BroadRouter

DeepSeek R1 0528 vs Hy4 API pricing

Updated

DeepSeek R1 0528: USD 0.385 input, USD 1.625 output per 1M tokens (Featherless). 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, DeepSeek R1 0528 costs 11% more than Hy4 (USD 0.695 vs USD 0.6254 per 1M).

Picked by the same-tier rule: both are in the third quarter of the indexed models by price (USD 0.4512 to USD 1.40 per 1M tokens at 3:1) and in the same size class, mid-size (no tier word, 40B to 200B parameters or no size in the name). DeepSeek R1 0528 is the 1st-closest-priced model from another maker to Hy4 in that bucket. 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 DeepSeek R1 0528 and Hy4 differ on price?

DeepSeek R1 0528 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.

DeepSeek R1 0528 and Hy4 API prices compared
PriceDeepSeek R1 0528Hy4
Model pageDeepSeek R1 0528
DeepSeek · 5 providers
Hy4
Tencent · 3 providers
Cheapest standard price, blended 3:1USD 0.695
USD 0.385 in / USD 1.625 out at Featherless
Featherless page checked 2026-11-15
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 0.385 lower
Featherless source
USD 0.417 promo
GMI Cloud source
Cheapest cached inputUSD 0.23
GMI Cloud source
USD 0.021 lower promo
GMI Cloud source
Cheapest outputUSD 1.625
Featherless 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 APIDeepSeek 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 0.57 / USD 2.29
input / output, 5 prices
USD 0.417 / USD 1.2505
input / output, 3 prices
Context window163,840 tokens, largest stated; from 131,072 at some providers1,048,576 tokens, largest stated; from 1,000,000 at some providers
Providers with a standard price53

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

What do DeepSeek R1 0528 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 DeepSeek R1 0528 and Hy4
WorkloadDeepSeek R1 0528Hy4Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 63.90
Featherless
USD 38.66
GMI Cloud
USD 25.24
Hy4 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 116.78
Featherless
USD 90.33
GMI Cloud
USD 26.45
Hy4 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 711.90
GMI Cloud
USD 257.26
GMI Cloud
USD 454.63
Hy4 lower

Hy4 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 2.77× as much as the cheaper one.

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

The cheaper model changes with the mix: below 12 input tokens per output token, Hy4 is cheaper; above 12, DeepSeek R1 0528 is cheaper. At the site's 3:1 blend, Hy4 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Price per 1M tokens of DeepSeek R1 0528 and Hy4 at different input:output mixes
Input : output tokensDeepSeek R1 0528Hy4
1 : 3 (long answers)USD 1.315
Featherless
USD 1.042 lower
GMI Cloud
1 : 1USD 1.005
Featherless
USD 0.8337 lower
GMI Cloud
3 : 1 (the site’s blend)USD 0.695
Featherless
USD 0.6254 lower
GMI Cloud
10 : 1 (retrieval, long prompts)USD 0.4977
Featherless
USD 0.4928 lower
GMI Cloud
30 : 1 (agents, big contexts)USD 0.425 lower
Featherless
USD 0.4439
GMI Cloud

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

What do DeepSeek R1 0528 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 is not among them. Count tokens on your own text with the counters below.

Check it on your own traffic

More comparisons: DeepSeek R1 0528 vs DeepSeek R1 · Hy4 vs Hy3 · every DeepSeek R1 0528 comparison · every Hy4 comparison · all 662 price comparisons

Questions

Is DeepSeek R1 0528 cheaper than Hy4?

No. On a blend of 3 input tokens to 1 output token, Hy4 costs USD 0.6254 per 1M tokens and DeepSeek R1 0528 USD 0.695, at each model's cheapest standard price. For input alone, DeepSeek R1 0528 is cheaper (USD 0.385 against USD 0.417 per 1M); for output alone, Hy4 is (USD 1.2505 against USD 1.625). This compares price only, not quality.

What do DeepSeek R1 0528 and Hy4 cost per 1M tokens?

DeepSeek R1 0528: from USD 0.385 input and USD 1.625 output at Featherless; median of 5 standard prices USD 0.57 / USD 2.29. 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 DeepSeek R1 0528 and Hy4?

2 providers have a standard price for both: GMI Cloud (USD 1 and USD 0.6254 at 3:1), Novita AI (USD 1.15 and USD 0.6254 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.695 and USD 0.6254.

Which is cheaper for a coding agent or a chatbot, DeepSeek R1 0528 or Hy4?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 711.90 a month on DeepSeek R1 0528 (GMI Cloud) against USD 257.26 on Hy4 (GMI Cloud), a difference of USD 454.63. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 63.90 a month on DeepSeek R1 0528 (Featherless) against USD 38.66 on Hy4 (GMI Cloud), a difference of USD 25.24. 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 DeepSeek R1 0528 and Hy4 change?

The cheaper model changes with the mix: below 12 input tokens per output token, Hy4 is cheaper; above 12, DeepSeek R1 0528 is cheaper. At the site's 3:1 blend, Hy4 is cheaper. More input per output token, as with retrieval or agents that resend long contexts, favours the lower input price; long answers favour the lower output price.

Do DeepSeek R1 0528 and Hy4 have cached input pricing?

DeepSeek R1 0528 from USD 0.23 per 1M cached input tokens (GMI Cloud; 3 of 5 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, DeepSeek R1 0528 or Hy4?

Hy4: up to 1,048,576 tokens, against 163,840 for DeepSeek R1 0528, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity