Qwen3.5 122B A10B vs Qwen3.5 35B A3B API pricing
Updated
Qwen3.5 122B A10B: USD 0.26 input, USD 2.08 output per 1M tokens (SiliconFlow). Qwen3.5 35B A3B: USD 0.14 input, USD 1 output per 1M tokens (DeepInfra). At 3 input tokens per output token, Qwen3.5 122B A10B costs 2.01× as much as Qwen3.5 35B A3B (USD 0.715 vs USD 0.355 per 1M).
How do Qwen3.5 122B A10B and Qwen3.5 35B A3B differ on price?
- Cheapest input price: Qwen3.5 35B A3B USD 0.14 against USD 0.26 per 1M tokens, so Qwen3.5 122B A10B costs 1.86× as much (86% more).
- Cheapest output price: Qwen3.5 35B A3B USD 1 against USD 2.08 per 1M tokens, so Qwen3.5 122B A10B costs 2.1× as much.
- Among the 201 indexed models, Qwen3.5 122B A10B ranks 112th cheapest and Qwen3.5 35B A3B 76th on the 3:1 blend.
- No input:output mix changes the answer: Qwen3.5 35B A3B is cheaper at every mix before cache discounts.
- Only Qwen3.5 35B A3B lists a cached-input discount: Qwen3.5 35B A3B at 4 standard prices of 7, from USD 0.05 (DeepInfra, 64% below that provider's input price). Qwen3.5 122B A10B's cached tokens bill at the input price.
- Both state a context window of up to 262,144 tokens.
- Qwen3.5 35B A3B has 7 providers with a standard price, 3 more than Qwen3.5 122B A10B; 4 providers sell both (SiliconFlow, Alibaba Cloud, GMI Cloud and Novita AI).
- On one account, SiliconFlow charges USD 0.715 for Qwen3.5 122B A10B (its cheapest price) and USD 0.63 for Qwen3.5 35B A3B (1.77× its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Qwen3.5 35B A3B: its dearest standard price is 1.94× its cheapest, against 1.54× for Qwen3.5 122B A10B.
- Qwen's own API charges USD 1.10 for Qwen3.5 122B A10B at 3:1, 54% above the cheapest provider (SiliconFlow).
- Qwen's own API charges USD 0.6875 for Qwen3.5 35B A3B at 3:1, 94% above the cheapest provider (DeepInfra).
- For the one-developer coding agent preset, the gap is USD 5,411 a year in Qwen3.5 35B A3B's favour (Qwen3.5 122B A10B USD 655.20 a month, Qwen3.5 35B A3B USD 204.30).
- Per character of input, Qwen3.5 122B A10B costs 1.86× as much as Qwen3.5 35B A3B in every measured language, because both use the Qwen3.8 27B tokenizer.
Qwen3.5 122B A10B and Qwen3.5 35B A3B 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.
| Price | Qwen3.5 122B A10B | Qwen3.5 35B A3B |
|---|---|---|
| Model page | Qwen3.5 122B A10B Qwen · 4 providers | Qwen3.5 35B A3B Qwen · 7 providers |
| Cheapest standard price, blended 3:1 | USD 0.715 USD 0.26 in / USD 2.08 out at SiliconFlow SiliconFlow page checked 2026-11-14 | USD 0.355 lower USD 0.14 in / USD 1 out at DeepInfra DeepInfra page checked 2026-11-14 |
| Cheapest input | USD 0.26 SiliconFlow source | USD 0.14 lower DeepInfra source |
| Cheapest cached input | No standard price lists a cache price; cached tokens bill at the input price. | USD 0.05 DeepInfra source |
| Cheapest output | USD 2.08 SiliconFlow source | USD 1 lower DeepInfra source |
| Maker's own API | USD 0.40 / USD 3.20 Alibaba Cloud source | USD 0.25 / USD 2 Alibaba Cloud source |
| Median standard price | USD 0.40 / USD 3.20 input / output, 4 prices | USD 0.24 / USD 1.80 input / output, 7 prices |
| Context window | 262,144 tokens, largest stated | 262,144 tokens, largest stated; from 256,000 at some providers |
| Providers with a standard price | 4 | 7 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Qwen3.5 122B A10B and Qwen3.5 35B A3B 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).
| Workload | Qwen3.5 122B A10B | Qwen3.5 35B A3B | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 60.84 SiliconFlow | USD 25.74 DeepInfra | USD 35.10 Qwen3.5 35B A3B lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 93.60 SiliconFlow | USD 42.12 DeepInfra | USD 51.48 Qwen3.5 35B A3B lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 655.20 SiliconFlow | USD 204.30 DeepInfra | USD 450.90 Qwen3.5 35B A3B lower |
Qwen3.5 35B A3B is cheaper on all three workloads. The widest gap is on Coding agent (one developer): the dearer model costs 3.2× as much as the cheaper one.
Does the cheaper model change with your input:output ratio?
