Alibaba
Qwen3.8 27B
Dense 27B vision-language model for coding, agent tasks, and image and video understanding
Model facts
- Context window
- 262K tokens
- Maximum output
- 33K tokens
- Cheapest paid input
- $0.1 per 1M tokens
- Cheapest paid output
- $0.4 per 1M tokens
- Open weights
- yes
- Providers
- 34
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video, pdf.
Local hardware estimate
At 4K context: Q4_K_M 18.0 GiB, Q8_0 30.9 GiB, F16 55.2 GiB working memory.
- Parameters
- 27.8 billion
- Architecture
- qwen3_5
- Model license
- apache-2.0
Planning estimate adapted from the MIT-licensed whichllm estimator using metadata from Hugging Face; not a vendor minimum requirement.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| xhigh | 52.0 | 68.1 | not measured | 42.9 |
| medium | 44.5 | 56.1 | not measured | 44.8 |
| low | 42.9 | 58.2 | not measured | 44.2 |
| Non-reasoning | 34.7 | 44.6 | not measured | 47.6 |
Observed price history
- 2026-08-24: $0.1 input / $0.4 output per 1M tokens
API providers
- Hetzner — model id Qwen3.8-27B; free input / free output per 1M tokens; provider documentation
- OVHcloud AI Endpoints — model id qwen3.8-27b; free input / free output per 1M tokens; provider documentation
- OrcaRouter (free) — model id qwen/qwen3.8-27b-free; free input / free output per 1M tokens; provider documentation
- RunInfra — model id Qwen/Qwen3.8-27B; $0.1 input / $0.4 output per 1M tokens; provider documentation
- EmpirioLabs AI — model id qwen3-8-27b; $0.17 input / $0.5 output per 1M tokens; provider documentation
- NanoGPT — model id qwen3.8-27b; $0.15 input / $0.7 output per 1M tokens; provider documentation
- CrofAI — model id qwen3.8-27b; $0.2 input / $1.5 output per 1M tokens; provider documentation
- LLM Tech — model id unsloth/Qwen3.8-27B-NVFP4; $0.25 input / $2.09 output per 1M tokens; provider documentation
- AKI.IO — model id qwen3.8-27b; $0.3 input / $2.2 output per 1M tokens; provider documentation
- Kosmik Compute — model id qwen/qwen3.8-27b; $0.35 input / $2.2 output per 1M tokens; provider documentation
- OrcaRouter — model id qwen/qwen3.8-27b; $0.33 input / $2.4 output per 1M tokens; provider documentation
- Cortecs — model id qwen3.8-27b; $0.334 input / $2.45 output per 1M tokens; provider documentation
- IteraCompute — model id iteracompute/qwen3.8-27b; $0.3 input / $2.5 output per 1M tokens; provider documentation
- DevPass (LLM Gateway) — model id Qwen3.8-27B; $0.41 input / $2.5 output per 1M tokens; provider documentation
- LLM Gateway (Consensus Protocol) — model id consensusprotocol/Qwen3.8-27B; $0.41 input / $2.5 output per 1M tokens; provider documentation
- Kilo Gateway — model id qwen/qwen3.8-27b; $0.425 input / $2.55 output per 1M tokens; provider documentation
- Regolo AI — model id qwen3.8-27b; $0.58 input / $2.42 output per 1M tokens; provider documentation
- Deep Infra — model id Qwen/Qwen3.8-27B; $0.4 input / $3 output per 1M tokens; provider documentation
- Hugging Face — model id Qwen/Qwen3.8-27B; $0.4 input / $3 output per 1M tokens; provider documentation
- Weights & Biases — model id Qwen/Qwen3.8-27B; $0.4 input / $3 output per 1M tokens; provider documentation
- ai& — model id qwen/qwen3.8-27b; $0.4 input / $3 output per 1M tokens; provider documentation
- LLM Gateway (NovitaAI) — model id novita/qwen3.8-27b; $0.42 input / $3 output per 1M tokens; provider documentation
- OpenRouter — model id qwen/qwen3.8-27b; $0.42 input / $3 output per 1M tokens; provider documentation
- Charm Hyper — model id qwen3.8-27b; $0.5 input / $3 output per 1M tokens; provider documentation
- Eden AI — model id qwen/qwen3.8-27b; $0.5 input / $3 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id alibaba/qwen3.8-27b; $0.5 input / $3 output per 1M tokens; provider documentation
- Cloudflare Workers AI — model id @cf/qwen/qwen3.8-27b; $0.45 input / $3.2 output per 1M tokens; provider documentation
- Neuralwatt — model id qwen-3.8-27b; $0.45 input / $3.2 output per 1M tokens; provider documentation
- Ofox — model id bailian/qwen3.8-27b; $0.45 input / $3.2 output per 1M tokens; provider documentation
- Venice AI — model id qwen-3-8-27b; $0.45 input / $3.2 output per 1M tokens; provider documentation
- Berget.AI — model id Qwen/Qwen3.8-27B-FP8; $0.46 input / $3.48 output per 1M tokens; provider documentation
- evroc — model id Qwen/Qwen3.8-27B; $0.87 input / $3.5 output per 1M tokens; provider documentation
- Groq — model id qwen/qwen3.8-27b; $0.8 input / $4 output per 1M tokens; provider documentation
- Arena — model id qwen3.8-27b; not published input / not published output per 1M tokens; provider documentation