Models, measured side by side
DeepSeek R1 vs Gemini 2.5 Pro
Compare DeepSeek R1, Gemini 2.5 Pro by token pricing, context length, benchmark results, speed and tool support.
Monthly workload
Monthly cost breakdown
InputOutput
DeepSeek R1
$27 / mo
Gemini 2.5 Pro
$75 / mo
Performance comparison
DeepSeek R1
13.1
Gemini 2.5 Pro
16.1
Overview
Pricing & capacity
| Pricing & capacity | DeepSeek R1 | Gemini 2.5 Pro |
|---|---|---|
| Input / 1M tokens | $0.70 | $1.25 |
| Output / 1M tokens | $2.50 | $10 |
| Cached input / 1M | Not listed | $0.13 |
| Monthly cost | $27 | $75 |
| Context window | 64K | 1M |
| Maximum output | 16K | 66K |
Input / 1M tokens
- DeepSeek R1
- $0.70
- Gemini 2.5 Pro
- $1.25
Output / 1M tokens
- DeepSeek R1
- $2.50
- Gemini 2.5 Pro
- $10
Cached input / 1M
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- $0.13
Monthly cost
- DeepSeek R1
- $27
- Gemini 2.5 Pro
- $75
Context window
- DeepSeek R1
- 64K
- Gemini 2.5 Pro
- 1M
Maximum output
- DeepSeek R1
- 16K
- Gemini 2.5 Pro
- 66K
Benchmarks & performance
| Benchmarks & performance | DeepSeek R1 | Gemini 2.5 Pro |
|---|---|---|
| Arena Elo | 1,239 | 1,255 |
| MMLU-Pro | 80% | 82.8% |
| Intelligence Index | 13.1 | 16.1 |
| GPQA | 81.3% | 84.4% |
| Humanity’s Last Exam | 15.8% | 22.5% |
| SciCode | Not listed | 46.3% |
| Output speed | Not listed | 128 tokens/s |
| Time to first token | Not listed | 18.08 s |
| DesignArena rating | Not listed | 1,156 |
| DesignArena win rate | Not listed | 57.5% |
Arena Elo
- DeepSeek R1
- 1,239
- Gemini 2.5 Pro
- 1,255
MMLU-Pro
- DeepSeek R1
- 80%
- Gemini 2.5 Pro
- 82.8%
Intelligence Index
- DeepSeek R1
- 13.1
- Gemini 2.5 Pro
- 16.1
GPQA
- DeepSeek R1
- 81.3%
- Gemini 2.5 Pro
- 84.4%
Humanity’s Last Exam
- DeepSeek R1
- 15.8%
- Gemini 2.5 Pro
- 22.5%
SciCode
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- 46.3%
Output speed
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- 128 tokens/s
Time to first token
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- 18.08 s
DesignArena rating
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- 1,156
DesignArena win rate
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- 57.5%
6 of 10
Tools & features
| Tools & features | DeepSeek R1 | Gemini 2.5 Pro |
|---|---|---|
| Function calling | Supported | Supported |
| Structured outputs | Not listed | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Built-in web search | Not listed | Not listed |
| Log probabilities | Not listed | Not listed |
| Deterministic seed | Supported | Supported |
| Parallel tool calls | Not listed | Not listed |
| Prompt caching | Not listed | Supported |
Function calling
- DeepSeek R1
- Supported
- Gemini 2.5 Pro
- Supported
Structured outputs
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- Supported
JSON mode
- DeepSeek R1
- Supported
- Gemini 2.5 Pro
- Supported
Reasoning
- DeepSeek R1
- Supported
- Gemini 2.5 Pro
- Supported
Built-in web search
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- Not listed
Log probabilities
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- Not listed
Deterministic seed
- DeepSeek R1
- Supported
- Gemini 2.5 Pro
- Supported
Parallel tool calls
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- Not listed
Prompt caching
- DeepSeek R1
- Not listed
- Gemini 2.5 Pro
- Supported
6 of 9
API & availability
| API & availability | DeepSeek R1 | Gemini 2.5 Pro |
|---|---|---|
| API identifier | deepseek-r1 | gemini-2.5-pro |
| API providers | Novita | Google, Google, Google AI Studio, Google, Google AI Studio, Google, Google AI Studio |
| Knowledge cutoff | 2024-07-31 | 2025-01-31 |
| Prices checked | Oct 8, 2026 | Oct 8, 2026 |
API identifier
- DeepSeek R1
deepseek-r1- Gemini 2.5 Pro
gemini-2.5-pro
API providers
- DeepSeek R1
- Novita
- Gemini 2.5 Pro
- Google, Google, Google AI Studio, Google, Google AI Studio, Google, Google AI Studio
Knowledge cutoff
- DeepSeek R1
- 2024-07-31
- Gemini 2.5 Pro
- 2025-01-31
Prices checked
- DeepSeek R1
- Oct 8, 2026
- Gemini 2.5 Pro
- Oct 8, 2026
About the models
Comparison FAQ
DeepSeek R1: $0.70 input and $2.50 output per million tokens. Gemini 2.5 Pro: $1.25 input and $10 output per million tokens. The cheaper choice depends on your input-to-output ratio; a model can have a lower input rate but a higher output rate.