Qwen3.5 397B-A17B
Qwen vision-language model for visual reasoning, documents, and agent tasks
Cheapest input
$0.172
$/MTok · models.dev
Cheapest output
$1.03
$/MTok
Context
262K
tokens
Offers
11
2 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestqwen3-5-397b-a17b | EmpirioLabs AI | $0.172 | $1.03 | $0.172 | 256K |
| models.devqwen3.5-397b-a17b | CrofAI | $0.35 | $1.75 | $0.07 | 262K |
| models.devqwen3.5-397b-a17b | Alibaba / Qwen | $0.43 | $2.58 | $0 | 262K |
| models.devqwen3.5-397b-a17b | DigitalOcean | $0.55 | $3.50 | $0 | 262K |
| models.devqwen3.5-397b-a17b | Alibaba / Qwen | $0.6 | $3.60 | $0 | 262K |
| models.devqwen3.5-397b-a17b | Cortecs | $0.6 | $3.60 | $0 | 250K |
| models.devqwen3.5-397b-a17b | Scaleway | $0.6 | $3.60 | $0 | 256K |
| LiteLLMQwen3.5-397B-A17B | — | $0.6 | $3.60 | $0.06 | — |
| models.devqwen3.5-397b-a17b | OVHcloud AI Endpoints | $0.71 | $4.25 | $0 | 262K |
| models.devqwen3-5-397b-a17b | Venice AI | $0.75 | $4.50 | $0 | 128K |
| models.devqwen3.5-397b-a17b | GreenPT | $0.798 | $4.96 | $0 | 262K |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- In: video
- In: audio
- Out: text
Knowledge cutoff: 2025-04Released: 2026-02-16Family: qwen
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence33.7
- AA coding48.2
- AA agentic19.8
Sources: Arena AI, Artificial Analysis. See /benchmarks.