Hy3 API pricing
Updated
The cheapest standard price for Hy3 is SiliconFlow at USD 0.132 per 1M input tokens and USD 0.528 per 1M output tokens. The median across 4 standard prices is USD 0.14 / USD 0.58. Every price is read from the provider's own pricing page, checked 2026-11-15.
Does Tencent sell Hy3 directly?
Tencent publishes no price for Hy3 on its own API that we could find, so this page compares hosts only.
Hy3 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 7.6× the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | SiliconFlow cheapestNotes and source quoteContext shown as 262K. “Hy3 262K $0.132 $0.033 $0.528” | USD 0.132 | USD 0.033 | USD 0.528 | USD 0.231 | 262,144 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | GMI Cloudtencent/Hy3Notes and source quote“Price (per 1M tokens) Input $0.14 Output $0.58 Cache Read $0.035 Cache Write -” | USD 0.14 | USD 0.035 | USD 0.58 | USD 0.25 | 262,144 | BF16 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | Novita AItencent/hy3Notes and source quote“Hy3 256K $0.14 /Mt · Cache Read $0.035 /Mt $0.58 /Mt” | USD 0.14 | USD 0.035 | USD 0.58 | USD 0.25 | 262,144 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Featherlesstencent/Hy3Notes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). No cached price published. “PRICING: INPUT $1 / OUTPUT $4” | USD 1 | not published | USD 4 | USD 1.75 | 32,768 | FP8 | Featherless 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. 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 Hy3 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) |
|---|---|---|---|
| SiliconFlow | USD 16.04 | USD 32.47 | USD 133.65 |
| GMI Cloud | USD 17.37 | USD 34.74 | USD 143.55 |
| Novita AI | USD 17.37 | USD 34.74 | USD 143.55 |
| Featherless | USD 162.00 | USD 300.00 | exceeds context |
For the support chatbot, the cheapest price (SiliconFlow, USD 16.04 a month) saves USD 1.33 against the median (USD 17.37). For the coding agent the gap is USD 9.90 a month (7% lower).
Which Hy3 provider is cheapest for your traffic?
SiliconFlow has the lowest input price (USD 0.132) and the lowest output price (USD 0.528), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| SiliconFlow | USD 0.231 cheapest | USD 0.1939 cheapest | USD 0.1642 cheapest |
| GMI Cloud | USD 0.25 | USD 0.2106 | USD 0.1791 |
| Novita AI | USD 0.25 | USD 0.2106 | USD 0.1791 |
| Featherless (no cache price) | USD 1.75 | USD 1.75 | USD 1.75 |
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.
3 of 4 providers publish a cached-input price below the input price: SiliconFlow (75% off), GMI Cloud (75% off), Novita AI (75% off). Featherless publishes none, so cached tokens there bill at the input price.
Context windows differ: 262,144 tokens at SiliconFlow, GMI Cloud and Novita AI; 32,768 tokens at Featherless. The cheapest row is not always the one that fits a long prompt.
Estimate your own bill
- LLM API cost calculator with Hy3 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 Hy3 compare with other Tencent models?
The Tencent models whose cheapest standard price is closest to Hy3's (USD 0.231 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Hy4 | USD 0.417 | USD 1.2505 | 1,048,576 | 3 |
| Hy4 Preview | USD 0.834 | USD 2.501 | 1,048,576 | 6 |
Priced closest from other makers: DeepSeek V3.2 (DeepSeek, USD 0.234) · Qwen3 VL 30B A3B Instruct (Qwen, USD 0.2375) · DeepSeek V4.1 Flash (DeepSeek, USD 0.21).
Compare Hy3 with
- Hy4 vs Hy3: API price side by side
Also compared: vs Hy4.
Every Hy3 price comparison · All model-vs-model price comparisons
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 Hy3 API cost per token?
From USD 0.132 per 1M input tokens (USD 0.000000132 per token) and USD 0.528 per 1M output tokens (USD 0.000000528 per token) at the cheapest standard price. The median of 4 standard prices is USD 0.14 input and USD 0.58 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Hy3?
SiliconFlow, ranked on a blend of 3 input tokens to 1 output token (USD 0.231 per 1M). It is also the cheapest on both input and output. Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Tencent sell Hy3 on its own API?
Tencent publishes no price for Hy3 on its own API that we could find, so there is no maker price to compare. The cheapest host is SiliconFlow at USD 0.132 / USD 0.528 per 1M tokens.
Does Hy3 have cached input pricing?
3 of 4 standard prices include one. The lowest is USD 0.033 per 1M at SiliconFlow; the median is USD 0.035. Providers without one bill cached input at the input price. What cached input means.
What is the Hy3 context window?
Up to 262,144 tokens. 1 standard price comes with less, down to 32,768 tokens (Featherless). 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 Hy3?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 133.65 a month at SiliconFlow, USD 143.55 at the median price and USD 2,160 at Featherless. Try your own numbers.
Is Hy3 free to use through an API?
No provider in our data lists a free price for Hy3 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.