tencent/Hy3 pricing
Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tencent Hy Team. Following the Hy3 Preview launch in late April, we gathered feedback from 50+ products and scaled up post-training with higher quality data. tencent/Hy3 from DeepInfra costs $0.130 per 1M input tokens and $0.530 per 1M output tokens. Cached input is $0.033 per 1M. Context window 262,144 tokens.
API id tencent/Hy3 · DeepInfra · source · updated 2026-09-25 · general-purpose
$0.130
Input / 1M tokens
$0.530
Output / 1M tokens
$0.033
Cached input / 1M
262K
Context window
tencent/Hy3 specifications
- Provider
- DeepInfra
- API id
tencent/Hy3- Model type
- general-purpose
- Context window
- 262K tokens
- Max output
- not published
- Currency
- USD
- Price source
- Provider API
- Last checked
- 2026-09-25
What tencent/Hy3 costs in practice
| Workload | Input tokens | Output tokens | Estimated cost |
|---|---|---|---|
| Short chat turn | 1,000 | 500 | $0.0004 |
| Document summary | 50,000 | 2,000 | $0.0076 |
| 1M tokens in, 200K out | 1,000,000 | 200,000 | $0.24 |
Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.
tencent/Hy3 price history
| Recorded | Input /1M | Output /1M |
|---|---|---|
| 2026-09-22 | $0.130 | $0.530 |
| 2026-08-27 | $0.140 | $0.580 |
Common questions
- How much does tencent/Hy3 cost per 1M tokens?
- tencent/Hy3 costs $0.130 per 1M input tokens and $0.530 per 1M output tokens on the standard tier. Cached input is $0.033 per 1M.
- What is tencent/Hy3's context window?
- tencent/Hy3 accepts up to 262,144 tokens in a single request.
- Is there a cheaper DeepInfra model than tencent/Hy3?
- Yes. deepseek-ai/DeepSeek-V4-Flash is $0.090 per 1M input tokens versus $0.130 for tencent/Hy3, with a 1,048,576 token context window.
- Where does this tencent/Hy3 price come from?
- From the OpenRouter catalogue, because DeepInfra does not publish machine-readable pricing. OpenRouter is a reseller, so its rate can differ from DeepInfra's own — verify before committing spend.
Head-to-head comparisons
Other DeepInfra models
- XiaomiMiMo/MiMo-V2.6-Flash $0.140
- anthropic/claude-fable-5 $10.00
- Qwen/Qwen3-VL-235B-A22B-Instruct $0.200
- Qwen/Qwen3-14B $0.120
- Qwen/Qwen3-Max-Thinking $1.20
- ByteDance/Seed-2.0-mini $0.100
- deepseek-ai/DeepSeek-V4-Flash-0731 $0.060
- zai-org/GLM-5.3-Flash $0.150
- anthropic/claude-opus-5-5 $4.00
- meta-llama/Llama-4-Scout-17B-16E-Instruct $0.100
- ibm-granite/granite-4.2-8b $0.060
- Qwen/Qwen3-30B-A3B $0.120
- openai/gpt-oss-120b-Ultra $0.200
- ByteDance/Seed-2.0-pro $0.500
- thinkingmachines/Inkling $0.950
- zai-org/GLM-4.6 $0.500