BroadRouter

Hy4 API pricing

Updated

2 providers tie for the cheapest standard price for Hy4 on the 3:1 blend; GMI Cloud (promotional) charges USD 0.417 per 1M input tokens and USD 1.2505 per 1M output tokens. The median across 3 standard prices is USD 0.417 / USD 1.2505. Every price is read from the provider's own pricing page, checked 2026-11-15.

Tencent · slug hy4 · up to 1,048,576 tokens of context · 3 providers with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

Does Tencent sell Hy4 directly?

Tencent publishes no price for Hy4 on its own API that we could find, so this page compares hosts only.

Hy4 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.

Hy4 API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1GMI Cloud tied cheapest promo
tencent/hy4
Notes and source quote

Promotional price, 50% off list (list 0.834 in / 2.501 out / 0.042 cached).

“Price (per 1M tokens) 50% off Input $0.417 $0.834 Output $1.2505 $2.501 Cache Read $0.021 $0.042 Cache Write -”
USD 0.417USD 0.021USD 1.2505USD 0.62541,000,000BF16GMI Cloud page
checked 2026-11-15
re-checked 2026-11-16
2Novita AI tied cheapest promo
tencent/hy4
Notes and source quote

Promotional price; list 0.834 in / 2.501 out per 1M.

“Hy4 977K $0.417 /Mt · Cache Read $0.021 /Mt $0.834 /Mt · Cache Read $0.042 /Mt $1.2505 /Mt $2.501 /Mt”
USD 0.417USD 0.021USD 1.2505USD 0.62541,000,000not statedNovita AI page
checked 2026-11-14
re-checked 2026-11-16
3Chutes
tencent/Hy4
Notes and source quote
“Hy4 tencent/Hy4 $0.025 per 1M tokens $0.525 per 1M tokens $1.5625 per 1M tokens 1.0M”
USD 0.525USD 0.025USD 1.5625USD 0.78441,048,576not statedChutes page
checked 2026-11-15
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Hy4 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.
Monthly cost of three workloads on Hy4, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
GMI Cloud (promo)USD 38.66USD 90.33USD 257.26
Novita AI (promo)USD 38.66USD 90.33USD 257.26
ChutesUSD 48.38USD 113.44USD 320.63

For the support chatbot, the cheapest price (GMI Cloud and 1 other, tied, USD 38.66 a month) saves USD 0 against the median (USD 38.66). For the coding agent the gap is USD 0 a month.

Which Hy4 provider is cheapest for your traffic?

GMI Cloud and Novita AI share the lowest input price (USD 0.417) and the lowest output price (USD 1.2505), so they are the cheapest standard price at every mix of input and output tokens, before cache discounts.

Hy4: price per 1M tokens at 3 input to 1 output, by share of input served from cache
ProviderNo cache hits50% cached90% cached
GMI CloudUSD 0.6254 cheapestUSD 0.4769 cheapestUSD 0.3581 cheapest
Novita AIUSD 0.6254 cheapestUSD 0.4769 cheapestUSD 0.3581 cheapest
ChutesUSD 0.7844USD 0.5969USD 0.4469

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 3 providers publish a cached-input price below the input price: GMI Cloud (95% off), Novita AI (95% off), Chutes (95% off).

Context windows differ: 1,048,576 tokens at Chutes; 1,000,000 tokens at GMI Cloud and Novita AI. The cheapest row is not always the one that fits a long prompt.

Estimate your own bill

The Tencent models whose cheapest standard price is closest to Hy4's (USD 0.6254 blended):

Tencent models priced closest to Hy4
ModelCheapest inputCheapest outputMax contextProviders
Hy4 PreviewUSD 0.834USD 2.5011,048,5766
Hy3USD 0.132USD 0.528262,1444

Priced closest from other makers: Beam 1.0 501B A23B (Reflection AI, USD 0.60) · DeepSeek R1 Distill Qwen 32B (DeepSeek, USD 0.60) · GLM 5.3 FlashX (Z.ai, USD 0.59).

Compare Hy4 with

Also compared: vs Hy3.

Every Hy4 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 Hy4 API cost per token?

From USD 0.417 per 1M input tokens (USD 0.000000417 per token) and USD 1.2505 per 1M output tokens (USD 0.000001250 per token) at the cheapest standard price. The median of 3 standard prices is USD 0.417 input and USD 1.2505 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?

2 providers are tied for the cheapest: GMI Cloud (promotional price) and Novita AI (promotional price), each USD 0.6254 per 1M on a blend of 3 input tokens to 1 output token. For input alone the lowest price is USD 0.417 (GMI Cloud and 1 other, tied); for output alone, USD 1.2505 (GMI Cloud and 1 other, tied). Batch, flex, priority and fast tiers are shown in the table but not ranked.

Does Tencent sell Hy4 on its own API?

Tencent publishes no price for Hy4 on its own API that we could find, so there is no maker price to compare. The cheapest host is GMI Cloud at USD 0.417 / USD 1.2505 per 1M tokens.

Does Hy4 have cached input pricing?

All 3 standard prices include one. The lowest is USD 0.021 per 1M at GMI Cloud; the median is USD 0.021. Providers without one bill cached input at the input price. What cached input means.

What is the Hy4 context window?

Up to 1,048,576 tokens. 2 standard prices come with less, down to 1,000,000 tokens (GMI Cloud 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?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 257.26 a month at GMI Cloud, USD 257.26 at the median price and USD 320.63 at Chutes. Try your own numbers.

Is Hy4 free to use through an API?

No provider in our data lists a free price for Hy4 as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity