All models
DeepSeek
R1 0528 balancedruns locally
deepseek/deepseek-r1-0528
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...
Input / 1M
$0.50
USD per million tokens
Output / 1M
$2.15
USD per million tokens
Est. cost / token
$0.000000913
$0.91 per 1M, 3:1 mix
Context window
164K
max output 33K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding4
- reasoning4
- math4
- summarization4
- extraction4
- classification4
- chat4
- creative4
- translation4
- vision1
- long context3
- agentic4
Run it locally
Will it run on my machine? →ollama run deepseek-r1:671b| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 303 GB |
| Q3_K_M | fair | 352 GB |
| Q4_K_Mrecommended | good | 438 GB |
| Q5_K_M | very good | 509 GB |
| Q6_K | excellent | 585 GB |
| Q8_0 | near-lossless | 756 GB |
| F16 | lossless | 1417 GB |
Estimates. Mixture-of-experts: memory covers all parameters; only the active ones are used per token, so it runs faster than its size suggests.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.50 | $2.15 | $0.35 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.50
- Output
- $2.15
- Cached input
- $0.35
- Blended (3:1)
- $0.91
Details
- Company
- DeepSeek
- Version
- 1
- Family
- DeepSeek
- Released
- 2025-05-28
- Parameters
- 671B (37B active)
- Max output
- 33K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 21 min ago