Alibaba
Qwen3.8 Flash Next
Open-weight experimental preview of the Qwen4 architecture: hybrid-attention MoE (125B total, 6B active) with vision encoder for coding, agent tasks, and image and video understanding
Model facts
- Context window
- 262K tokens
- Maximum output
- 262K tokens
- Cheapest paid input
- $0.12 per 1M tokens
- Cheapest paid output
- $0.4 per 1M tokens
- Open weights
- yes
- Providers
- 6
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, open weights, text, image, video.
Local hardware estimate
At 4K context: Q4_K_M 111.1 GiB, Q8_0 195.0 GiB, F16 352.1 GiB working memory.
- Parameters
- 180.0 billion
- Architecture
- qwen4exp
- Model license
- other
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 |
|---|---|---|---|---|
| default | 55.8 | 73.1 | not measured | 89.1 |
Observed price history
- 2026-08-26: not published input / not published output per 1M tokens
- 2026-08-28: $0.15 input / $0.47 output per 1M tokens
- 2026-09-01: $0.12 input / $0.4 output per 1M tokens
API providers
- Vercel AI Gateway — model id alibaba/qwen3.8-flash-next; $0.12 input / $0.4 output per 1M tokens; provider documentation
- AMD — model id Qwen3.8-Flash-Next; $0.15 input / $0.47 output per 1M tokens; provider documentation
- Requesty — model id qwen3.8-flash-next; $0.2 input / $0.5 output per 1M tokens; provider documentation
- Requesty (EU) — model id qwen3.8-flash-next@eu; $0.2 input / $0.5 output per 1M tokens; provider documentation
- Cortecs — model id qwen3.8-flash-next; $0.201 input / $0.5 output per 1M tokens; provider documentation
- Arena — model id farris; not published input / not published output per 1M tokens; provider documentation