Hy4 preview API pricing
As of October 22, 2026, Tencent Hy4 preview costs $0.834 per million input tokens and $2.501 per million output tokens on Tencent's own API, with cached input at $0.0378 per million.
Hy4 preview benchmarks and specs · Every Tencent model's price
- Input, per million tokens$0.834
- Output, per million tokens$2.501
- Cached input, per million$0.0378
- Context window1.05M tokens
- Max output64K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0021 | $2.08 | Yes |
| Repository review | 50K input + 3K output tokens | $0.049 | $49.20 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.192 | $191.81 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | Not computable | Not computable |
Price history
We have read Tencent's own price every day since October 21, 2026. It has not changed yet; any change will be listed here with its date.
- October 21, 2026 First recorded: $0.834 input, $2.501 output
Cheaper models as good as Hy4 preview
Models within two points of Hy4 preview or above it on the Vibe Coding Index, with a lower output price. Cheapest first.
- MiMo-V2.6-Flash$0.28 Coding 54.7 against 44.3 · 89% cheaper output
- DeepSeek V4 Flash 0731$0.28 Coding 51.8 against 44.3 · 89% cheaper output
- MiMo-V2.5$0.336 Coding 50.0 against 44.3 · 87% cheaper output
- Claude Haiku 5.5$0.50 Coding 70.7 against 44.3 · 80% cheaper output
- GLM 5.3 Flash$0.50 Coding 57.7 against 44.3 · 80% cheaper output
Hy4 preview pricing questions
- How much does Hy4 preview cost per million tokens?
- $0.834 per million input tokens and $2.501 per million output tokens, as listed on OpenRouter on October 22, 2026.
- Does Hy4 preview support prompt caching?
- Yes. OpenRouter lists cached input at $0.0378 per million tokens, against $0.834 for uncached input.
- Is there a cheaper model as good as Hy4 preview?
- MiMo-V2.6-Flash scores 54.7 on the Vibe Coding Index, within two points of Hy4 preview or above it, and costs $0.28 per million output tokens.
- Has the price of Hy4 preview changed?
- Not since we started recording it daily on October 21, 2026.