Qwen3.8 27B
The cheapest provider for Qwen3.8 27B is DeepInfra at $0.581 per 1M tokens (blended), charging $0.15 per 1M input and $1.875 per 1M output tokens. 17 providers serve it; the most expensive charges 2.7× as much. Context window: 1M tokens. Prices tracked since Oct 3, 2026.
Best price
$0.581
at DeepInfra
Input / output
$0.15 / $1.875
per 1M tokens
Providers
17
2.7× spread
7 days
—
best price
30 days
—
best price
Context
1M
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 |
|---|---|---|---|---|---|---|---|
DeepInfraCheapest bf16·−25% discount | $0.15 | $1.875 | $0.581 | best | |||
| −25% discount | $0.15 | $1.875 | $0.581 | best | |||
| fp4 | $0.05 | $2.20 | $0.588 | +1% | |||
| fp8·−10% discount | $0.203 | $1.782 | $0.597 | +3% | |||
| fp8 | $0.0893 | $2.20 | $0.617 | +6% | |||
| fp8 | $0.24 | $2.20 | $0.73 | +26% | |||
| fp8 | $0.24 | $2.20 | $0.73 | +26% | |||
| fp8 | $0.20 | $2.50 | $0.775 | +33% | |||
| $0.049 | $3.00 | $0.787 | +35% | ||||
| $0.425 | $2.55 | $0.956 | +65% | ||||
| fp8 | $0.40 | $3.00 | $1.05 | +81% | |||
| $0.42 | $3.00 | $1.065 | +83% | ||||
| fp16 | $0.99 | $1.49 | $1.115 | +92% | |||
| $0.0248 | $4.40 | $1.12 | +92% | ||||
| $0.45 | $3.20 | $1.14 | +96% | ||||
| fp8 | $0.45 | $3.20 | $1.14 | +96% | |||
| $0.0248 | $6.20 | $1.57 | +170% |
- DeepInfraCheapest$0.581$0.15 in · $1.875 outbest256K ctx99.5% uptimebf16·−25% discount
- $0.581$0.15 in · $1.875 outbest1M ctx96.5% uptime−25% discount
- $0.588$0.05 in · $2.20 out+1%256K ctx99.5% uptimefp4
- $0.597$0.203 in · $1.782 out+3%256K ctx99.8% uptimefp8·−10% discount
- $0.617$0.0893 in · $2.20 out+6%256K ctx96.9% uptimefp8
- $0.73$0.24 in · $2.20 out+26%256K ctx99.3% uptimefp8
- $0.73$0.24 in · $2.20 out+26%256K ctx99.9% uptimefp8
- $0.775$0.20 in · $2.50 out+33%256K ctx99.1% uptimefp8
- $0.787$0.049 in · $3.00 out+35%256K ctx99.8% uptime
- $0.956$0.425 in · $2.55 out+65%1M ctx99.7% uptime
- $1.05$0.40 in · $3.00 out+81%256K ctx99.9% uptimefp8
- $1.065$0.42 in · $3.00 out+83%1M ctx99.6% uptime
- $1.115$0.99 in · $1.49 out+92%64K ctx100% uptimefp16
- $1.12$0.0248 in · $4.40 out+92%256K ctx93.8% uptime
- $1.14$0.45 in · $3.20 out+96%256K ctx95.7% uptime
- $1.14$0.45 in · $3.20 out+96%256K ctx99.4% uptimefp8
- $1.57$0.0248 in · $6.20 out+170%256K ctx99.9% uptime
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 | Cache write |
|---|---|---|
| DeepInfra, Phala | $0.0375 | — |
| Darkbloom | $0.025 | — |
| AkashML | $0.045 | — |
| Ionstream, Novita | $0.085 | — |
| Chutes | $0.024 | — |
| Parasail, Cloudflare | $0.05 | — |
| DekaLLM | $0.02 | — |
| Alibaba | $0.085 | $0.531 |
| CoreWeave | $0.15 | — |
| Cerebras | $0.99 | — |
| Reka | $0.0155 | — |
| Wafer | $0.0198 | — |
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
Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be...
- Released
- Aug 14, 2026
- First tracked
- Oct 3, 2026
- Canonical slug
- qwen/qwen3.8-27b-20260814
- Weights
- Qwen/Qwen3.8-27B