deepseek-ai/DeepSeek-R1 vs deepseek-v3.2
Side-by-side comparison of deepseek-ai/DeepSeek-R1 and deepseek-v3.2: benchmarks, pricing, context window and capabilities. Both are accessible through Requesty's unified API.
deepseek-ai/DeepSeek-R1
Input / 1M
$0.85
Output / 1M
$2.50
Context
64K
Model ID
deepinfra/deepseek-ai/DeepSeek-R1
deepseek-v3.2
Input / 1M
$0.56
Output / 1M
$1.68
Context
164K
Model ID
vertex/deepseek-v3.2
Pricing & specifications
| deepseek-ai/DeepSeek-R1 | deepseek-v3.2 | |
|---|---|---|
| Input price / 1M | $0.85 | $0.56 |
| Output price / 1M | $2.50 | $1.68 |
| Context window | 64K tokens | 164K tokens |
| Max output | 8K tokens | 66K tokens |
| Vision input | N/A | N/A |
| Tool calling | Yes | Yes |
| Reasoning | Yes | Yes |
| Prompt caching | N/A | Yes |
| Computer use | N/A | N/A |
| Provider | DeepInfra | Google Vertex AI |
Questions people ask
Is deepseek-ai/DeepSeek-R1 better than deepseek-v3.2?
Benchmark data is limited for one or both models. Compare pricing and capabilities in the tables above, and test both on your own workload.
Which is cheaper, deepseek-ai/DeepSeek-R1 or deepseek-v3.2?
deepseek-v3.2 is cheaper. deepseek-ai/DeepSeek-R1 costs $0.85/$2.50 per 1M input/output tokens, while deepseek-v3.2 costs $0.56/$1.68.
Can I use deepseek-ai/DeepSeek-R1 and deepseek-v3.2 through the same API?
Yes. Requesty provides a single OpenAI-compatible API that routes to both. Change just the "model" parameter to switch between "deepinfra/deepseek-ai/DeepSeek-R1" and "vertex/deepseek-v3.2", no other code changes needed.
What are the context windows?
deepseek-ai/DeepSeek-R1 supports up to 64K tokens of context. deepseek-v3.2 supports up to 164K 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-ai/DeepSeek-R1 and deepseek-v3.2 with one line of code
Requesty provides a single OpenAI-compatible API for 600+ models. Change the model parameter, not your code.