All models
DeepSeek
DeepSeek V3.1 fastruns locally
deepseek/deepseek-chat-v3-1
DeepSeek-V3.1 is a large hybrid reasoning model (671B parameters, 37B active) that supports both thinking and non-thinking modes via prompt templates. It extends the DeepSeek-V3 base with a two-phase long-context...
Input / 1M
$0.25
USD per million tokens
Output / 1M
$0.95
USD per million tokens
Est. cost / token
$0.000000425
$0.42 per 1M, 3:1 mix
Context window
164K
max output 147K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context3
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 309 GB |
| Q3_K_M | fair | 359 GB |
| Q4_K_Mrecommended | good | 447 GB |
| Q5_K_M | very good | 519 GB |
| Q6_K | excellent | 597 GB |
| Q8_0 | near-lossless | 771 GB |
| F16 | lossless | 1445 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.25 | $0.95 | $0.13 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.25
- Output
- $0.95
- Cached input
- $0.13
- Blended (3:1)
- $0.42
Details
- Company
- DeepSeek
- Version
- 3.1
- Family
- DeepSeek
- Released
- 2025-08-21
- Parameters
- 684.5B
- Max output
- 147K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 29 min ago