Model Library
TencentReleased April 23, 2026Hy3-preview
Tencent · Released April 23, 2026
Intelligence score
26
At a glance
- Intelligence
- 26
- Speed
- 202.9tokens/sec
- Latency
- 3.26stime to first token
- Input price
- $0.12per 1M tokens
- Output price
- $0.43per 1M tokens
- Context window
- 260Ktokens
- Parameters
- 295billions
Summary
Comparison summary
Hy3-preview (Non-reasoning) scores 26 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 17). Hy3-preview (Non-reasoning) generates output at 202.9 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s). Hy3-preview (Non-reasoning) costs $0.12 per 1M input tokens (very competitive, median: $0.60) and $0.43 per 1M output tokens (very competitive, median: $2.40), based on the median across providers serving the model.
Specifications
Technical specifications
| Model name | Hy3-preview |
|---|---|
| Provider | Tencent |
| Release date | April 23, 2026 |
| Intelligence score | 26 |
| Speed | 202.9 tokens/sec |
| Latency (TTFT) | 3.26s |
| Input price | $0.12 / 1M tokens |
| Output price | $0.43 / 1M tokens |
| Context window | 260,000 tokens |
| Parameters | 295B |
| Reasoning | No |
| Input modalities | text |
| Output modalities | — |
| Open weights | Yes |
| License | TENCENT HY COMMUNITY LICENSE AGREEMENT |
| API availability | — |
| Source | Model Intelligence legacy profile: hy3-non-reasoning |
Pricing
Token prices
Price per 1M tokens
Hy3-preview, as listed in the catalog record
- Input$0.12
- Output$0.43
| Token type | Price per 1M |
|---|---|
| Input | $0.12 |
| Output | $0.43 |
Model Intelligence legacy profile: hy3-non-reasoning
FAQ · 20
Frequently asked questions
Hy3-preview (Non-reasoning) was released on April 23, 2026.
Hy3-preview (Non-reasoning) was created by Tencent.
Hy3-preview (Non-reasoning) scores 26 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other open weight non-reasoning models of similar size (median: 17).
Hy3-preview (Non-reasoning) generates output at 202.9 tokens per second (based on the median across providers serving the model), which is well above average compared to other open weight non-reasoning models of similar size (median: 58.3 t/s).
Hy3-preview (Non-reasoning) has a time to first token (TTFT) of 3.26s (based on the median across providers serving the model), which is at the higher end compared to other open weight non-reasoning models of similar size (median: 2.33s).
Hy3-preview (Non-reasoning) costs $0.12 per 1M input tokens (very competitive, median: $0.60) and $0.43 per 1M output tokens (very competitive, median: $2.40), based on the median across providers serving the model.
Hy3-preview (Non-reasoning) costs $0.12 per 1M input tokens and $0.43 per 1M output tokens (based on the median across providers serving the model). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.10 per 1M tokens. Pricing may vary by provider.
No, Hy3-preview (Non-reasoning) is not a reasoning model. It provides direct responses without extended chain-of-thought reasoning.
Hy3-preview (Non-reasoning) supports text input.
Hy3-preview (Non-reasoning) supports text output.
No, Hy3-preview (Non-reasoning) does not support image input. It can only process text.
No, Hy3-preview (Non-reasoning) is not multimodal. It only supports text input.
Hy3-preview (Non-reasoning) has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.
Yes, Hy3-preview (Non-reasoning) is open weights. The model weights are publicly available and can be downloaded for self-hosting.
Hy3-preview (Non-reasoning) has 295 billion parameters (21 billion active).
Hy3-preview (Non-reasoning) is a Mixture of Experts (MoE) model with 295 billion total parameters, but only 21 billion active parameters are used during inference.
Hy3-preview (Non-reasoning) is released under the TENCENT HY COMMUNITY LICENSE AGREEMENT license. This license allows commercial use.
Hy3-preview (Non-reasoning) achieves a score of 26 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
Yes, Hy3-preview (Non-reasoning) is available via API through 2 providers.
Hy3-preview (Non-reasoning) is available through 2 API providers.