BroadRouter

Hy4 Preview vs Hy4 API pricing

Updated

Hy4 Preview: USD 0.834 input, USD 2.501 output per 1M tokens (DeepInfra and 4 others). Hy4: USD 0.417 input, USD 1.2505 output per 1M tokens (GMI Cloud and 1 other, promotional). At 3 input tokens per output token, Hy4 Preview costs 2× as much as Hy4 (USD 1.251 vs USD 0.6254 per 1M).

Hy4 Preview is the first Preview release in its Tencent line, and Hy4 the newest main release at or before it (by version in the name), so this page shows how the new line is priced against the main model. Price only: every number is computed from prices read from each provider's own pricing page (linked per cell, newest check 2026-11-15), with no claim about quality, speed or accuracy.

How do Hy4 Preview and Hy4 differ on price?

Hy4 Preview and Hy4 prices side by side

USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.

Hy4 Preview and Hy4 API prices compared
PriceHy4 PreviewHy4
Model pageHy4 Preview
Tencent · 6 providers
Hy4
Tencent · 3 providers
Cheapest standard price, blended 3:1USD 1.251
USD 0.834 in / USD 2.501 out at DeepInfra and 4 others
DeepInfra page checked 2026-11-14
USD 0.6254 lower promo
USD 0.417 in / USD 1.2505 out at GMI Cloud and 1 other
GMI Cloud page checked 2026-11-15
Cheapest inputUSD 0.834
DeepInfra source
USD 0.417 lower promo
GMI Cloud source
Cheapest cached inputUSD 0.042
DeepInfra source
USD 0.021 lower promo
GMI Cloud source
Cheapest outputUSD 2.501
DeepInfra source
USD 1.2505 lower promo
GMI Cloud source
Cheapest non-promotional priceThe cheapest price is not promotional.USD 0.525 / USD 1.5625
Chutes, USD 0.7844 blended source
Maker's own APITencent publishes no paid standard price on its own API that we found.Tencent publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.834 / USD 2.501
input / output, 6 prices
USD 0.417 / USD 1.2505
input / output, 3 prices
Context window1,048,576 tokens, largest stated; from 262,144 at some providers1,048,576 tokens, largest stated; from 1,000,000 at some providers
Providers with a standard price63

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

What do Hy4 Preview and Hy4 cost for a real workload?

30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).

Monthly cost of three workloads on Hy4 Preview and Hy4
WorkloadHy4 PreviewHy4Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 77.31
DeepInfra
USD 38.66
GMI Cloud
USD 38.66
Hy4 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 180.65
DeepInfra
USD 90.33
GMI Cloud
USD 90.33
Hy4 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 514.53
DeepInfra
USD 257.26
GMI Cloud
USD 257.26
Hy4 lower

Hy4 is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 2× as much as the cheaper one.

Does the cheaper model change with your input:output ratio?

Hy4 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Hy4 Preview's, so the input:output ratio never changes the answer.

Price per 1M tokens of Hy4 Preview and Hy4 at different input:output mixes
Input : output tokensHy4 PreviewHy4
1 : 3 (long answers)USD 2.084
DeepInfra
USD 1.042 lower
GMI Cloud
1 : 1USD 1.667
DeepInfra
USD 0.8337 lower
GMI Cloud
3 : 1 (the site’s blend)USD 1.251
DeepInfra
USD 0.6254 lower
GMI Cloud
10 : 1 (retrieval, long prompts)USD 0.9855
DeepInfra
USD 0.4928 lower
GMI Cloud
30 : 1 (agents, big contexts)USD 0.8878
DeepInfra
USD 0.4439 lower
GMI Cloud

USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.

What do Hy4 Preview and Hy4 cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Hy4 Preview and Hy4 are not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: Hy4 vs Hy3 · every Hy4 Preview comparison · every Hy4 comparison · all 651 price comparisons

Questions

Is Hy4 Preview cheaper than Hy4?

No. On a blend of 3 input tokens to 1 output token, Hy4 costs USD 0.6254 per 1M tokens and Hy4 Preview USD 1.251, at each model's cheapest standard price. For input alone, Hy4 is cheaper (USD 0.417 against USD 0.834 per 1M); for output alone, Hy4 is (USD 1.2505 against USD 2.501). This compares price only, not quality.

What do Hy4 Preview and Hy4 cost per 1M tokens?

Hy4 Preview: from USD 0.834 input and USD 2.501 output at DeepInfra and 4 others; median of 6 standard prices USD 0.834 / USD 2.501. Hy4: from USD 0.417 input and USD 1.2505 output at GMI Cloud and 1 other (promotional); median of 3 standard prices USD 0.417 / USD 1.2505. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Hy4 Preview and Hy4?

2 providers have a standard price for both: GMI Cloud (USD 1.251 and USD 0.6254 at 3:1), Novita AI (USD 1.251 and USD 0.6254 at 3:1). The first 2 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 1.251 and USD 0.6254.

Which is cheaper for a coding agent or a chatbot, Hy4 Preview or Hy4?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 514.53 a month on Hy4 Preview (DeepInfra) against USD 257.26 on Hy4 (GMI Cloud), a difference of USD 257.26. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 77.31 a month on Hy4 Preview (DeepInfra) against USD 38.66 on Hy4 (GMI Cloud), a difference of USD 38.66. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.

At what input:output ratio does the cheaper of Hy4 Preview and Hy4 change?

Hy4 is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Hy4 Preview's, so the input:output ratio never changes the answer.

Do Hy4 Preview and Hy4 have cached input pricing?

Hy4 Preview from USD 0.042 per 1M cached input tokens (DeepInfra; 6 of 6 standard prices list a discount). Hy4 from USD 0.021 per 1M cached input tokens (GMI Cloud; 3 of 3 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Hy4 Preview or Hy4?

Both go up to 1,048,576 tokens on the providers that state it.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity