Qwen 3.8 27B API pricing
Qwen 3.8 27B by Cerebras costs $0.99 per 1M input tokens and $1.49 per 1M output tokens (1M in + 1M out = $2.48).
- API model id
qwen-3.8-27b- Input / 1M
- $0.99
- Output / 1M
- $1.49
- Cached input / 1M
- —
- Context window
- 131K
- Notes
- Cerebras Inference self-serve pay-as-you-go (Developer tier), USD per 1M tokens. Context 131,072 on paid tiers (65,536 on Free Trial).
- Source
- https://inference-docs.cerebras.ai/models/qwen-3.8-27b
- Provider type
- Inference host (HQ: US)
- Regions
- unknown
- EU data residency
- unknown — Pricing page and model docs do not say which data centers serve the self-serve API. OpenRouter's provider list reports HQ US, no datacenter countries.
- Last verified
- 2026-10-21
Cost estimate
| Provider | Model | Cost |
|---|---|---|
| Cerebras | Qwen 3.8 27B | $1.36 |
Uses standard list prices (no caching, batch or off-peak discounts). € and CHF rows are priced in that currency by the provider and not converted, so compare them with care.
Other Cerebras models
- gpt-oss-120b: $0.35 / $0.75