Pricingby GlyphQwen3.5-35B-A3B
Qwen (Alibaba) · Open weights · 262K context · released Feb 25, 2026 · checked 13h ago
The Qwen3.5 Series 35B-A3B is a native vision-language model designed with a hybrid architecture that integrates linear attention mechanisms and a sparse mixture-of-experts model, achieving higher inference efficiency.
Ways to buy 7
| Way to buy | Input | Output | In / out per 1M | Cached | Vs list |
|---|---|---|---|---|---|
| Darkbloom fp4, cheapest · cached $0.033 | $0.065 | $0.75 | $0.065 / $0.75-47% vs list | $0.033 | -47% vs list |
fp8 · cached $0.05 | $0.14 | $1 | $0.14 / $1-21% vs list | $0.05 | -21% vs list |
fp8 · cached $0.05 | $0.15 | $1 | $0.15 / $1-19% vs list | $0.05 | -19% vs list |
Default region · cached $0.05 | $0.15 | $1 | $0.15 / $1-19% vs list | $0.05 | -19% vs list |
The lab's own API | $0.163 | $1.3 | $0.163 / $1.3List price | n/a | List price |
| AtlasCloud fp8 · cached $0.225 | $0.225 | $1.8 | $0.225 / $1.8+38% vs list | $0.225 | +38% vs list |
fp8 · cached $0.15 | $0.24 | $1.8 | $0.24 / $1.8+41% vs list | $0.15 | +41% vs list |
USD per 1M tokens. Regions are separate routes.
Through a gateway
Your own numbers100M input and 20M output tokens a month: $42.25 direct.
Kong AI Gateway$42.25+0%
LiteLLM$42.25+0%
Requesty$44.36+5%
Eden AI$44.57+5.5%
OpenRouter$44.57+5.5%
Cloudflare AI GatewayNot offeredNot offered
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. |
DeepSeek · 1MCheapest: $0.081 on Particle AI (us-flex) | $0.15 | $0.6 | $0.15 / $0.6 | $0.262 | 1M | $0.081 on Particle AI (us-flex) | · | DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the deepseek-flash API model name. |
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. |
Anthropic · 1M | $0.1 | $0.5 | $0.1 / $0.5 | $0.2 | 1M | Lab list price | · | Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. |
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 Qwen3.5-35B-A3B
Takes text, image, video in and returns text. First listed Sep 23, 2026. Up to 82K output tokens. Blended price $0.447 per 1M tokens at 3 input to 1 output. Model id qwen3-5-35b-a3b.
Price history
List price since Sep 23, 2026, from daily reads of the OpenRouter catalog.
Qwen3.5-35B-A3B
Venice cut its price: input $0.313 to $0.15 and output $1.25 to $1 per 1M tokens.
Darkbloom (fp4) cut its price: input $0.08 to $0.065 per 1M tokens.
Darkbloom (fp4) set its first price: cached input $0.04 per 1M tokens.
Across GlyphCompany profile
Questions
How much does Qwen3.5-35B-A3B cost?
$0.163 per million input tokens and $1.3 per million output tokens.
What is the context window of Qwen3.5-35B-A3B?
262K tokens, with up to 82K tokens of output.
Where is Qwen3.5-35B-A3B cheapest?
Of 7 routes tracked, Darkbloom is cheapest at $0.065 input and $0.75 output per million tokens.
Has Qwen3.5-35B-A3B's price changed?
Yes. The output price went from $1.25 to $1, first seen Oct 25, 2026.