All models
DeepSeek
DeepSeek V4.1 Flash fastruns locally
deepseek/deepseek-v4-1-flash
DeepSeek V4.1 Flash is a sparse mixture-of-experts model from DeepSeek, and the first built on the company's Causal Encoder-Decoder (CED) architecture. It activates 8B parameters on input and 16B on...
Input / 1M
$0.045
USD per million tokens
Output / 1M
$0.50
USD per million tokens
Est. cost / token
$0.000000159
$0.16 per 1M, 3:1 mix
Context window
1.05M
max output 944K
Major features
VisionOpen weightsCachingReasoningJSON schemaTools
Task suitability (heuristic 1–5, not a benchmark)
- coding3
- reasoning3
- math3
- summarization4
- extraction4
- classification4
- chat3
- creative3
- translation4
- vision3
- long context5
- agentic3
Run it locally
Will it run on my machine? →| Quantization | Quality | Memory needed (8K ctx) |
|---|---|---|
| Q2_K | poor | 343 GB |
| Q3_K_M | fair | 400 GB |
| Q4_K_Mrecommended | good | 498 GB |
| Q5_K_M | very good | 578 GB |
| Q6_K | excellent | 665 GB |
| Q8_0 | near-lossless | 859 GB |
| F16 | lossless | 1611 GB |
Estimates.
Price history
| Recorded | Input | Output | Cached | Source |
|---|---|---|---|---|
| 2026-11-05 03:20 | $0.045 | $0.50 | $0.018 | openrouter |
A row is added whenever a sync detects a price change. Vendor pricing source
Pricing (USD per 1M tokens)
- Input
- $0.045
- Output
- $0.50
- Cached input
- $0.018
- Blended (3:1)
- $0.16
Details
- Company
- DeepSeek
- Version
- 4.1
- Family
- DeepSeek
- Released
- 2026-09-10
- Parameters
- 763.2B
- Max output
- 944K
- Open weights
- Yes
- Inputs
- image, text
- Last synced
- 26 min ago