Text model
tencent/hy3 pricing
Novita AI charges $0.14 per million input tokens and $0.58 per million output tokens for tencent/hy3, and $0.035 for cached input. Below: every rate that applies, what common workloads cost, and cheaper options.
- Input
- $0.14/ 1M
- Output
- $0.58/ 1M
- Cached input
- $0.035/ 1M
- Context
- 262.1Ktokens
All rates
| Tier | Input | Output | Cache read | Cache write |
|---|---|---|---|---|
| Standard | $0.14 | $0.58 | $0.035 | — |
USD per million tokens. Long-context tiers apply when the whole prompt, cached tokens included, passes the threshold.
Work it out
What common workloads cost
| Workload | Per call | Cost per call | Calls a month | Per month |
|---|---|---|---|---|
| Chat reply | 1,500 input and 400 output tokens | $0.000442 | 100,000 | $44.20 |
| RAG answer, cached context | 2,000 fresh + 4,000 cached input, 500 output | $0.00071 | 100,000 | $71.00 |
| Agent step | 4,000 fresh + 8,000 cached input, 800 output | $0.0013 | 250,000 | $326.00 |
| Batch summary | 3,000 input and 300 output tokens via the Batch API | — | 1,000,000 | — |
Planning a mix of models? Simulate a workload with tencent/hy3, alongside anything else you run.
Cheaper options
Current models that cost at least 15% less for a typical chat reply. Cheaper isn't always equivalent: test quality on your own prompts, then use veqen diff to see the impact at your volume.
| Model | Chat reply | Saving |
|---|---|---|
| novita/google/gemma-4-31b-it | $0.00037 | 16% |
| novita/qwen/qwen3-235b-a22b-instruct-2507 | $0.000367 | 17% |
| deepinfra/Qwen/Qwen3-235B-A22B-Instruct-2507 | $0.000355 | 20% |
| nebius/NousResearch/Hermes-4-70B | $0.000355 | 20% |
Price history
No price changes since Veqen started tracking this model.
Compare
Last verified with price book 2026-10-22. Sources: Novita AI pricing and LiteLLM's MIT-licensed price file. Track every call to this model, per customer or project: install the SDK.