Hy3
$0.132 per 1M input tokens and $0.528 per 1M output tokens · 262K context · tools, reasoning, JSON, open weights.
Prices checked Oct 21, 2026 · tracked by LLM Cost Index since Oct 21, 2026
What Hy3 costs per month
Estimated monthly bill for typical workloads, using the cached-input price for repeated context. Try your own numbers in the cost calculator.
| Workload | Per month |
|---|---|
| Customer chatbot 1,000 conversations a day, 8 turns each | $70.49 |
| Document Q&A (RAG) 500 questions a day over retrieved documents | $14.95 |
| Coding / tool-using agent 200 tasks a day, long tool-heavy contexts | $33.46 |
| Content generation 30 long articles a day | $1.54 |
| Classification / extraction 100,000 short items a day | $143 |
Price history
We started tracking Hy3 on Oct 21, 2026; the chart appears as soon as there is a second data point. See all recent price changes.
Where to run Hy3: 5 providers
Tencent is the cheapest at $0.132 input / $0.528 output per 1M tokens. Uptime is the average over the last 30 days as reported by OpenRouter; see provider reliability.
| Provider | Input / 1M | Output / 1M | Context | Uptime | Notes |
|---|---|---|---|---|---|
| Tencent | $0.132 | $0.528 | 262K | 100% | fp8 |
| GMICloud | $0.14 | $0.58 | 262K | 100% | bf16 |
| Novita | $0.14 | $0.58 | 262K | 99.6% | — |
| Phala | $0.15 | $0.64 | 262K | 99.9% | — |
| AtlasCloud | $0.20 | $0.80 | 262K | 100% | fp8 |
Cheaper alternatives to Hy3
Models with the same tool calling, structured output for at least 20% less (3:1 input/output mix), most capable first.
| Model | Input / 1M | Output / 1M | Context | Capabilities |
|---|---|---|---|---|
| GLM 5.3 Flash Z.ai | $0.041 | $0.12 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.1 Flash inclusionAI | $0.075 | $0.225 | 262K | toolsreasoningJSON |
| MiMo-V2.6-Flash Xiaomi | $0.14 | $0.28 | 1.05M | visionaudiotoolsreasoningJSONopen weights |
| DeepSeek V4.1 Flash DeepSeek | $0.049 | $0.375 | 1.05M | visiontoolsreasoningJSONopen weights |
| Ling 3.0 Flash VL inclusionAI | $0.06 | $0.18 | 131K | visiontoolsreasoningJSONopen weights |
How to pay less for Hy3
For a customer chatbot (1,000 conversations a day, 8 turns each) that costs $91.87 a month at list price without caching:
| Option | Per month | You save |
|---|---|---|
| Move to GLM 5.3 Flash (similar capabilities) | $16.82 | $75.05 (82%) |
| Use prompt caching (60% of input cached) | $70.49 | $21.38 (23%) |
Other workloads: cut-your-bill tool for Hy3.
Specifications
| Model ID | tencent/hy3 |
| Input | text |
| Output | text |
| Tool calling | Yes |
| Structured output | Yes |
| Reasoning mode | Yes |
| Open weights | Yes — tencent/Hy3 |
| Released | Jul 6, 2026 |
FAQ
- How much does Hy3 cost?
- $0.132 per million input tokens and $0.528 per million output tokens; cached input costs $0.033 per million. Prices as of Oct 21, 2026.
- What is the context window of Hy3?
- 262K tokens, with up to 128K output tokens per response.
- Does Hy3 support images, tools and structured output?
- Images as input: no. Tool calling: yes. Structured (JSON) output: yes. Reasoning mode: yes.
- What are cheaper alternatives to Hy3?
- Models with the same key capabilities for at least 20% less include GLM 5.3 Flash ($0.041 / $0.12), Ling 3.1 Flash ($0.075 / $0.225), MiMo-V2.6-Flash ($0.14 / $0.28).
More from Tencent: all Tencent models · how we collect prices