deepseek-r1 vs gemini-3.8-flash
Side-by-side comparison of deepseek-r1 and gemini-3.8-flash: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API. gemini-3.8-flash outperforms deepseek-r1 on 3 of 3 shared benchmarks.
deepseek-r1
Input / 1M
$4.00
Output / 1M
$4.00
Context
64K
Model ID
novita/deepseek/deepseek-r1
gemini-3.8-flash
Input / 1M
$1.50$0.75
Output / 1M
$7.50$3.75
Context
1.0M
Model ID
vertex/gemini-3.8-flash
Benchmark comparison
Intelligence Indexreasoning
deepseek-r113.9%
gemini-3.8-flash47.1%
Coding Indexcoding
deepseek-r1N/A
gemini-3.8-flash76.3%
Math Indexmath
deepseek-r176.0%
gemini-3.8-flashN/A
GPQA Diamondreasoning
deepseek-r181.3%
gemini-3.8-flash95.3%
AIME 2025math
deepseek-r176.0%
gemini-3.8-flashN/A
LiveCodeBenchcoding
deepseek-r177.0%
gemini-3.8-flashN/A
Terminal-Bench Hardagentic
deepseek-r115.9%
gemini-3.8-flashN/A
τ²-Benchagentic
deepseek-r136.5%
gemini-3.8-flashN/A
SciCodecoding
deepseek-r1N/A
gemini-3.8-flash56.6%
MMLU Proknowledge
deepseek-r184.9%
gemini-3.8-flashN/A
Humanity's Last Examreasoning
deepseek-r115.8%
gemini-3.8-flash47.8%
Scores sourced from official model cards, Artificial Analysis, and public leaderboards. Benchmarks measure specific skills and don't capture every aspect of model quality.
Pricing & specifications
| deepseek-r1 | gemini-3.8-flash | |
|---|---|---|
| Input price / 1M | $4.00 | $1.50$0.75 |
| Output price / 1M | $4.00 | $7.50$3.75 |
| Context window | 64K tokens | 1.0M tokens |
| Max output | N/A | 66K tokens |
| Vision input | N/A | Yes |
| Tool calling | Yes | Yes |
| Reasoning | N/A | Yes |
| Prompt caching | N/A | Yes |
| Computer use | N/A | N/A |
| Provider | Novita AI | Google LLC (Vertex AI) |
Questions people ask
Is deepseek-r1 better than gemini-3.8-flash?
gemini-3.8-flash outperforms deepseek-r1 on 3 of 3 shared benchmarks. See the benchmark comparison above for specifics: deepseek-r1 and gemini-3.8-flash have different strengths across reasoning, coding, math and multimodal tasks.
Which is cheaper, deepseek-r1 or gemini-3.8-flash?
gemini-3.8-flash is cheaper. deepseek-r1 costs $4.00/$4.00 per 1M input/output tokens, while gemini-3.8-flash costs $0.75/$3.75. The prices shown are what you pay: gemini-3.8-flash runs at 50% off its list rate of $1.50 per 1M input and $7.50 per 1M output.
Can I use deepseek-r1 and gemini-3.8-flash through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "novita/deepseek/deepseek-r1" and "vertex/gemini-3.8-flash", no other code changes needed.
What are the context windows?
deepseek-r1 supports up to 64K tokens of context. gemini-3.8-flash supports up to 1.0M tokens. Longer context means you can feed larger documents or codebases in a single prompt, though quality often degrades past 128K for most models.
Switch between deepseek-r1 and gemini-3.8-flash with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.