Qwen3.6 35B A3B
- Input / output
- $0.05 / $0.70
- Providers
- 9
- Spread
- 2.5×
- 7 days
- +474%
- 30 days
- 0%
- Context
- 256K
Providers
| Provider | Input | Output | Blended | vs ref | Context | Uptime 1d | Price since |
|---|---|---|---|---|---|---|---|
DarkbloomCheapest fp4 | $0.05 | $0.70 | $0.213 | −15% | |||
DeepInfrafp8/flex fp8 | $0.08 | $0.76 | $0.25 | ref | |||
| fp8 | $0.10 | $0.89 | $0.298 | +19% | |||
| fp8 | $0.10 | $0.90 | $0.30 | +20% | |||
| fp8 | $0.10 | $0.90 | $0.30 | +20% | |||
| fp8 | $0.10 | $0.95 | $0.313 | +25% | |||
| fp8 | $0.10 | $1.00 | $0.325 | +30% | |||
| fp8 | $0.11 | $1.01 | $0.335 | +34% | |||
DeepInfrafp8/priority fp8 | $0.15 | $1.425 | $0.469 | +88% | |||
| fp8 | $0.25 | $1.25 | $0.50 | +100% | |||
| fp8 | $0.24 | $1.80 | $0.63 | +152% |
- DarkbloomCheapest$0.213$0.05 in · $0.70 out−15% vs ref256K ctx100% uptimefp4
- fp8/flex$0.25$0.08 in · $0.76 outref vs ref256K ctx90.0% uptimefp8
- $0.298$0.10 in · $0.89 out+19% vs ref256K ctx100% uptimefp8
- $0.30$0.10 in · $0.90 out+20% vs ref256K ctx100% uptimefp8
- $0.30$0.10 in · $0.90 out+20% vs ref256K ctx98.0% uptimefp8
- $0.313$0.10 in · $0.95 out+25% vs ref256K ctx99.7% uptimefp8
- $0.325$0.10 in · $1.00 out+30% vs ref250K ctx99.8% uptimefp8
- $0.335$0.11 in · $1.01 out+34% vs ref256K ctx99.9% uptimefp8
- fp8/priority$0.469$0.15 in · $1.425 out+88% vs ref256K ctx99.7% uptimefp8
- $0.50$0.25 in · $1.25 out+100% vs ref256K ctx46.0% uptimefp8
- $0.63$0.24 in · $1.80 out+152% vs ref256K ctx94.6% uptimefp8
Blended = (3 × input + output) / 4. Ref $0.25 = median of cheapest 20%.
Price history
USD per 1M tokens · each step is a price change
Prices in USD / 1M tokens.
Other pricing
| Offered by | Cache read |
|---|---|
| Darkbloom, Parasail | $0.025 |
| DeepInfra (fp8/flex) | $0.08 |
| CoreWeave | $0.035 |
| AkashML | $0.05 |
| DeepInfra | $0.10 |
| PrimeIntellect | $0.099 |
| DeepInfra (fp8/priority), SiliconFlow | $0.15 |
| AtlasCloud | $0.25 |
Changes
- PriceCache read price,$0.092→$0.099+7.6%
- PriceOutput price,$0.937→$1.01+7.8%
- PriceInput price,$0.102→$0.11+7.8%
- PriceCache read price,$0.099→$0.092−7.1%
- PriceOutput price,$1.01→$0.937−7.2%
- PriceInput price,$0.11→$0.102−7.3%
- PriceCache read price,$0.09→$0.099+10.0%
- PriceOutput price,$0.914→$1.01+10.5%
- PriceInput price,$0.10→$0.11+10.0%
- PriceCache read price,$0.099→$0.09−9.1%
- PriceOutput price,$1.01→$0.914−9.5%
- PriceInput price,$0.11→$0.10−9.1%
- PriceCache read price,$0.01→$0.099+890%
- PriceOutput price,$0.101→$1.01+900%
- PriceInput price,$0.011→$0.11+900%
About
The cheapest provider for Qwen3.6 35B A3B is Darkbloom at $0.213 per 1M tokens (blended), charging $0.05 per 1M input and $0.70 per 1M output tokens. 9 providers serve it; the most expensive charges 2.5× the typical price. Context window: 256K tokens. Prices tracked since Oct 3, 2026.
Qwen3.6-35B-A3B is an open-weight multimodal model from Alibaba Cloud with 35 billion total parameters and 3 billion active parameters per token. It uses a hybrid sparse mixture-of-experts architecture combining Gated...
- Released
- Apr 27, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3.6-35b-a3b-20260415
- Weights
- Qwen/Qwen3.6-35B-A3B