BroadRouter

Qwen3.5 397B A17B vs Qwen3.5 122B A10B API pricing

Updated

Qwen3.5 397B A17B: USD 0.45 input, USD 3 output per 1M tokens (Chutes and 1 other). Qwen3.5 122B A10B: USD 0.26 input, USD 2.08 output per 1M tokens (SiliconFlow). At 3 input tokens per output token, Qwen3.5 397B A17B costs 52% more than Qwen3.5 122B A10B (USD 1.087 vs USD 0.715 per 1M).

Qwen3.5 397B A17B and Qwen3.5 122B A10B are neighbouring sizes of the same Qwen generation (397B with 17B active and 122B with 10B active parameters, by name). 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 Qwen3.5 397B A17B and Qwen3.5 122B A10B differ on price?

Qwen3.5 397B A17B and Qwen3.5 122B A10B 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.

Qwen3.5 397B A17B and Qwen3.5 122B A10B API prices compared
PriceQwen3.5 397B A17BQwen3.5 122B A10B
Model pageQwen3.5 397B A17B
Qwen · 7 providers
Qwen3.5 122B A10B
Qwen · 4 providers
Cheapest standard price, blended 3:1USD 1.087
USD 0.45 in / USD 3 out at Chutes and 1 other
Chutes page checked 2026-11-15
USD 0.715 lower
USD 0.26 in / USD 2.08 out at SiliconFlow
SiliconFlow page checked 2026-11-14
Cheapest inputUSD 0.45
Chutes source
USD 0.26 lower
SiliconFlow source
Cheapest cached inputUSD 0.045
Chutes source
No standard price lists a cache price; cached tokens bill at the input price.
Cheapest outputUSD 3
Chutes source
USD 2.08 lower
SiliconFlow source
Maker's own APIUSD 0.60 / USD 3.60
Alibaba Cloud source
USD 0.40 / USD 3.20
Alibaba Cloud source
Median standard priceUSD 0.55 / USD 3.60
input / output, 7 prices
USD 0.40 / USD 3.20
input / output, 4 prices
Context window262,144 tokens, largest stated262,144 tokens, largest stated
Providers with a standard price74

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

What do Qwen3.5 397B A17B and Qwen3.5 122B A10B 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 Qwen3.5 397B A17B and Qwen3.5 122B A10B
WorkloadQwen3.5 397B A17BQwen3.5 122B A10BDifference
Support chatbot
2,000 requests a day, 1,500 input tokens (60% cached), 300 output
USD 72.63
Chutes
USD 60.84
SiliconFlow
USD 11.79
Qwen3.5 122B A10B lower
RAG over documents
1,000 requests a day, 8,000 input tokens (30% cached), 500 output
USD 123.84
Chutes
USD 93.60
SiliconFlow
USD 30.24
Qwen3.5 122B A10B lower
Coding agent (one developer)
1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning
USD 460.35
Chutes
USD 655.20
SiliconFlow
USD 194.85
Qwen3.5 397B A17B lower

The cheaper model depends on the workload: Qwen3.5 122B A10B for Support chatbot, Qwen3.5 122B A10B for RAG over documents, Qwen3.5 397B A17B for Coding agent (one developer). Cache-heavy work rewards a low cached-input price. The widest gap is on Coding agent (one developer): the dearer model costs 42% more than the cheaper one.

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

Qwen3.5 122B A10B 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 Qwen3.5 397B A17B's, so the input:output ratio never changes the answer.

Price per 1M tokens of Qwen3.5 397B A17B and Qwen3.5 122B A10B at different input:output mixes
Input : output tokensQwen3.5 397B A17BQwen3.5 122B A10B
1 : 3 (long answers)USD 2.363
Chutes
USD 1.625 lower
SiliconFlow
1 : 1USD 1.725
Chutes
USD 1.17 lower
SiliconFlow
3 : 1 (the site’s blend)USD 1.087
Chutes
USD 0.715 lower
SiliconFlow
10 : 1 (retrieval, long prompts)USD 0.6818
Chutes
USD 0.4255 lower
SiliconFlow
30 : 1 (agents, big contexts)USD 0.5323
Chutes
USD 0.3187 lower
SiliconFlow

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

What do Qwen3.5 397B A17B and Qwen3.5 122B A10B cost per character in other languages?

