DeepSeek R1 was retired from the DeepSeek API on July 24, 2026. Prices shown are the last published rates. DeepSeek names DeepSeek V4.1 Flash as the replacement. Details
Cost Comparison
| Prompts | DeepSeek R1 | Claude Sonnet 5.5 |
|---|---|---|
| 1 | $0.000350 | $0.0060 |
| 100 | $0.0350 | $0.6000 |
| 1,000 | $0.3500 | $6.00 |
| 10,000 | $3.50 | $60.00 |
| 100,000 | $35.00 | $600.00 |
Based on 500 input + 500 output tokens per prompt. Prices verified October 2026. Embed this calculator
At 10,000 requests per day, DeepSeek R1 costs $105.00/month vs Claude Sonnet 5.5 at $1,800.00/month — DeepSeek R1 is 94% cheaper.
| DeepSeek R1 | Claude Sonnet 5.5 | |
|---|---|---|
| Input price | $0.28 / 1M | $2.00 / 1M |
| Output price | $0.42 / 1M | $10.00 / 1M |
| Cached input | — | $0.20 / 1M |
| Typical prompt | $0.000350 | $0.0060 |
| Batch discount | None | 50% off |
| Context window | 131K tokens | 1M tokens |
| Max output | Not published | 128,000 tokens |
| Knowledge cutoff | Not published | Jun 2026 |
| Input types | Text | Text, Images, PDF |
| Reasoning mode | Always on | Always on |
| Open weights | Yes | No |
| Released | January 20, 2025 | September 28, 2026 |
| Status | Retired | Current |
Try It Yourself
How many tokens you expect the model to generate per response
Showing a typical prompt (500 input + 500 output tokens) across 27 models. Paste your own prompt above for an exact count.
| Model | Per Prompt | Prompts / $1 | Monthly |
|---|---|---|---|
DeepSeek R1Retired DeepSeek | $0.0003500.035¢ | 2,857 | $1.05 |
| Anthropic | $0.00600.6¢ | 166 | $18.00 |
GPT-6 LunaCheapest OpenAI | $0.0003000.03¢ | 3,333 | $0.9000 |
| Mistral | $0.0003750.037¢ | 2,666 | $1.13 |
| OpenAI (via Together) | $0.0003750.037¢ | 2,666 | $1.13 |
| OpenAI | $0.0007000.07¢ | 1,428 | $2.10 |
| DeepSeek | $0.0007500.075¢ | 1,333 | $2.25 |
| Meta (via Together) | $0.0009250.092¢ | 1,081 | $2.77 |
| Mistral | $0.00100.1¢ | 1,000 | $3.00 |
| $0.00140.14¢ | 714 | $4.20 | |
| xAI | $0.00190.19¢ | 533 | $5.63 |
| $0.00220.22¢ | 444 | $6.75 | |
| DeepSeek | $0.00260.26¢ | 378 | $7.92 |
| Meta | $0.00270.27¢ | 363 | $8.25 |
| Anthropic | $0.00300.3¢ | 333 | $9.00 |
| xAI | $0.00400.4¢ | 250 | $12.00 |
| Alibaba (Qwen) | $0.00400.4¢ | 250 | $12.00 |
| Mistral | $0.00450.45¢ | 222 | $13.50 |
| OpenAI | $0.00600.6¢ | 166 | $18.00 |
| OpenAI | $0.00600.6¢ | 166 | $18.00 |
| OpenAI | $0.00700.7¢ | 142 | $21.00 |
| $0.00700.7¢ | 142 | $21.00 | |
| Moonshot AI | $0.00900.9¢ | 111 | $27.00 |
| OpenAI | $0.0120 | 83 | $36.00 |
| Anthropic | $0.0120 | 83 | $36.00 |
| OpenAI | $0.0300 | 33 | $90.00 |
| Anthropic | $0.0300 | 33 | $90.00 |
Prices from official provider pricing pages, verified October 2026.
DeepSeek R1 vs Claude Sonnet 5.5 — Frequently Asked Questions
DeepSeek R1 is 94% cheaper than Claude Sonnet 5.5. One typical prompt (500 input + 500 output tokens) costs $0.000350 on DeepSeek R1 and $0.0060 on Claude Sonnet 5.5. DeepSeek R1 charges $0.28/$0.42 per million tokens (input/output) vs Claude Sonnet 5.5's $2.00/$10.00.
It depends on your priorities. DeepSeek R1 is more cost-effective at $0.3500 per 1,000 prompts. Claude Sonnet 5.5 may offer different capabilities or quality. DeepSeek R1 has a 131K context window vs Claude Sonnet 5.5's 1M. Use the calculator above to compare at your actual volume.
Beyond price: DeepSeek R1 accepts text, always reasons before answering and has open weights you can self-host. Claude Sonnet 5.5 accepts text, images and PDFs, writes up to 128,000 tokens per response, has a knowledge cutoff of June 2026 and always reasons before answering. DeepSeek R1 has a 131K context window and Claude Sonnet 5.5 1M. See the specs table above for a side-by-side view.
At 10,000 requests per day, switching from Claude Sonnet 5.5 to DeepSeek R1 saves about $1,695.00/month — a 94% cut on every call. Savings scale linearly with volume.
At 100,000 daily requests, DeepSeek R1 costs $1,050.00/month and Claude Sonnet 5.5 costs $18,000.00/month — a difference of $16,950.00/month.