Skip to content
CostPerPrompt

Qwen3.5-35B-A3B API Pricing

Alibaba (Qwen) · context window 262K · prices updated 2026-09-15

Input per 1M tokens
$0.1625
Output per 1M tokens
$1.30
Cached input per 1M
No discounted cached tier on this model

Where Qwen3.5-35B-A3B sits on price

At $1.30 per million output tokens, Qwen3.5-35B-A3B is a mid tier model — 1.6× cheaper than the median output price of $2.08, which puts it cheaper than 60% and pricier than 40% of the models we track. It sits 30th cheapest of the 53 Alibaba (Qwen) models we track. Output costs 8.0× more than input here, so anything that makes the model write less — tighter instructions, structured output, lower max_tokens — moves the bill more than trimming the prompt.

Output tokens per $1
769,231
One full context fill
$0.0426
Cheaper than
60% of tracked models

What real workloads cost on Qwen3.5-35B-A3B

These three workloads are the ones teams actually run on a mid-priced model — a $1.30/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
Support chatbot — 500 conversations/day (5K in / 1.4K out) Conversation history re-sent each turn — the classic prompt-caching win. $0.0026 $39.49
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0011 $341
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0.0003 $8.29

Model your exact traffic in the API cost calculator — it preloads Qwen3.5-35B-A3B with caching and batch options.

Qwen3.5-35B-A3B price history

Alibaba (Qwen) last raised Qwen3.5-35B-A3B's output price on Sep 15, 2026 (+4% per output token), from $0.3125/$1.25 to $0.1625/$1.30 per 1M in/out. That is one of 6 repricings in the 44 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 2, 2026 (tracking began) $0.14 $1.00
Aug 13, 2026 $0.25 $1.25 +25%
Aug 14, 2026 $0.225 $1.80 +44%
Aug 21, 2026 $0.25 $1.25 -31%
Sep 5, 2026 $0.08 $0.75 -40%
Sep 6, 2026 $0.3125 $1.25 +67%
Sep 15, 2026 $0.1625 $1.30 +4%

Change-points from our daily price snapshots (tracking since Aug 2, 2026; intraday moves between snapshots are not captured).

Qwen3.5-35B-A3B vs Claude 3 Haiku

The closest-priced alternative from another vendor is Claude 3 Haiku (Anthropic) — 4% cheaper on output, with $0.0875 more per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Claude 3 Haiku pricing →

Cheaper alternatives

More Alibaba (Qwen) models

Frequently asked questions

How much does the Qwen3.5-35B-A3B API cost?

Qwen3.5-35B-A3B costs $0.1625 per million input tokens and $1.30 per million output tokens and no discounted cached-input tier. That works out to roughly 769,231 output tokens per dollar.

What does the support chatbot workload cost on Qwen3.5-35B-A3B?

Support chatbot — 500 conversations/day (5K in / 1.4K out) costs about $0.0026 per request and $39.49 per month on Qwen3.5-35B-A3B. Conversation history re-sent each turn — the classic prompt-caching win.

What does it cost to fill Qwen3.5-35B-A3B's 262K context window?

Sending 262K of input in a single request costs $0.0426 at $0.1625 per million tokens — before any output. There is no cached-input tier on this model, so every repeat of that context is billed at full price. This is why large context windows are cheap to advertise and expensive to actually use.

Is Qwen3.5-35B-A3B worth the price?

Qwen3.5-35B-A3B sits in the middle of the market (30 of 53 by price within Alibaba (Qwen)). The honest test is a routing experiment: send the same 200 real requests to this model and to a tier below, and compare failure rate against the price gap — most teams find a majority of traffic never needed the pricier model.