Cost to send 1M characters at each model's cheapest non-promotional standard input price, with the Qwen3.8 27B tokenizer for Qwen3.5 397B A17B (the same one for both, so the gap equals the price gap):

Input cost per 1M characters by language, Qwen3.5 397B A17B and Qwen3.5 122B A10B
ContentQwen3.5 397B A17BQwen3.5 122B A10B
EnglishUSD 0.100
Chutes
USD 0.058 lower
SiliconFlow
Arabic MSAUSD 0.139
Chutes
USD 0.081 lower
SiliconFlow
Egyptian ArabicUSD 0.147
Chutes
USD 0.085 lower
SiliconFlow
HindiUSD 0.190
Chutes
USD 0.110 lower
SiliconFlow
ChineseUSD 0.260
Chutes
USD 0.150 lower
SiliconFlow
SpanishUSD 0.104
Chutes
USD 0.060 lower
SiliconFlow
CodeUSD 0.125
Chutes
USD 0.072 lower
SiliconFlow

From the real cost by language dataset (measured tokens per character on FLORES-200 and other texts). Your own text will differ.

Check it on your own traffic

More comparisons: Qwen3.5 122B A10B vs Qwen3.5 35B A3B · every Qwen3.5 397B A17B comparison · every Qwen3.5 122B A10B comparison · all 662 price comparisons

Questions

Is Qwen3.5 397B A17B cheaper than Qwen3.5 122B A10B?

No. On a blend of 3 input tokens to 1 output token, Qwen3.5 122B A10B costs USD 0.715 per 1M tokens and Qwen3.5 397B A17B USD 1.087, at each model's cheapest standard price. For input alone, Qwen3.5 122B A10B is cheaper (USD 0.26 against USD 0.45 per 1M); for output alone, Qwen3.5 122B A10B is (USD 2.08 against USD 3). This compares price only, not quality.

What do Qwen3.5 397B A17B and Qwen3.5 122B A10B cost per 1M tokens?

Qwen3.5 397B A17B: from USD 0.45 input and USD 3 output at Chutes and 1 other; Alibaba Cloud's own API charges USD 0.60 / USD 3.60; median of 7 standard prices USD 0.55 / USD 3.60. Qwen3.5 122B A10B: from USD 0.26 input and USD 2.08 output at SiliconFlow; Alibaba Cloud's own API charges USD 0.40 / USD 3.20; median of 4 standard prices USD 0.40 / USD 3.20. Each price is read from the provider's own pricing page; the source is linked in the table.

Which providers sell both Qwen3.5 397B A17B and Qwen3.5 122B A10B?

3 providers have a standard price for both: Alibaba Cloud (USD 1.35 and USD 1.10 at 3:1), GMI Cloud (USD 1.35 and USD 1.10 at 3:1), Novita AI (USD 1.35 and USD 1.10 at 3:1). The first 3 tie for the lowest combined price. Buying each model from its own cheapest provider costs USD 1.087 and USD 0.715.

Which is cheaper for a coding agent or a chatbot, Qwen3.5 397B A17B or Qwen3.5 122B A10B?

For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 460.35 a month on Qwen3.5 397B A17B (Chutes) against USD 655.20 on Qwen3.5 122B A10B (SiliconFlow), a difference of USD 194.85. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 72.63 a month on Qwen3.5 397B A17B (Chutes) against USD 60.84 on Qwen3.5 122B A10B (SiliconFlow), a difference of USD 11.79. 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 Qwen3.5 397B A17B and Qwen3.5 122B A10B change?

Qwen3.5 122B A10B 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 Qwen3.5 397B A17B's, so the input:output ratio never changes the answer.

Do Qwen3.5 397B A17B and Qwen3.5 122B A10B have cached input pricing?

Qwen3.5 397B A17B from USD 0.045 per 1M cached input tokens (Chutes; 3 of 7 standard prices list a discount). Qwen3.5 122B A10B: no standard price lists a cached-input discount. Cached tokens are billed at the input price where no cache price is published.

Which has the larger context window, Qwen3.5 397B A17B or Qwen3.5 122B A10B?

Both go up to 262,144 tokens on the providers that state it.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity