Tencent: Hy3
budgettencent/hy3
Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...
AA INDEX25.3
CONTEXT262K
MODALITYtext->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED12 min ago
Input
$0.14 /M
Output
$0.58 /M
Blended (40/60)
$0.40 /M
Cost / IQ
$0.6388 /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%
7d0%
Price History
30-day view, daily close
Low: $0.40/M
High: $0.40/M
Average: $0.40/M
Pricing Variants
Cached Input
$0.03/M
75% cheaper than standard
Provider Comparison
5 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓Tencent | $0.13 | $0.53 | $0.37 | -8.5% |
| GMICloud | $0.14 | $0.58 | $0.40 | median |
| Novita | $0.14 | $0.58 | $0.40 | median |
| Phala | $0.15 | $0.64 | $0.44 | +9.9% |
| AtlasCloud | $0.20 | $0.80 | $0.56 | +38.6% |
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)$0.6388/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 #153 of 189 budget models
← YOU ARE HERE | Tencent: Hy3
Data Sources
Source
Aggregator & direct provider data
5 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/tencent/hy3
# Response (truncated)
{ "model_id": "tencent/hy3", "name": "Tencent: Hy3", "blended_price_per_m": 0.404, "sit_adjusted_price": 0.638804 }