All models
DeepSeek
DeepSeek V4 Flash 0731 fastruns locally
deepseek/deepseek-v4-flash-0731
DeepSeek V4 Flash 0731 is a sparse mixture-of-experts model from DeepSeek, with 13B active parameters out of 284B total. This re-post-trained revision is suited for coding, reasoning, and agent workflows....
Input / 1M
$0.059
USD per million tokens
Output / 1M
$0.30
USD per million tokens
Est. cost / token
$0.000000119
$0.12 per 1M, 3:1 mix
Context window
1.05M
max output 944K
Major features
Open weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision1
- long context5
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 139 GB |
| Q3_K_M | fair | 162 GB |
| Q4_K_Mrecommended | good | 201 GB |
| Q5_K_M | very good | 233 GB |
| Q6_K | excellent | 267 GB |
| Q8_0 | near-lossless | 345 GB |
| F16 | lossless | 644 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.059 | $0.30 | $0.035 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.059
- Output
- $0.30
- Cached input
- $0.035
- Blended (3:1)
- $0.12
Details
- Company
- DeepSeek
- Version
- 4
- Family
- DeepSeek
- Released
- 2026-07-31
- Parameters
- 304.2B
- Max output
- 944K
- Open weights
- Yes
- Inputs
- text
- Last synced
- 26 min ago