DeepSeek: DeepSeek V4 Pro 0423
microdeepseek/deepseek-v4-pro
DeepSeek V4 Pro is a large-scale Mixture-of-Experts model from DeepSeek with 1.6T total parameters and 49B activated parameters, supporting a 1M-token context window. It is designed for advanced reasoning, coding,...
AA INDEX12.6
CONTEXT1049K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED37 min ago
Input
$1.30 /M
Output
$2.60 /M
Blended (40/60)
$2.08 /M
Cost / IQ
$6.6032 /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.
24h0%
7d↓ 4.3%
Price History
30-day view, daily close
Low: $1.88/M
High: $2.37/M
Average: $2.18/M
Pricing Variants
Cached Input
$0.25/M
72.2% cheaper than standard
Provider Comparison
11 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Relace | $0.90 | $1.50 | $1.26 | -39.4% |
| SiliconFlow | $1.00 | $1.50 | $1.30 | -37.5% |
| StreamLake | $0.96 | $1.91 | $1.53 | -26.5% |
| GMICloud | $0.96 | $1.91 | $1.53 | -26.4% |
| DigitalOcean | $1.04 | $2.09 | $1.67 | -19.7% |
| DeepInfra | $1.30 | $2.60 | $2.08 | median |
| Alibaba | $1.42 | $2.83 | $2.27 | +8.9% |
| Novita | $1.60 | $3.20 | $2.56 | +23.1% |
| Venice | $1.65 | $3.30 | $2.64 | +27.0% |
| AtlasCloud | $1.68 | $3.38 | $2.70 | +29.8% |
| Baidu | $1.69 | $3.38 | $2.70 | +30.0% |
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)$6.6032/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
0.8% above SIT TPI
Value Ranking (by Cost / IQ)
Rank #416 of 508 micro models
← YOU ARE HERE | DeepSeek: DeepSeek V4 Pro 0423
Data Sources
Source
Aggregator & direct provider data
11 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/deepseek/deepseek-v4-pro
# Response (truncated)
{ "model_id": "deepseek/deepseek-v4-pro", "name": "DeepSeek: DeepSeek V4 Pro 0423", "blended_price_per_m": 2.08, "sit_adjusted_price": 6.603175 }