Model
Model
qwen
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...
| Provider | Quantization | Input / M tokens | Output / M tokens |
|---|---|---|---|
| Darkbloomdarkbloom/fp4 | fp4 | $0.035 | $2.20 |
| Chuteschutes/fp8 | fp8 | $0.039 | $1.25 |
| Near AInear-ai/fp8 | fp8 | $0.04 | $1.35 |
| Ionstreamionstream/fp8 | fp8 | $0.04 | $1.95 |
| Rekareka/fp8 | fp8 | $0.04 | $2.20 |
| Modalmodal | — | $0.04 | $2.30 |
| DekaLLMdekallm | — | $0.04 | $2.50 |
| Waferwafer/fp8 | fp8 | $0.06 | $2.30 |
| DeepInfradeepinfra/bf16 | bf16 | $0.15 | $1.875 |
| Mancer 2mancer/fp8 | fp8 | $0.20 | $2.50 |
| ModelRunmodelrun/fp4 | fp4 | $0.20 | $2.50 |
| Phalaphala | — | $0.20 | $2.50 |
| AkashMLakashml/fp8 | fp8 | $0.225 | $1.98 |
| Parasailparasail/fp8 | fp8 | $0.24 | $2.20 |
| CoreWeavecoreweave/fp8 | fp8 | $0.40 | $3.00 |
| Novitanovita | — | $0.42 | $3.00 |
| Alibabaalibaba | — | $0.425 | $2.55 |
| Cloudflarecloudflare | — | $0.45 | $3.20 |
| Venicevenice/fp8 | fp8 | $0.45 | $3.20 |
| Cerebrascerebras/fp16 | fp16 | $0.99 | $1.49 |
Prices are what the Provider charges, synced 2026-10-21. Amber adds its platform fee to each Trial’s total; see pricing.
Amber has no curated Model Configuration for this Model yet. Create a custom one in your Workspace to evaluate it.