Qwen3.5 35B A3B 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 122B A10B's, so the input:output ratio never changes the answer.
| Input : output tokens | Qwen3.5 122B A10B | Qwen3.5 35B A3B |
|---|---|---|
| 1 : 3 (long answers) | USD 1.625 SiliconFlow | USD 0.785 lower DeepInfra |
| 1 : 1 | USD 1.17 SiliconFlow | USD 0.57 lower DeepInfra |
| 3 : 1 (the site’s blend) | USD 0.715 SiliconFlow | USD 0.355 lower DeepInfra |
| 10 : 1 (retrieval, long prompts) | USD 0.4255 SiliconFlow | USD 0.2182 lower DeepInfra |
| 30 : 1 (agents, big contexts) | USD 0.3187 SiliconFlow | USD 0.1677 lower DeepInfra |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Qwen3.5 122B A10B and Qwen3.5 35B A3B 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 122B A10B (the same one for both, so the gap equals the price gap):
| Content | Qwen3.5 122B A10B | Qwen3.5 35B A3B |
|---|---|---|
| English | USD 0.058 SiliconFlow | USD 0.031 lower DeepInfra |
| Arabic MSA | USD 0.081 SiliconFlow | USD 0.043 lower DeepInfra |
| Egyptian Arabic | USD 0.085 SiliconFlow | USD 0.046 lower DeepInfra |
| Hindi | USD 0.110 SiliconFlow | USD 0.059 lower DeepInfra |
| Chinese | USD 0.150 SiliconFlow | USD 0.081 lower DeepInfra |
| Spanish | USD 0.060 SiliconFlow | USD 0.032 lower DeepInfra |
| Code | USD 0.072 SiliconFlow | USD 0.039 lower DeepInfra |
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
- Qwen3.5 122B A10B API pricing: all 4 providers and other tiers.
- Qwen3.5 35B A3B API pricing: all 7 providers and other tiers.
- Cost calculator with Qwen3.5 122B A10B and Qwen3.5 35B A3B preloaded
- Qwen token counter
- Prompt caching calculator
More comparisons: Qwen3.5 397B A17B vs Qwen3.5 122B A10B · DeepSeek V4.1 Flash vs Qwen3.5 35B A3B · Qwen3.6 35B A3B vs Qwen3.5 35B A3B · Qwen3.5 35B A3B vs Qwen3 30B A3B · Qwen3.5 35B A3B vs Qwen3.5 27B · every Qwen3.5 122B A10B comparison · every Qwen3.5 35B A3B comparison · all 662 price comparisons
Questions
Is Qwen3.5 122B A10B cheaper than Qwen3.5 35B A3B?
No. On a blend of 3 input tokens to 1 output token, Qwen3.5 35B A3B costs USD 0.355 per 1M tokens and Qwen3.5 122B A10B USD 0.715, at each model's cheapest standard price. For input alone, Qwen3.5 35B A3B is cheaper (USD 0.14 against USD 0.26 per 1M); for output alone, Qwen3.5 35B A3B is (USD 1 against USD 2.08). This compares price only, not quality.
What do Qwen3.5 122B A10B and Qwen3.5 35B A3B cost per 1M tokens?
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. Qwen3.5 35B A3B: from USD 0.14 input and USD 1 output at DeepInfra; Alibaba Cloud's own API charges USD 0.25 / USD 2; median of 7 standard prices USD 0.24 / USD 1.80. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Qwen3.5 122B A10B and Qwen3.5 35B A3B?
4 providers have a standard price for both: SiliconFlow (USD 0.715 and USD 0.63 at 3:1), Alibaba Cloud (USD 1.10 and USD 0.6875 at 3:1), GMI Cloud (USD 1.10 and USD 0.6875 at 3:1), Novita AI (USD 1.10 and USD 0.6875 at 3:1). The first is the lowest combined price. Buying each model from its own cheapest provider costs USD 0.715 and USD 0.355.
Which is cheaper for a coding agent or a chatbot, Qwen3.5 122B A10B or Qwen3.5 35B A3B?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 655.20 a month on Qwen3.5 122B A10B (SiliconFlow) against USD 204.30 on Qwen3.5 35B A3B (DeepInfra), a difference of USD 450.90. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 60.84 a month on Qwen3.5 122B A10B (SiliconFlow) against USD 25.74 on Qwen3.5 35B A3B (DeepInfra), a difference of USD 35.10. 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 122B A10B and Qwen3.5 35B A3B change?
Qwen3.5 35B A3B 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 122B A10B's, so the input:output ratio never changes the answer.
Do Qwen3.5 122B A10B and Qwen3.5 35B A3B have cached input pricing?
Qwen3.5 122B A10B: no standard price lists a cached-input discount. Qwen3.5 35B A3B from USD 0.05 per 1M cached input tokens (DeepInfra; 4 of 7 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, Qwen3.5 122B A10B or Qwen3.5 35B A3B?
Both go up to 262,144 tokens on the providers that state it.