Qwen3.5 35B-A3B API Pricing
Alibaba · released Feb 23, 2026 · 262K context · API model ID qwen3.5-35b-a3b
Qwen3.5 35B-A3B by Alibaba API pricing: $0.25 per 1M input tokens and $2.00 per 1M output tokens (provider list price via models.dev, Oct 10, 2026).
Prices
| Price | USD per 1M tokens |
|---|---|
| Input | $0.25 |
| Output | $2.00 |
| Cache read | Not published |
| Cache write | Not published |
Alibaba's list price for its own API, as compiled by models.dev and checked Oct 10, 2026, 09:00 UTC. Prices on cloud platforms and resellers can differ. Provider documentation
Estimated monthly cost
$375.00
per month
- per day
- $12.50
- per request
- $0.00125
Cannot estimate: a needed price is not published.
Cost = input tokens × input price + output tokens × output price, 30 days a month. Cached input uses the cache read price. Cache write fees are not included.
Monthly cost by workload
| Workload | Per month |
|---|---|
| Chatbot1,000 in / 500 out tokens, 10,000 requests a day | $375.00/mo |
| RAG8,000 in / 500 out tokens, 5,000 requests a day | $450.00/mo |
| Coding agent50,000 in / 2,000 out tokens, 1,000 requests a day, 80% cached input | $495.00/mo |
Context and capabilities
- Context
- 262,144 tokens
- Max output
- 65,536 tokens
- Input
- text, image, video, audio
- Output
- text
- Knowledge cutoff
- Not published
- Open weights
- Yes
- Tool calling
- Yes
- Reasoning
- Yes
- Structured outputs
- Yes
Capabilities and limits as listed by models.dev.
Similarly priced models
- GLM-5.3-FlashX · $0.37 in / $1.25 out
- Gemini 3.5 Flash Lite · $0.30 in / $2.50 out
- DeepSeek V4.1 Flash · $0.30 in / $1.20 out
- MiniMax-M3 · $0.30 in / $1.20 out
Price history
No price changes since we started tracking on Oct 8, 2026.
Questions
- How much does Qwen3.5 35B-A3B cost per month?
- For a chatbot handling 10,000 requests a day with 1,000 input and 500 output tokens each, Qwen3.5 35B-A3B costs about $375.00 per month at Alibaba's list prices ($0.25 per 1M input tokens, $2.00 per 1M output tokens).
- Does Qwen3.5 35B-A3B support prompt caching?
- No cache read price is published for Qwen3.5 35B-A3B.
- How long is Qwen3.5 35B-A3B's context window?
- Qwen3.5 35B-A3B accepts up to 262,144 tokens (262K) of context and returns up to 65,536 tokens per response.