DeepSeek V4 Flash 0423 pricing
DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and... Live index: 16 priced offers. Best input $0.047 per million tokens from Openrouter. Best output $0.094 per million tokens from Openrouter.
Pricing across providers
All figures are list prices per million tokens unless a column says otherwise. 16 offers are listed for DeepSeek V4 Flash 0423. Best input in this view: Openrouter.
| Provider | Input / 1M | Output / 1M | Cached input | Batch |
|---|---|---|---|---|
A Aihubmix | $0.142 | $0.284 | $0.028 | — |
AC Alibaba Cloud | $0.200 | $0.400 | $0.040 | — |
A Azure | $0.190 | $0.510 | $0.028 | — |
D DeepInfra | $0.090 | $0.180 | $0.018 | — |
FA Fireworks AI | $0.140 | $0.280 | $0.028 | — |
L Libertai | $0.250 | $1.75 | — | — |
N Nebius | $0.140 | $0.280 | — | — |
N Novita | $0.140 | $0.280 | $0.028 | — |
O Openrouter | $0.047 | $0.094 | — | — |
P Pinstripes | $0.100 | $0.200 | — | — |
QA Qwen Ai Platform | $0.200 | $0.400 | $0.040 | — |
Q Qwencloud | $0.200 | $0.400 | $0.040 | — |
T Tencent | $0.140 | $0.280 | $0.0028 | — |
T Tensormesh | $0.140 | $0.280 | $0.0000 | — |
W Wandb | $0.140 | $0.280 | $0.070 | — |
D Deepseeknative | $0.300 | $1.20 | $0.0060 | — |
Input vs output · per provider
Pricing history
If you only care about current multi seller rates, use the pricing section. This timeline is for the official listing history. The native listing moved from $0.440 in and $1.32 out to $0.300 in and $1.20 out in the latest window.
Since Sep 13, 2026
$0.300 in · $1.20 out(current listing)
Output rate -9% vs previous period
Aug 21, 2026 → Sep 13, 2026
$0.440 in · $1.32 out
Output rate +371% vs previous period
Jun 21, 2026 → Aug 21, 2026
$0.140 in · $0.280 out
Cost calculator
Use this block to stress test DeepSeek V4 Flash 0423 cost without a spreadsheet. All estimates come from public list rates in this page.
Provider
0.014200¢ / req
0.014200¢ / req
Model specifications
Quick spec sheet for DeepSeek V4 Flash 0423 before you dive back into pricing. Reported under Deepseek.
- Context window
- 1,048,576 tokens
- Max output
- 384,000 tokens
- Vision (images)
- No
- Tool / function calling
- Yes
- Streaming
- Yes
- Released
- Apr 2026
- Primary provider
- Deepseek
- Model family
- N/A
Compare DeepSeek V4 Flash 0423
These links open full side by side pages for DeepSeek V4 Flash 0423. We picked pairs that people often shop together. 6 ready to open.
Locked
Compare with
Pick a model on both sides.
Popular DeepSeek V4 Flash 0423 comparisons
- DeepSeek V4 Flash 0423 vs GPT-4o
DeepSeek V4 Flash 0423 88% cheaper on output
- DeepSeek V4 Flash 0423 vs Claude Sonnet 4.6
DeepSeek V4 Flash 0423 92% cheaper on output
- DeepSeek V4 Flash 0423 vs Gemini 2.0 Flash
Gemini 2.0 Flash 66% cheaper on output
- DeepSeek V4 Flash 0423 vs Llama 3.1 70B
Compare pricing side by side
- DeepSeek V4 Flash 0423 vs Mistral 7B
Mistral 7B 79% cheaper on output
- DeepSeek V4 Flash 0423 vs GLM 4.7
DeepSeek V4 Flash 0423 45% cheaper on output
Frequently asked questions
Quick frequently asked items for DeepSeek V4 Flash 0423 pricing and limits. The short model note from our index: DeepSeek V4 Flash is an efficiency-optimized Mixture-of-Experts model from DeepSeek with 284B total parameters and 13B activated parameters, supporting a 1M-token context window. It is designed for fast inference and...
Related models
Models close to DeepSeek V4 Flash 0423 by family, provider, and context window — each with live pricing in our catalog.