DeepSeek: DeepSeek V4 Flash 0423
microdeepseek/deepseek-v4-flash
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...
AA INDEXN/A
CONTEXT1049K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED8 min ago
Input
$0.13 /M
Output
$0.28 /M
Blended (40/60)
$0.22 /M
Cost / IQ
N/A /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price. No AA score available for this model.
24h0%
7d↓ 0.1%
Price History
30-day view, daily close
Low: $0.22/M
High: $0.22/M
Average: $0.22/M
Pricing Variants
Cached Input
$0.02/M
80% cheaper than standard
Provider Comparison
12 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓StreamLake | $0.08 | $0.17 | $0.13 | -40.0% |
| DeepInfra | $0.09 | $0.18 | $0.14 | -34.6% |
| GMICloud | $0.09 | $0.18 | $0.15 | -33.8% |
| Wafer | $0.12 | $0.17 | $0.15 | -31.8% |
| Fireworks | $0.10 | $0.21 | $0.17 | -23.7% |
| SiliconFlow | $0.13 | $0.28 | $0.22 | -0.0% |
| Venice | $0.14 | $0.28 | $0.22 | +0.0% |
| AtlasCloud | $0.14 | $0.28 | $0.22 | +1.8% |
| Baidu | $0.14 | $0.28 | $0.22 | +1.8% |
| Parasail | $0.14 | $0.28 | $0.22 | +1.8% |
| Relace | $0.05 | $0.45 | $0.29 | +31.8% |
| Mancer 2 | $0.15 | $0.50 | $0.36 | +63.6% |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)N/A (no AA score)
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #344 of 508 micro models
← YOU ARE HERE | DeepSeek: DeepSeek V4 Flash 0423
Data Sources
Source
Aggregator & direct provider data
12 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/deepseek/deepseek-v4-flash
# Response (truncated)
{ "model_id": "deepseek/deepseek-v4-flash", "name": "DeepSeek: DeepSeek V4 Flash 0423", "blended_price_per_m": 0.2201, "sit_adjusted_price": null }