DeepSeek: DeepSeek V4 Flash 0731
budgetdeepseek/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....
AA INDEX34.3
CONTEXT1311K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED2 min ago
Input
$0.14 /M
Output
$0.35 /M
Blended (40/60)
$0.26 /M
Cost / IQ
$0.3025 /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.
24h↓ 0.5%
7d↓ 24.8%
Price History
30-day view, daily close
Low: $0.22/M
High: $0.35/M
Average: $0.27/M
Pricing Variants
Cached Input
$0.02/M
0% cheaper than standard
Batch (async)
$0.24/M
6.8% cheaper than standard
In: $0.11/M · Out: $0.33/M
Provider Comparison
31 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Engy | $0.04 | $0.09 | $0.07 | -72.3% |
| StreamLake | $0.04 | $0.13 | $0.10 | -62.7% |
| DeepInfra | $0.06 | $0.18 | $0.13 | -49.2% |
| Makora | $0.09 | $0.20 | $0.15 | -41.1% |
| Inceptron | $0.06 | $0.26 | $0.18 | -30.4% |
| DigitalOcean | $0.12 | $0.24 | $0.19 | -26.7% |
| Relace | $0.02 | $0.32 | $0.20 | -23.3% |
| BaseTen | $0.13 | $0.26 | $0.21 | -19.9% |
| CoreWeave | $0.13 | $0.28 | $0.22 | -15.3% |
| Cohere | $0.14 | $0.28 | $0.22 | -13.7% |
| Nebius | $0.14 | $0.28 | $0.22 | -13.7% |
| Parasail | $0.14 | $0.28 | $0.22 | -13.7% |
| Together | $0.14 | $0.28 | $0.22 | -13.7% |
| Wafer | $0.05 | $0.35 | $0.23 | -10.6% |
| OpenInference | $0.03 | $0.40 | $0.25 | -2.9% |
| Sail Research | $0.02 | $0.42 | $0.26 | median |
| TensorX | $0.25 | $0.30 | $0.28 | +7.9% |
| Venice | $0.17 | $0.35 | $0.28 | +7.9% |
| Morph | $0.14 | $0.40 | $0.30 | +14.2% |
| Reka | $0.02 | $0.53 | $0.33 | +25.3% |
| AtlasCloud | $0.16 | $0.48 | $0.35 | +34.2% |
| Mancer 2 | $0.20 | $0.60 | $0.44 | +69.5% |
| Fireworks | $0.22 | $0.66 | $0.48 | +86.4% |
| SiliconFlow | $0.22 | $0.66 | $0.48 | +86.4% |
| GMICloud | $0.29 | $0.86 | $0.63 | +142.4% |
| Alibaba | $0.35 | $1.06 | $0.77 | +198.3% |
| NextBit | $0.35 | $1.06 | $0.77 | +198.3% |
| Baidu | $0.44 | $1.32 | $0.97 | +272.9% |
| Cloudflare | $0.44 | $1.32 | $0.97 | +272.9% |
| Novita | $0.44 | $1.32 | $0.97 | +272.9% |
| Phala | $0.44 | $1.32 | $0.97 | +272.9% |
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)$0.3025/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #56 of 167 budget models
← YOU ARE HERE | DeepSeek: DeepSeek V4 Flash 0731
Data Sources
Source
Aggregator & direct provider data
31 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/deepseek/deepseek-v4-flash-0731
# Response (truncated)
{ "model_id": "deepseek/deepseek-v4-flash-0731", "name": "DeepSeek: DeepSeek V4 Flash 0731", "blended_price_per_m": 0.2596, "sit_adjusted_price": 0.302471 }