (>200k ctx) | $18.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens | |
| OpenRouter · ~google | Image (input) | $0.000002 per image |
| Input | $2.00 per 1M tokens | |
| Input (audio, cached read) | $0.20 per 1M tokens | |
| Input (audio) | $2.00 per 1M tokens | |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens | |
| Query | $0.014 per query | |
| OpenRouter · google | Image (input) | $0.000002 per image |
| Input | $2.00 per 1M tokens | |
| Input (audio, cached read) | $0.20 per 1M tokens | |
| Input (audio) | $2.00 per 1M tokens | |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens | |
| Query | $0.014 per query | |
| OpenRouter | Input | $2.00 per 1M tokens |
| Input (>200k ctx) | $4.00 per 1M tokens | |
| Input (audio, cached read) | $0.20 per 1M tokens | |
| Input (audio) | $2.00 per 1M tokens | |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read, >200k ctx) | $0.40 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Output (>200k ctx) | $18.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens | |
| Other · edenai | Input | $2.00 per 1M tokens |
| Input (>200k ctx) | $4.00 per 1M tokens | |
| Input (audio) | $2.00 per 1M tokens | |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read, >200k ctx) | $0.40 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Output (>200k ctx) | $18.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens | |
| Other · google-ai-studio | Input | $2.00 per 1M tokens |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Other · kilo | Input | $2.00 per 1M tokens |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens | |
| Other · nano-gpt | Input | $2.00 per 1M tokens |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $12.00 per 1M tokens | |
| Other · openrouter | Input | $0.50 per 1M tokens |
| Input (>200k ctx) | $4.00 per 1M tokens | |
| Input (cache write) | $0.375 per 1M tokens | |
| Input (cached read, >200k ctx) | $0.40 per 1M tokens | |
| Input (cached read) | $0.20 per 1M tokens | |
| Output | $1.50 per 1M tokens | |
| Output (>200k ctx) | $18.00 per 1M tokens | |
| Output (reasoning) | $12.00 per 1M tokens |
Specifications
- Provider
- Context window
- 1,048,576
- Max output tokens
- 65,536
- Open weights
- no
- Released
- 02/19/2026
- Retires
- no date announced
- First seen by this tracker
Price history
Input — per 1M tokens
| From | Amount |
|---|---|
| 09/14/2026 | 1.25 |
| 09/17/2026 | 2 |
Output — per 1M tokens
| From | Amount |
|---|---|
| 09/14/2026 | 10 |
| 09/17/2026 | 12 |
Input (cached read) — per 1M tokens
| From | Amount |
|---|---|
| 09/14/2026 | 0.125 |
| 09/17/2026 | 0.2 |
Input (cached read, >200k ctx) — per 1M tokens
| From | Amount |
|---|---|
| 09/14/2026 | 0.25 |
| 09/17/2026 | 0.4 |
Input (>200k ctx) — per 1M tokens
| From | Amount |
|---|---|
| 09/14/2026 | 2.5 |
| 09/17/2026 | 4 |
Output (>200k ctx) — per 1M tokens
| From | Amount |
|---|---|
| 09/14/2026 | 15 |
| 09/17/2026 | 18 |
Web search (context size: low) — per query
| From | Amount |
|---|---|
| 09/14/2026 | 0.035 |
| 09/17/2026 | 0.014 |
Web search (context size: medium) — per query
| From | Amount |
|---|---|
| 09/14/2026 | 0.035 |
| 09/17/2026 | 0.014 |
Web search (context size: high) — per query
| From | Amount |
|---|---|
| 09/14/2026 | 0.035 |
| 09/17/2026 | 0.014 |
No changes recorded
- Input (cached read, priority, >200k ctx)
- 0.72 per 1M tokens, unchanged since 09/17/2026
- Input (cached read, priority)
- 0.36 per 1M tokens, unchanged since 09/17/2026
- Input (priority, >200k ctx)
- 7.2 per 1M tokens, unchanged since 09/17/2026
- Input (batch)
- 1 per 1M tokens, unchanged since 09/17/2026
- Input (priority)
- 3.6 per 1M tokens, unchanged since 09/17/2026
- Output (priority, >200k ctx)
- 32.4 per 1M tokens, unchanged since 09/17/2026
- Output (batch)
- 6 per 1M tokens, unchanged since 09/17/2026
- Output (priority)
- 21.6 per 1M tokens, unchanged since 09/17/2026
- Input (cached read, flex)
- 0.2 per 1M tokens, unchanged since 09/17/2026
- Input (flex)
- 1 per 1M tokens, unchanged since 09/17/2026
- Output (flex)
- 6 per 1M tokens, unchanged since 09/17/2026