R1 0528
by DeepSeek · deepseek/deepseek-r1-0528 · #177 cheapest of 325 paid models
Prices updated Jul 22, 2026, 2:50 AM UTC · refreshed hourly
May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) 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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.50
per 1M tokens
Output
$2.15
per 1M tokens
Blended (3:1)
$0.913
3 input : 1 output
Cache read
$0.35
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for R1 0528 with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.913 | $0.0532 | — |
| 50% | $0.856 | $0.0456 | −14% |
| 90% | $0.811 | $0.0396 | −25% |
*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 | $0.000895 | $0.895 |
| Document summary | 8,000 | 1,000 | $0.00615 | $6.15 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0193 | $19.30 |
| Long-context analysis | 150,000 | 5,000 | $0.0857 | $85.75 |
Performance
Intelligence Index
—
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Design Arena Elo
| Category | Elo |
|---|---|
| Website | 1,177 |
| UI components | 1,146 |
| Data viz | 1,215 |
| SVG | 1,085 |
| 3D | 1,170 |
| Game dev | 1,157 |
| Code categories | 1,172 |
Specs
Context window
164K
tokens
Max output
33K
tokens
Input modalities
text
Tokenizer
DeepSeek