OpenRouter
Catalog quote- Input
- $0.50
- Output
- $3.60
- Cached input
- $0.30
QwenListed Feb 16, 2026
Qwen3.5-397B-A17B
Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M…
Source description
Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimodal benchmarks.
Context window262.1K
Max output235.9K
Parameters397B
Provider endpoints17
Benchmark results0
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Access & cost
17 quotesPrices across providers
Your token mix
USD · listed token rates- Input
- $0.45
- Output
- $3.00
novita
via Hugging Face- Input
- $0.60
- Output
- $3.60
featherless-ai
via Hugging Face- Input
- —
- Output
- —
scaleway
via Hugging Face- Input
- $0.684
- Output
- $4.104
ovhcloud
via Hugging Face- Input
- $0.71
- Output
- $4.25
deepinfra
via Hugging Face- Input
- $0.45
- Output
- $3.00
- Input
- $0.39
- Output
- $2.34
Max prompt 258048 tokens
- Input
- $0.45
- Output
- $3.00
- Cached input
- $0.22
- Input
- $0.50
- Output
- $3.60
- Cached input
- $0.30
- Input
- $0.55
- Output
- $3.50
- Cached input
- $0.11
Endpoint degraded (status -5)
- Input
- $0.55
- Output
- $3.50
- Cached input
- $0.225
Endpoint degraded (status -5)
- Input
- $0.55
- Output
- $3.50
- Cached input
- $0.55
Endpoint degraded (status -2)
- Input
- $0.60
- Output
- $3.60
- Cached input
- $0.12
Endpoint degraded (status -2)
- Input
- $0.60
- Output
- $3.60
Endpoint degraded (status -2)
- Input
- $0.60
- Output
- $3.60
Endpoint degraded (status -5)
- Input
- $0.75
- Output
- $4.50
Endpoint degraded (status -5)
Model specifications
- Developer
- Qwen
- Modality
- Language
- Context
- 262,144 tokens
- Maximum output
- 235,929 tokens
- Weights
- Open weights
- Provider listed
- Feb 16, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
qwen/qwen3.5-397b-a17b - deepinfra
Qwen/Qwen3.5-397B-A17B - huggingface
Qwen/Qwen3.5-397B-A17B
Sources
Updated Oct 18, 2026
More from Qwen
View all ↗QwenListed Sep 14
Qwen3.8-Flash
Qwen's fast, low-cost model with a one-million-token context window, billed at a flat rate across the entire window.
1M contextNo reported score
No reported score
QwenReleased Aug 14
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…
1M context27BImage inputVideo input
AA IntelligenceEffort: xhigh · Xhigh33.68LiveBenchEffort: max · single run · equal mean of 7 suites62.66%
$0.02in$0.50out/ 1M tokens · USDTenstorrent · via OpenRouter · 28 endpointstenstorrent/fp4 · quantization=fp4
QwenListed Aug 3
Qwen3.8-Max
Qwen's latest 2.4-trillion-parameter MoE flagship model delivering a comprehensive leap in coding and professional work.
256K contextNo reported score
No reported score
QwenListed May 28
Qwen3.7-Max
The largest and most capable in the Qwen3.7 series. Qwen3.7 is a next‑generation flagship model designed for the agent‑centric.
256K contextNo reported score
No reported score