Qwen3.8 27B
by Qwen · qwen/qwen3.8-27b
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...
- Input / 1M tokens
- $0.15
- Output / 1M tokens
- $1.88
- Context
- 1M
Specs
| Input price | $0.15 / 1M tokens |
|---|---|
| Output price | $1.88 / 1M tokens |
| Cached input | $0.0375 / 1M tokens |
| Context window | 1M tokens |
| Max output | 236K tokens |
| Reads | text, image, video |
| Writes | text |
| Tool calling | Yes |
| Reasoning | Yes |
| Listed | Aug 14, 2026 |
List prices in USD, updated Oct 30, 2026. Providers may charge differently.
Providers
20 providers serve this model, as of Oct 30, 2026, 18:12 UTC.
| Provider | Quantization | Context | Max output | Input / 1M | Output / 1M | Cache read / 1M | Uptime (30 min) | Latency (median) | Throughput (median) | Supports | Status |
|---|---|---|---|---|---|---|---|---|---|---|---|
| Chutes | fp8 | 262K | 65.5K | $0.039 | $1.25 | $0.0039 | 100% | 2.64 s | 26 tok/s | Normal | |
| Near AI | fp8 | 262K | 65.5K | $0.04 | $1.35 | $0.018 | 100% | 3.21 s | 24 tok/s | Normal | |
| Darkbloom | fp4 | 262K | 32.8K | $0.035 | $1.50 | $0.0175 | 100% | 798 ms | 57 tok/s | Normal | |
| Ionstream | fp8 | 262K | 65.5K | $0.04 | $1.95 | $0.02 | 96.7% | 971 ms | 42 tok/s | Normal | |
| DeepInfra | bf16 | 262K | 236K | $0.15 | $1.88 | $0.0375 | 100% | 367 ms | 49 tok/s | Normal | |
| AkashML | fp8 | 262K | 131K | $0.225 | $1.98 | $0.05 | 100% | 549 ms | 45 tok/s | Normal | |
| Reka | fp8 | 262K | 236K | $0.04 | $2.20 | $0.02 | 100% | 379 ms | 31 tok/s | Normal | |
| Modal | — | 262K | 236K | $0.04 | $2.30 | $0.02 | 100% | 2.25 s | 22 tok/s | Normal | |
| Wafer | fp8 | 262K | 236K | $0.06 | $2.30 | $0.059 | 100% | 2.43 s | 59 tok/s | Normal | |
| Parasail | fp8 | 262K | 236K | $0.24 | $2.20 | $0.05 | 100% | 1.49 s | 48 tok/s | Normal | |
| Cerebras | fp16 | 65.5K | 32.8K | $0.99 | $1.49 | $0.99 | 100% | 363 ms | 594 tok/s | Normal | |
| DekaLLM | — | 262K | 236K | $0.04 | $2.50 | $0.02 | 100% | 3.89 s | 43 tok/s | Normal | |
| Mancer 2 | fp8 | 262K | 236K | $0.18 | $2.50 | — | 0% | 1.25 s | 52 tok/s | Normal | |
| ModelRun | fp4 | 262K | 236K | $0.20 | $2.50 | $0.09 | 100% | 277 ms | 129 tok/s | Normal | |
| Phala | — | 1M | 262K | $0.20 | $2.50 | $0.05 | 100% | 1.88 s | 67 tok/s | Normal | |
| Alibaba | — | 1M | 131K | $0.425 | $2.55 | $0.085 | 100% | 1.33 s | 43 tok/s | Normal | |
| CoreWeave | fp8 | 262K | 236K | $0.40 | $3.00 | $0.15 | 100% | 442 ms | 61 tok/s | Normal | |
| Novita | — | 1M | 131K | $0.42 | $3.00 | $0.085 | 100% | 2.54 s | 47 tok/s | Normal | |
| Cloudflare | — | 262K | 236K | $0.45 | $3.20 | $0.05 | — | 565 ms | 37 tok/s | Normal | |
| Venice | fp8 | 262K | 65.5K | $0.45 | $3.20 | — | 100% | 1.08 s | 55 tok/s | Normal |
"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.
Usage
#38
by tokens, Oct 29, 2026
91.1B
tokens that day · 7 days +19%
Data as of 2026-10-30T18:12:03.879Z.All rankings
Related models
- Qwen
Qwen3.8 Flash
- Input
- $0.15
- Output
- $0.47
- Context
- 1M
- Qwen
Qwen3.7 Flash
- Input
- $0.03
- Output
- $0.13
- Context
- 1M
- Qwen
Qwen3.8 Max Prime
- Input
- $4.00
- Output
- $12.00
- Context
- 1M
- Qwen
Qwen3.8 Omni Flash
- Input
- $0.15
- Output
- $0.47
- Context
- 1M
- Qwen
Qwen3.8 Max (0902)
- Input
- $2.00
- Output
- $6.00
- Context
- 1M
- Qwen
Qwen3.8 2.4T A95B
- Input
- $2.00
- Output
- $6.00
- Context
- 1.05M