BroadRouter

Hy3 vs MiMo v2.5 API pricing

Updated

Hy3: USD 0.132 input, USD 0.528 output per 1M tokens (SiliconFlow). MiMo v2.5: USD 0.14 input, USD 0.28 output per 1M tokens (Baidu and 1 other). At 3 input tokens per output token, Hy3 costs 32% more than MiMo v2.5 (USD 0.231 vs USD 0.175 per 1M).

Picked by the same-tier rule: both are in the second quarter of the indexed models by price (USD 0.1591 to USD 0.4569 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). Hy3 is the 2nd-closest-priced model from another maker to MiMo v2.5 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 Hy3 and MiMo v2.5 differ on price?

Hy3 and MiMo v2.5 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.

Hy3 and MiMo v2.5 API prices compared
PriceHy3MiMo v2.5
Model pageHy3
Tencent · 4 providers
MiMo v2.5
Xiaomi · 4 providers
Cheapest standard price, blended 3:1USD 0.231
USD 0.132 in / USD 0.528 out at SiliconFlow
SiliconFlow page checked 2026-11-14
USD 0.175 lower
USD 0.14 in / USD 0.28 out at Baidu and 1 other
Baidu page checked 2026-11-15
Cheapest inputUSD 0.132 lower
SiliconFlow source
USD 0.14
Baidu source
Cheapest cached inputUSD 0.033
SiliconFlow source
USD 0.0028 lower
Baidu source
Cheapest outputUSD 0.528
SiliconFlow source
USD 0.28 lower
Baidu source
Maker's own APITencent publishes no paid standard price on its own API that we found.Xiaomi publishes no paid standard price on its own API that we found.
Median standard priceUSD 0.14 / USD 0.58
input / output, 4 prices
USD 0.1445 / USD 0.3865
input / output, 4 prices
Context window262,144 tokens, largest stated; from 32,768 at some providers1,048,576 tokens, largest stated; from 32,768 at some providers
Providers with a standard price44

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

What do Hy3 and MiMo v2.5 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 Hy3 and MiMo v2.5
WorkloadHy3MiMo v2.5Difference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 16.04
SiliconFlow
USD 10.23
Baidu
USD 5.81
MiMo v2.5 lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 32.47
SiliconFlow
USD 27.92
Baidu
USD 4.55
MiMo v2.5 lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 133.65
SiliconFlow
USD 67.28
Baidu
USD 66.37
MiMo v2.5 lower

MiMo v2.5 is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 99% more than the cheaper one.

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

The cheaper model changes with the mix: below 31 input tokens per output token, MiMo v2.5 is cheaper; above 31, Hy3 is cheaper. At the site's 3:1 blend, MiMo v2.5 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 Hy3 and MiMo v2.5 at different input:output mixes
Input : output tokensHy3MiMo v2.5
1 : 3 (long answers)USD 0.429
SiliconFlow
USD 0.245 lower
Baidu
1 : 1USD 0.33
SiliconFlow
USD 0.21 lower
Baidu
3 : 1 (the site’s blend)USD 0.231
SiliconFlow
USD 0.175 lower
Baidu
10 : 1 (retrieval, long prompts)USD 0.168
SiliconFlow
USD 0.1527 lower
Baidu
30 : 1 (agents, big contexts)USD 0.1448
SiliconFlow
USD 0.1445 lower
Baidu

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

What do Hy3 and MiMo v2.5 cost per character in other languages?

Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Hy3 and MiMo v2.5 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 Hy3 comparison · every MiMo v2.5 comparison · all 651 price comparisons

Questions

Is Hy3 cheaper than MiMo v2.5?

No. On a blend of 3 input tokens to 1 output token, MiMo v2.5 costs USD 0.175 per 1M tokens and Hy3 USD 0.231, at each model's cheapest standard price. For input alone, Hy3 is cheaper (USD 0.132 against USD 0.14 per 1M); for output alone, MiMo v2.5 is (USD 0.28 against USD 0.528). This compares price only, not quality.

What do Hy3 and MiMo v2.5 cost per 1M tokens?

Hy3: from USD 0.132 input and USD 0.528 output at SiliconFlow; median of 4 standard prices USD 0.14 / USD 0.58. MiMo v2.5: from USD 0.14 input and USD 0.28 output at Baidu and 1 other; median of 4 standard prices USD 0.1445 / USD 0.3865. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Hy3 and MiMo v2.5?

1 provider has a standard price for both: Featherless (USD 1.75 and USD 0.235 at 3:1). Buying each model from its own cheapest provider costs USD 0.231 and USD 0.175.

Which is cheaper for a coding agent or a chatbot, Hy3 or MiMo v2.5?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 133.65 a month on Hy3 (SiliconFlow) against USD 67.28 on MiMo v2.5 (Baidu), a difference of USD 66.37. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 16.04 a month on Hy3 (SiliconFlow) against USD 10.23 on MiMo v2.5 (Baidu), a difference of USD 5.81. 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 Hy3 and MiMo v2.5 change?

The cheaper model changes with the mix: below 31 input tokens per output token, MiMo v2.5 is cheaper; above 31, Hy3 is cheaper. At the site's 3:1 blend, MiMo v2.5 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 Hy3 and MiMo v2.5 have cached input pricing?

Hy3 from USD 0.033 per 1M cached input tokens (SiliconFlow; 3 of 4 standard prices list a discount). MiMo v2.5 from USD 0.0028 per 1M cached input tokens (Baidu; 4 of 4 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, Hy3 or MiMo v2.5?

MiMo v2.5: up to 1,048,576 tokens, against 262,144 for Hy3, 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