Qwen3.5-35B-A3B
The cheapest provider for Qwen3.5-35B-A3B is Darkbloom at $0.248 per 1M tokens (blended), charging $0.08 per 1M input and $0.75 per 1M output tokens. 7 providers serve it; the most expensive charges 2.5× as much. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
Best price
$0.248
at Darkbloom
Input / output
$0.08 / $0.75
per 1M tokens
Providers
7
2.5× spread
7 days
—
best price
30 days
—
best price
Context
256K
tokens
Providers
Active offers ranked by blended price. Bars are relative to the most expensive.
| Provider | Input | Output | Blended | vs cheapest | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DarkbloomCheapest fp4 | $0.08 | $0.75 | $0.248 | best | |||
| fp8 | $0.14 | $1.00 | $0.355 | +43% | |||
| fp8 | $0.15 | $1.00 | $0.363 | +46% | |||
| $0.163 | $1.30 | $0.447 | +81% | ||||
| $0.313 | $1.25 | $0.547 | +121% | ||||
| fp8 | $0.225 | $1.80 | $0.619 | +150% | |||
| fp8 | $0.24 | $1.80 | $0.63 | +155% |
- DarkbloomCheapest$0.248$0.08 in · $0.75 outbest256K ctx99.9% uptimefp4
- $0.355$0.14 in · $1.00 out+43%256K ctx99.8% uptimefp8
- $0.363$0.15 in · $1.00 out+46%256K ctx100% uptimefp8
- $0.447$0.163 in · $1.30 out+81%256K ctx97.0% uptime
- $0.547$0.313 in · $1.25 out+121%250K ctx99.9% uptime
- $0.619$0.225 in · $1.80 out+150%256K ctx97.7% uptimefp8
- $0.63$0.24 in · $1.80 out+155%256K ctx41.0% uptimefp8
Blended = (3 × input + output) / 4.
Price history
Hover to compare providers at any point in time. Click a legend item to hide it.
USD per 1M tokens · each step is a price change
Not enough history yet
Tracking since Oct 3, 2026. The chart fills in as new crawls arrive every 6 hours.
Other pricing
Cache, reasoning and per-call fees. Token rates per 1M; others per unit.
| Offered by | Cache read |
|---|---|
| Darkbloom | $0.04 |
| DeepInfra, Parasail | $0.05 |
| Venice | $0.156 |
| AtlasCloud | $0.225 |
| SiliconFlow | $0.15 |
Change log
Every recorded change for this model since Oct 3, 2026.
No changes yet
Tracking since Oct 3, 2026. Price changes, new providers and delistings will show up here.
About this model
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency. Its overall...
- Released
- Feb 25, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3.5-35b-a3b-20260224
- Weights
- Qwen/Qwen3.5-35B-A3B