Qwen3.6 35B-A3B API pricing
Official Qwen list price, last checked Oct 29, 2026. Updated Oct 29, 2026.
Qwen3.6 35B-A3B costs $0.375 per 1M input tokens and $2.25 per 1M output tokens, and a 256K-token context window, per Qwen's official pricing page (checked Oct 29, 2026). It's priced in the middle of the pack: number 25 of 77 by blended price ($0.8438 per 1M tokens at a 3 to 1 input to output mix). LMArena doesn't list it on the boards we track, so we don't rank its quality. For less, look at Step 3.7 Flash ($0.4375 blended).
Qwen3.6 35B-A3B price per million tokens
| Qwen3.6 35B-A3B price per million tokens | USD |
|---|---|
| Input | $0.375 |
| Cached input | Not listed |
| Output | $2.25 |
| Blended, 3 parts input to 1 part output | $0.8438 |
| Context window | 256K tokens |
Official note from Qwen: International (Singapore). Prompts up to 256K.
What Qwen3.6 35B-A3B costs for real work
List-price estimates for a month, no discounts. Our math, not a quote: change the token counts in the plan vs API calculator.
| Workload | Tokens a month | Qwen3.6 35B-A3B | Gemini 3.5 Flash-Lite | Step 3.7 Flash |
|---|---|---|---|---|
| Light: a side project or personal assistant | 2M in, 0.5M out | $1.88 | $1.85 | $0.97 |
| Medium: a small team or one product feature | 20M in, 5M out | $18.75 | $18.50 | $9.75 |
| Heavy: a production app | 200M in, 50M out | $188 | $185 | $97.50 |
How Qwen3.6 35B-A3B ranks on LMArena
It isn't on any LMArena board we track as of Oct 29, 2026. We don't estimate quality for unranked models. See the best model for each task for ranked options.
Closest rivals to Qwen3.6 35B-A3B
The models nearest in price, other makers first. Ranks are on LMArena, where we have them.
| Model | In / out | Blended | Verdict |
|---|---|---|---|
| Gemini 3.5 Flash-Lite | $0.30 / $2.50 | $0.85 | Same price, no score to separate them. Compare |
| GLM-4.7 | $0.60 / $2.20 | $1 | Qwen3.6 35B-A3B wins on price. Compare |
| GLM-4.6 | $0.60 / $2.20 | $1 | Qwen3.6 35B-A3B wins on price. Compare |
| Seed 2.1 Turbo | $0.50 / $2.50 | $1 | Qwen3.6 35B-A3B wins on price. Compare |
Cheaper alternatives to Qwen3.6 35B-A3B
At least 40% cheaper blended, cheapest at the bottom of the list we found.
| Model | In / out | Blended | Verdict |
|---|---|---|---|
| Step 3.7 Flash | $0.20 / $1.15 | $0.4375 | Step 3.7 Flash wins on price. Compare |
| Mistral Small 4 | $0.15 / $0.60 | $0.2625 | Mistral Small 4 wins on price. Compare |
| MiniMax-M3.1 Flash | $0.15 / $0.60 | $0.2625 | MiniMax-M3.1 Flash wins on price. Compare |
More from Qwen
- Qwen3.5 27B$0.30 in, $2.40 out per 1M
- Qwen3.5 Plus$0.40 in, $2.40 out per 1M
- Qwen3.7 Plus$0.40 in, $1.60 out per 1M
- Qwen3.5 35B-A3B$0.25 in, $2 out per 1M
- Qwen3 Coder Flash$0.30 in, $1.50 out per 1M
FAQ
How much does the Qwen3.6 35B-A3B API cost per million tokens?
$0.375 per 1M input tokens and $2.25 per 1M output tokens, as of Oct 29, 2026. A typical 3 to 1 input to output mix works out to $0.8438 per 1M tokens.
Does Qwen3.6 35B-A3B charge more for long prompts?
Qwen doesn't list a long-prompt surcharge for Qwen3.6 35B-A3B. Its pricing note says: International (Singapore). Prompts up to 256K.
Is Qwen3.6 35B-A3B cheaper than Gemini 3.5 Flash-Lite?
No. A medium month (20M input and 5M output tokens) costs $18.75 on Qwen3.6 35B-A3B and $18.50 on Gemini 3.5 Flash-Lite at list price.
How does Qwen3.6 35B-A3B rank on LMArena?
It isn't listed on the LMArena boards we track, so we show no quality rank rather than guess.
What is a cheaper alternative to Qwen3.6 35B-A3B?
Step 3.7 Flash costs $0.20 in and $1.15 out per 1M tokens, about 1.9x less blended.
Where does this Qwen3.6 35B-A3B price come from?
From Qwen's official pricing page, which we check every day. This page was last checked Oct 29, 2026.