Hy3
Summary
Hy3 is an open-weight language model from Tencent (Hunyuan), released on 6 Jul 2026. It accepts text and generates text, with a 262K-token context window and up to 262K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.13 per million input tokens and $0.53 per million output tokens (SiliconFlow), across 5 providers we track.
Tencent Hy reasoning model for coding, instruction following, and agent tasks
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Tencent (Hunyuan) |
|---|---|
| Release date | 6 Jul 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | apache-2.0 [Hugging Face] |
| Parameters | 299B [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 262K tokens [models.dev] |
| Input | Text [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | tencent/Hy3 [Hugging Face] |
Hy3 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| SiliconFlow tencent/Hy3 | $0.13 | $0.53 | $0.03 | 262K | models.dev, 18 Nov 2026 |
| OpenRouter tencent/hy3 | $0.13 | $0.53 | $0.03 | 262K | OpenRouter, 18 Nov 2026 |
| Hugging Face Inference Providers tencent/Hy3 | $0.14 | $0.58 | – | 262K | models.dev, 18 Nov 2026 |
| Novita AI tencent/hy3 | $0.14 | $0.58 | $0.04 | 262K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway tencent/hy3 | $0.14 | $0.58 | $0.04 | 262K | models.dev, 18 Nov 2026 |
Running Hy3 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 181 GB | 185 GB | 193 GB |
| Q8_0 (8-bit) | 317 GB | 321 GB | 329 GB |
| FP16 / BF16 (16-bit) | 598 GB | 601 GB | 609 GB |
At 4-bit with an 8K conversation, Hy3 needs about 185 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Hy3?
Hy3 has a context window of 262,144 tokens (262K) and can generate up to 262,144 tokens in a single response, according to models.dev.
How much does the Hy3 API cost?
Hy3 is listed from $0.13 per million input tokens and $0.53 per million output tokens (SiliconFlow). Prices last verified 18 Nov 2026.
Is Hy3 open source?
Hy3 is an open-weight model: its weights are published on Hugging Face as tencent/Hy3 under the apache-2.0 license. Check the license terms before commercial use.
When was Hy3 released?
Tencent (Hunyuan) released Hy3 on 6 Jul 2026, according to models.dev.
Which providers offer Hy3?
We track Hy3 on 5 providers: SiliconFlow, OpenRouter, Hugging Face Inference Providers, Novita AI, Vercel AI Gateway.
How much VRAM does Hy3 need?
About 185 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 321 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Ternary Bonsai 2 27B | Prism ML | 18 Sept 2026 | 262K | $0.07 | $0.50 | Open |
| Gemma 4 12B IT | Google DeepMind | 9 Jun 2026 | 262K | $0.10 | $0.30 | Open |
| Gemma 4 31B IT | Google DeepMind | 2 Apr 2026 | 262K | $0.14 | $0.40 | Open |
| Mistral Small 4 | Mistral AI | 16 Mar 2026 | 262K | $0.15 | $0.60 | Open |
| Qwen3.6 35B-A3B | Alibaba (Qwen) | 17 Apr 2026 | 262K | $0.10 | $0.90 | Open |
| Step 3.7 Flash | StepFun | 29 May 2026 | 256K | $0.20 | $1.15 | Open |
Change history
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- OpenRouter price changed: input $0.08 → $0.13, output $0.33 → $0.53 per 1M tokens
- OpenRouter price changed: input $0.13 → $0.08, output $0.53 → $0.33 per 1M tokens
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- OpenRouter price changed: input $0.08 → $0.13, output $0.33 → $0.53 per 1M tokens
- OpenRouter price changed: input $0.13 → $0.08, output $0.53 → $0.33 per 1M tokens
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- Max output changed from 128K to 262K
- Max output changed from 262K to 128K
- Now listed on Novita AI
- No longer listed on deepinfra
- Max output changed from 128K to 262K
- OpenRouter price changed: input $0.08 → $0.13, output $0.33 → $0.53 per 1M tokens
- OpenRouter price changed: input $0.13 → $0.08, output $0.53 → $0.33 per 1M tokens
Sources
- https://openrouter.ai/tencent/hy3
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/tencent/hy3.toml
- https://huggingface.co/tencent/Hy3
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/tencent/Hy3.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/tencent/Hy3.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/tencent/hy3.toml