DeepSeek: DeepSeek V3.1 Terminus
microdeepseek/deepseek-v3.1-terminus
DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...
AA INDEX13.9
CONTEXT164K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED2 min ago
Input
$0.28 /M
Output
$1.00 /M
Blended (40/60)
$0.71 /M
Cost / IQ
$2.0502 /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↑ 0.8%
7d↑ 0.8%
Price History
30-day view, daily close
Low: $0.71/M
High: $0.71/M
Average: $0.71/M
Pricing Variants
Cached Input
$0.14/M
55% cheaper than standard
Provider Comparison
4 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Novita | $0.27 | $1.00 | $0.71 | -0.8% |
| SiliconFlow | $0.27 | $1.00 | $0.71 | -0.8% |
| AtlasCloud | $0.30 | $1.00 | $0.72 | +0.8% |
| StreamLake | $0.34 | $1.03 | $0.75 | +5.6% |
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)$2.0502/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 #292 of 581 micro models
← YOU ARE HERE | DeepSeek: DeepSeek V3.1 Terminus
Data Sources
Source
Aggregator & direct provider data
4 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/deepseek/deepseek-v3.1-terminus
# Response (truncated)
{ "model_id": "deepseek/deepseek-v3.1-terminus", "name": "DeepSeek: DeepSeek V3.1 Terminus", "blended_price_per_m": 0.714, "sit_adjusted_price": 2.050152 }