← Model list
Hy3 (DeepInfra)
tencent·tencent/hy3-4·GA·Open weights·Hy series·NEW
Tencent Hy reasoning model for coding, instruction following, and agent tasks
At a glance
Reference price$0.14 / $0.58 per 1M
Cache read $0.035 · LLM Gateway
Lowest paid$0.14 / $0.58
LLM Gateway Gateway
Context262,144
Output limit131,072
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
Modalities
Text
Knowledge cutoff—
Released / updated2026-07-06 / 2026-07-06
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 1 providers1 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| LLM Gateway deepinfra/hy3 | Gateway | $0.14 | $0.58 | $0.035 | — | 262,144 | 131,072 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1LLM Gateway$44.40
The cheapest paid channel is the only channel.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = noneeffort = loweffort = high
Related models
Hy-MT2-30B-A3Bsame series$0.074 / $0.295Hy-MT2-1.8Bsame series$0.044 / $0.177Tencent: Hy-MT2-30B-A3Bsame series$0.074 / $0.295GPT-5 Nanocheaper alternative$0.05 / $0.40GLM-4.7-Flashcheaper alternative$0 / $0Hy3cheaper alternative$0 / $0Nemotron 3 Nano 30B A3Bcheaper alternative$0 / $0
Price historyone sample accumulated per data sync
Input list $0.14Output list $0.58Min blended $0.25
Price history accumulates from each data sync; currently only 1 sample(s) (2026-08-21). Each future sync adds a point, and once accumulated a line is drawn here.