Hy4 Preview API pricing
Updated
Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), 5 tie for the lowest blended standard price for Hy4 Preview; DeepInfra charges USD 0.834 per 1M input tokens and USD 2.501 per 1M output tokens. The median across 6 standard prices is USD 0.834 / USD 2.501. Each price is read from the provider's own pricing page.
Does Tencent sell Hy4 Preview directly?
Tencent publishes no price for Hy4 Preview on its own API that we could find, so this page compares hosts only.
Hy4 Preview price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 25% above the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | DeepInfra tied cheapesttencent/Hy4-previewNotes and source quote“$0.834 in $2.501 out $0.042 cached / 1M tokens” | USD 0.834 | USD 0.042 | USD 2.501 | USD 1.251 | 1,048,576 | FP4 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | GMI Cloud tied cheapesttencent/hy4-previewNotes and source quote“Price (per 1M tokens) Input $0.834 Output $2.501 Cache Read $0.042 Cache Write -” | USD 0.834 | USD 0.042 | USD 2.501 | USD 1.251 | 262,144 | BF16 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | Hyperbolic tied cheapesthy4-previewNotes and source quoteContext shown on page as "1M" (rounded); stored as the decimal value. “Hy4 Preview hy4-preview Tencent · 1M context · Text $0.834 $2.501 $0.042” | USD 0.834 | USD 0.042 | USD 2.501 | USD 1.251 | 1,000,000 | not stated | Hyperbolic page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Novita AI tied cheapesttencent/hy4-previewNotes and source quote“Hy4 Preview 977K $0.834 /Mt · Cache Read $0.042 /Mt $2.501 /Mt” | USD 0.834 | USD 0.042 | USD 2.501 | USD 1.251 | 1,000,000 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 5 | SiliconFlow tied cheapestNotes and source quoteContext shown as 1049K. “Hy4-preview 1049K $0.834 $0.042 $2.501” | USD 0.834 | USD 0.042 | USD 2.501 | USD 1.251 | 1,048,576 | not stated | SiliconFlow page checked 2026-11-15 not auto-checked (page loads prices with JavaScript) |
| 6 | Venicehy4-previewNotes and source quote“| Hy4 Preview | `hy4-preview` | $1.0425 | $3.12625 | $0.0525 | — | Private |” | USD 1.0425 | USD 0.0525 | USD 3.12625 | USD 1.563 | 1,048,576 | FP4 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. "Not auto-checked" rows are on pages that load prices with JavaScript; their checked date is a read with a page renderer. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Hy4 Preview cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| DeepInfra | USD 77.31 | USD 180.65 | USD 514.53 |
| GMI Cloud | USD 77.31 | USD 180.65 | USD 514.53 |
| Hyperbolic | USD 77.31 | USD 180.65 | USD 514.53 |
| Novita AI | USD 77.31 | USD 180.65 | USD 514.53 |
| SiliconFlow | USD 77.31 | USD 180.65 | USD 514.53 |
| Venice | USD 96.64 | USD 225.81 | USD 643.16 |
For the support chatbot, the cheapest price (DeepInfra and 4 others, tied, USD 77.31 a month) saves USD 0 against the median (USD 77.31). For the coding agent the gap is USD 0 a month.
Which Hy4 Preview provider is cheapest for your traffic?
DeepInfra, GMI Cloud, Hyperbolic, Novita AI and SiliconFlow share the lowest input price (USD 0.834) and the lowest output price (USD 2.501), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| DeepInfra | USD 1.251 cheapest | USD 0.9537 cheapest | USD 0.7161 cheapest |
| GMI Cloud | USD 1.251 cheapest | USD 0.9537 cheapest | USD 0.7161 cheapest |
| Hyperbolic | USD 1.251 cheapest | USD 0.9537 cheapest | USD 0.7161 cheapest |
| Novita AI | USD 1.251 cheapest | USD 0.9537 cheapest | USD 0.7161 cheapest |
| SiliconFlow | USD 1.251 cheapest | USD 0.9537 cheapest | USD 0.7161 cheapest |
| Venice | USD 1.563 | USD 1.192 | USD 0.8952 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
All 6 providers publish a cached-input price below the input price: DeepInfra (95% off), GMI Cloud (95% off), Hyperbolic (95% off), Novita AI (95% off), SiliconFlow (95% off), Venice (95% off).
Context windows differ: 1,048,576 tokens at DeepInfra, SiliconFlow and Venice; 1,000,000 tokens at Hyperbolic and Novita AI; 262,144 tokens at GMI Cloud. The cheapest row is not always the one that fits a long prompt.
Estimate your own bill
- LLM API cost calculator with Hy4 Preview preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Hy4 Preview compare with other Tencent models?
The Tencent models whose cheapest standard price is closest to Hy4 Preview's (USD 1.251 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Hy4 | USD 0.417 | USD 1.2505 | 1,048,576 | 3 |
| Hy3 | USD 0.132 | USD 0.528 | 262,144 | 4 |
Priced closest from other makers: Qwen3 235B A22B Thinking 2507 FP8 (Qwen, USD 1.212) · DeepSeek V4 Pro 0813 (DeepSeek, USD 1.30) · Kimi K2.7 Code (Moonshot AI, USD 1.20).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Hy4 Preview API cost per token?
From USD 0.834 per 1M input tokens (USD 0.000000834 per token) and USD 2.501 per 1M output tokens (USD 0.000002501 per token) at the lowest standard prices we found. The median of 6 standard prices is USD 0.834 input and USD 2.501 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Hy4 Preview?
Among the 6 providers we checked (prices read 2026-11-14 to 2026-11-15), 5 are tied for the lowest price: DeepInfra, GMI Cloud, Hyperbolic, Novita AI and SiliconFlow, each USD 1.251 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.834 (DeepInfra and 4 others, tied); for output alone, USD 2.501 (DeepInfra and 4 others, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Tencent sell Hy4 Preview on its own API?
Tencent publishes no price for Hy4 Preview on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is DeepInfra at USD 0.834 / USD 2.501 per 1M tokens.
Does Hy4 Preview have cached input pricing?
All 6 standard prices include one. The lowest is USD 0.042 per 1M at DeepInfra; the median is USD 0.042. Providers without one bill cached input at the input price. What cached input means.
What is the Hy4 Preview context window?
Up to 1,048,576 tokens. 3 standard prices come with less, down to 262,144 tokens (GMI Cloud, Hyperbolic and Novita AI). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Hy4 Preview?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 514.53 a month at DeepInfra, USD 514.53 at the median price and USD 643.16 at Venice. Try your own numbers.
Is Hy4 Preview free to use through an API?
No provider in our data lists a free price for Hy4 Preview as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.