Pricingby GlyphQwen3.5 397B A17B
Qwen (Alibaba) · Open weights · 262K context · released Feb 16, 2026 · checked 13h ago
The Qwen3.5 series 397B-A17B native vision-language model is built on a hybrid architecture that integrates a linear attention mechanism with a sparse mixture-of-experts model, achieving higher inference efficiency.
Ways to buy 10
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
The lab's own API | $0.39 | $2.34 | $0.39 / $2.34List price | n/a | List price |
fp8 · cached $0.22 | $0.45 | $3 | $0.45 / $3+24% vs list | $0.22 | +24% vs list |
fp8 · cached $0.3 | $0.5 | $3.6 | $0.5 / $3.6+45% vs list | $0.3 | +45% vs list |
| AtlasCloud fp8 · cached $0.55 | $0.55 | $3.5 | $0.55 / $3.5+47% vs list | $0.55 | +47% vs list |
Default region · cached $0.11 | $0.55 | $3.5 | $0.55 / $3.5+47% vs list | $0.11 | +47% vs list |
| Phala Default region · cached $0.225 | $0.55 | $3.5 | $0.55 / $3.5+47% vs list | $0.225 | +47% vs list |
| GMICloud fp8 | $0.6 | $3.6 | $0.6 / $3.6+54% vs list | n/a | +54% vs list |
Default region | $0.6 | $3.6 | $0.6 / $3.6+54% vs list | n/a | +54% vs list |
| StreamLake Default region · cached $0.12 | $0.6 | $3.6 | $0.6 / $3.6+54% vs list | $0.12 | +54% vs list |
Default region | $0.75 | $4.5 | $0.75 / $4.5+92% vs list | n/a | +92% vs list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $85.80 direct.
Kong AI Gateway$85.80+0%
LiteLLM$85.80+0%
Cloudflare AI Gateway$90.09+5%
Requesty$90.09+5%
Eden AI$90.52+5.5%
OpenRouter$90.52+5.5%
HeliconeNot offeredNot offered
Neon AI GatewayNot offeredNot offered
TrueFoundry AI GatewayNot offeredNot offered
Vercel AI GatewayNot offeredNot offered
A dash: not on that gateway's own model list. No published token fee: Martian Gateway, Portkey.
Related models
| In / out per 1M | Cheapest route | |||||||
|---|---|---|---|---|---|---|---|---|
Qwen (Alibaba) · 1M | $4 | $12 | $4 / $12 | $6 | 1M | Lab list price | · | Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. |
Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · | Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. |
Qwen (Alibaba) · 1M | $2 | $6 | $2 / $6 | $3 | 1M | Lab list price | · | Qwen3.8 Max 0902 is an updated snapshot of Qwen3.8 Max from Alibaba's Qwen team. |
Qwen (Alibaba) · 1M | $0.15 | $0.47 | $0.15 / $0.47 | $0.23 | 1M | Lab list price | · | Qwen3.8 Flash is a multimodal reasoning model from Alibaba. |
Google · 1MCheapest: $0.75 on Google Gemini API (flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Gemini API (flex) | · | Gemini 3.8 Flash is Google's most intelligent Flash model with significant gains from 3.7 Flash across software engineering, agentic tasks, and multi-step reasoning. |
Google · 1MCheapest: $0.75 on Google Vertex AI (global-flex) | $0.75 | $3.75 | $0.75 / $3.75 | $1.5 | 1M | $0.75 on Google Vertex AI (global-flex) | · | Gemini 3.7 Flash is a multimodal model from Google for fast agentic workflows, coding, and complex multi-step reasoning. |
Z.ai · 1M | $0.179 | $1.4 | $0.179 / $1.4 | $0.484 | 1M | on Wafer (fp4) | · | GLM-5.3 is a large-scale reasoning model from Z.ai, built for complex software engineering and long-horizon agent tasks. |
Z.ai · 1M | $0.37 | $1.25 | $0.37 / $1.25 | $0.59 | 1M | Lab list price | · | GLM-5.3-FlashX-Legal (GLM-Legal) is Z.ai's legal-domain variant of GLM-5.3-FlashX, a native multimodal model that accepts text, image, and video input and produces text. |
About Qwen3.5 397B A17B
Takes text, image, video in and returns text. First listed Sep 23, 2026. Up to 64K output tokens. Blended price $0.878 per 1M tokens at 3 input to 1 output. Model id qwen3-5-397b-a17b.
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
Across GlyphCompany profile
Questions
How much does Qwen3.5 397B A17B cost?
$0.39 per million input tokens and $2.34 per million output tokens.
What is the context window of Qwen3.5 397B A17B?
262K tokens, with up to 64K tokens of output.
Where is Qwen3.5 397B A17B cheapest?
Of 10 routes tracked, Qwen (Alibaba) is cheapest at $0.39 input and $2.34 output per million tokens.