tokevenDeepSeek R1
DeepSeek R1 is DeepSeek's balanced performance model, priced at $0.55/MTok input and $2.19/MTok output with a 128K context window. Prices are off-peak rates from api-docs.deepseek.com (read 2026-10-11). Peak-hour prices are 2x the listed input and output rates — Tokeven does not model time-of-day tiers; off-peak is used as the base. Cache hit: $0.14/MTok input. No batch discount published. Reasoning model: output includes chain-of-thought tokens. Not yet benchmarked, so never recommended.
Input $/MTok
$0.55
Output $/MTok
$2.19
Context window
128K
Cache read discount
75% off
DeepSeek R1 pricing breakdown
| Rate | Input $/MTok | Output $/MTok |
|---|---|---|
| Standard | $0.55 | $2.19 |
| Cached read (75% off input) | $0.14 | - |
| Cached write (no surcharge) | $0.55 | - |
| Batch (0% off) | $0.55 | $2.19 |
All rates in USD per million tokens. Prices verified against provider documentation.
DeepSeek R1 task benchmarks
Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 88 models.
Not benchmarked. The third-party benchmark source used for confidence scores does not cover DeepSeek models yet. Scores will appear here once independent benchmarks are published.
DeepSeek R1 cost by use case
Estimated cost per API call using default token counts for each workload.
| Use case | Input tokens | Output tokens | Cost / call |
|---|---|---|---|
| Code Generation | 2,000 | 4,000 | $0.009860 |
| Unit Test Generation | 3,000 | 5,000 | $0.0126 |
| SQL Generation | 1,500 | 1,000 | $0.003015 |
| API Generation | 3,000 | 6,000 | $0.0148 |
| Code Refactoring | 4,000 | 4,000 | $0.0110 |
| Code Review | 5,000 | 2,000 | $0.007130 |
| PR Review | 8,000 | 3,000 | $0.0110 |
| Security Review | 6,000 | 2,500 | $0.008775 |
| Bug Detection | 5,000 | 2,000 | $0.007130 |
| Document Summarization | 10,000 | 1,000 | $0.007690 |
| PDF Summarization | 15,000 | 1,500 | $0.0115 |
| Meeting Notes | 8,000 | 2,000 | $0.008780 |
Monthly cost projections
Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).
| Calls / month | Without caching | With caching (75% read discount) |
|---|---|---|
| 1K | $9.86 | $9.29 |
| 10K | $98.6 | $92.86 |
| 100K | $986 | $928.64 |
| 500K | $4,930 | $4,643.18 |
| 1M | $9,860 | $9,286.35 |
Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.
Mid-tier alternatives to DeepSeek R1
Same-tier models from other providers, sorted by input price.
| Model | Provider | Input $/MTok | Output $/MTok | Input savings |
|---|---|---|---|---|
| MiniMax M2 | MiniMax | $0.26 | $1.00 | 53% cheaper |
| Kimi K2 | Moonshot (Kimi) | $0.95 | $4.00 | 73% more |
| GPT 5 | GPT | $1.25 | $10.00 | 127% more |
| GPT 5.1 | GPT | $1.25 | $10.00 | 127% more |
| Gemini 2.5 Pro | Gemini | $1.25 | $10.00 | 127% more |
| Grok 4.3 | Grok | $1.25 | $2.50 | 127% more |
| Grok 4.20 Non-Reasoning | Grok | $1.25 | $2.50 | 127% more |
| Grok 4.20 Reasoning | Grok | $1.25 | $2.50 | 127% more |
| Grok 4.20 Multi-Agent | Grok | $1.25 | $2.50 | 127% more |
| GPT 5.2 | GPT | $1.75 | $14.00 | 218% more |
| Claude Sonnet 5 | Claude | $2.00 | $10.00 | 264% more |
| Claude Sonnet 5.5 | Claude | $2.00 | $10.00 | 264% more |
| GPT 5.6 Terra | GPT | $2.00 | $12.00 | 264% more |
| GPT 4.1 | GPT | $2.00 | $8.00 | 264% more |
| o3 | GPT | $2.00 | $8.00 | 264% more |
| Gemini 3.1 Pro | Gemini | $2.00 | $12.00 | 264% more |
| Gemini 3.1 Pro Custom Tools | Gemini | $2.00 | $12.00 | 264% more |
| GPT 5.4 | GPT | $2.50 | $15.00 | 355% more |
| GPT 4o | GPT | $2.50 | $10.00 | 355% more |
| Claude Sonnet 4.6 | Claude | $3.00 | $15.00 | 445% more |
| Claude Sonnet 4.5 | Claude | $3.00 | $15.00 | 445% more |
Track your DeepSeek R1 spend
See exactly how much you spend on DeepSeek R1 and where you can save. Two-line wrapper install, no API keys shared.