Qwen3.5-35B-A3B: Benchmarks, Pricing & Context Window
Qwen3.5-35B-A3B is a language model from Qwen, released in February 2026, with multimodal input, a 262K-token context window, and pricing from $0.140/M input, $0.050/M cached input, $1.00/M output.
Qwen3.5-35B-A3B is a multimodal Mixture-of-Experts model with 35 billion total parameters and 3 billion activated parameters. It combines strong reasoning, coding, agentic, and visual understanding performance with production-friendly
Qwen3.5-35B-A3B benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Qwen3.5-35B-A3B across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Qwen3.5-35B-A3B holds up as conversations get longer.
Quality Tracker
Qwen3.5-35B-A3B Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Sat Sep 12 2026Qwen3.5-35B-A3B pricing
Providers
Qwen3.5-35B-A3B starts at $0.140 per million input tokens and $1.00 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.0500 per million cached input tokens. See all 2 providers below with their per-token pricing, latency, throughput, and modality support.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.140 | $0.0500 | $1.00 | 262.1K/262.1K | — | — | / |
 Novita | $0.250 | — | $2.00 | 262.1K/65.0K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Qwen3.5-35B-A3B model size
Qwen3.5-35B-A3B has 35 billion parameters. See how it compares to other models in the same parameter range.
Qwen3.5-35B-A3B context window
Input and output token limits for Qwen3.5-35B-A3B, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Qwen3.5-35B-A3B.
Qwen3.5-35B-A3B latency
Qwen3.5-35B-A3B time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Qwen3.5-35B-A3B examples
Recent arena outputs from Qwen3.5-35B-A3B, picked from the highest-ranked matchups.
Qwen3.5-35B-A3B license
Qwen3.5-35B-A3B is released under the Apache 2.0 license, which permits commercial use, has 35.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 35.0B
Apache License 2.0 - allows commercial use
Qwen3.5-35B-A3B resources
Official sources for Qwen3.5-35B-A3B: provider documentation, official playground, source repository, model weights.
Qwen3.5-35B-A3B vs other models
The most-compared alternatives to Qwen3.5-35B-A3B are Gemini 3 Pro, Grok-3 Mini, ChatGPT-4o Latest. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Qwen3.5-35B-A3B
Models ranked just above and below Qwen3.5-35B-A3B by LLM Stats score.
FAQ
Common questions about Qwen3.5-35B-A3B.