R1
by DeepSeek · deepseek/deepseek-r1 · #195 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:31 AM UTC · refreshed hourly
DeepSeek R1 is here: Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass....
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.70
per 1M tokens
Output
$2.50
per 1M tokens
Blended (3:1)
$1.15
3 input : 1 output
Cache read
—
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for R1 (no cache-read rate published — hits billed as normal input).
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.15 | $0.0739 | — |
| 50% | $1.15 | $0.0739 | −0% |
| 90% | $1.15 | $0.0739 | −0% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.0011 | $1.10 |
| Document summary | 8,000 | 1,000 | $0.0081 | $8.10 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.026 | $26.00 |
| Long-context analysis | 150,000 | 5,000 | $0.1175 | $117.50 |
Performance
Intelligence Index
20.1
AA composite quality
Coding Index
24.6
Math Index
76
Agentic Index
3.1
Output speed
0 tok/s
median
Time to first token
0s
median
Time to first answer
0s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 84.9% |
| GPQA Diamond | 81.3% |
| Humanity's Last Exam | 14.9% |
| LiveCodeBench | 77.0% |
| SciCode | 40.3% |
| MATH-500 | 98.3% |
| AIME | 89.3% |
| AIME 2025 | 76.0% |
| IFBench | 39.6% |
| AA-LCR (Long Context Reasoning) | 54.7% |
| Terminal-Bench Hard | 15.9% |
| τ²-Bench (Telecom) | 36.5% |
Specs
Context window
164K
tokens
Max output
16K
tokens
Input modalities
text
Tokenizer
DeepSeek