# deepseek-ai/DeepSeek-R1 API prices

deepseek-ai/DeepSeek-R1 (deepseek-thinking) — 164k context, 164k max output.
2 metered per-token offers from 2 provider(s), in USD per 1M tokens.
Prices as of 2026-10-04.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| SiliconFlow | $0.5 | $2.18 | — | 164k |
| SiliconFlow (China) | $0.5 | $2.18 | — | 164k |

## Summary

- Cheapest input: $0.5 per 1M tokens (SiliconFlow)
- Cheapest output: $2.18 per 1M tokens (SiliconFlow)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-05-28
- Inputs: text

## FAQ

### What is the cheapest deepseek-ai/DeepSeek-R1 API?

As of Oct 4, 2026, SiliconFlow has the lowest deepseek-ai/DeepSeek-R1 output price at $2.18 per 1M tokens, and SiliconFlow has the lowest input price at $0.5 per 1M tokens. Prices are metered per-token rates in USD; free tiers and subscription plans are excluded.

### How many providers offer deepseek-ai/DeepSeek-R1?

2 providers list deepseek-ai/DeepSeek-R1 on Sovyron; 2 of them sell it at a metered per-token price.

### Is deepseek-ai/DeepSeek-R1 free?

No provider in the Sovyron catalog lists a free tier for deepseek-ai/DeepSeek-R1.

### What is the context window of deepseek-ai/DeepSeek-R1?

deepseek-ai/DeepSeek-R1 supports a 164k-token context window and up to 164k output tokens.

HTML page: https://sovyron.com/models/deepseek-ai-deepseek-r1/
Full dataset: https://sovyron.com/data/catalog.json