Qwen3.5 35B-A3B API Pricing
Alibaba · released 2026-02-23
Also searched as: Qwen3.5 35B A3B pricing · Qwen 3.5 35B A3B price
Qwen3.5 35B-A3B price
0.025¢ / 1K
0.200¢ / 1K
0.069¢ / 1K
Single public source; verify on the official site
Official list price from Alibaba, as recorded by models.dev
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0725¢ |
| RAG query | 4,000 in / 500 out | 0.2¢ |
| Long document summary | 50,000 in / 1,000 out | $0.0145 |
| Code review of a 2k-line file | 30,000 in / 2,000 out | $0.0115 |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $21.75 |
Cost = (input tokens ÷ 1,000,000 × $0.25) + (output tokens ÷ 1,000,000 × $2.00).
Benchmarks
| Benchmark | Value | Source | As of |
|---|---|---|---|
| Epoch Capabilities Index (ECI) | 143.9 | epoch | 2026-02-24 |
| Epoch Mock AIME accuracy | 70.0% | epoch | 2026-02-24 |
| Epoch FrontierMath (T1–3) accuracy | No public data yet | ||
| Arena text rating | 1394 | arena | 2026-10-28 |
| Arena coding rating (human preference votes, not task accuracy) | 1435 | arena | 2026-10-28 |
| Arena math rating | 1398 | arena | 2026-10-28 |
| Arena WebDev rating | 1254 | arena | 2026-10-28 |
Similar ECI, lower price
| Model | ECI | Blended $/1M |
|---|---|---|
| GPT-5 Nano | 139.2 | $0.1375 |
| GPT-5.4 nano | 146.4 | $0.4625 |
| DeepSeek V4 Flash | 146.9 | $0.525 |
| MiniMax-M3 | 147.6 | $0.525 |
| Gemini 3.1 Flash Lite | 144.9 | $0.5625 |
More from Alibaba
| Model | Released | Blended $/1M |
|---|---|---|
| Qwen-Image-2.1-Turbo | 2026-10-09 | — |
| Qwen-Image-2.1-Pro | 2026-10-02 | — |
| Qwen 3.8 Max Prime | 2026-09-23 | — |
| Qwen3.8 Omni Flash | 2026-09-17 | $0.23 |
| Qwen-Image-2.1 | 2026-09-14 | — |
| Qwen3.8 Max 0902 | 2026-09-02 | $3.00 |
| Qwen3.8 Flash Next | 2026-08-27 | — |
| Qwen3.8 Flash | 2026-08-26 | $0.23 |
Count tokens & estimate cost for Qwen3.5 35B-A3B See Qwen3.5 35B-A3B on the leaderboard
Prices: Alibaba's official list price as recorded by models.dev; benchmarks: see sources below; last synced 2026-11-06.
FAQ
Who develops Qwen3.5 35B-A3B?
Qwen3.5 35B-A3B is developed by Alibaba, released 2026-02-23.
How much does Qwen3.5 35B-A3B cost per million tokens?
Qwen3.5 35B-A3B costs $0.25 per 1M input tokens and $2.00 per 1M output tokens ($0.6875 blended), per Alibaba's official list price as recorded by models.dev.
What is the Qwen3.5 35B-A3B API price?
The Qwen3.5 35B-A3B API price is $0.25 per 1M input tokens and $2.00 per 1M output tokens ($0.6875 per 1M blended).
How much does Qwen3.5 35B-A3B cost for a typical request?
A short chat reply (500 in / 300 out tokens) costs about 0.0725¢ on Qwen3.5 35B-A3B, at $0.25/1M input and $2.00/1M output.
Is Qwen3.5 35B-A3B free?
Qwen3.5 35B-A3B's official API list price is $0.25 per 1M input tokens and $2.00 per 1M output tokens. This site tracks list prices only, not free tiers or trial credits — check Alibaba's site for those.
How does Qwen3.5 35B-A3B rank on benchmarks?
Qwen3.5 35B-A3B scores 143.9 on the Epoch Capabilities Index (ECI), ranking #80 of 107 models we track with a published ECI score.
Is there a cheaper model with a similar ECI to Qwen3.5 35B-A3B?
Yes — GPT-5 Nano scores a similar ECI (139.2) at $0.1375/1M blended, versus $0.6875/1M for Qwen3.5 35B-A3B.
Where does this data come from?
Pricing for Qwen3.5 35B-A3B comes from models.dev and LiteLLM (open MIT-licensed catalogs); benchmark scores come from Epoch AI and LMArena (open CC BY 4.0 licenses) — see /data-sources/. Last synced 2026-11-06.