Skip to content
Metatext Decide — typed decisions for your agents, with a probability on every answerGet early access
Metatext
Sign Up

Qwen3.5 35B-A3B Base

Thinking MachinesOpen weights

Qwen3.5 35B-A3B Base by Thinking Machines costs $0.54 per 1M input tokens and $1.34 per 1M output tokens, with a 66K-token context window.

Pricing

Input (per 1M tokens)
$0.54
Output (per 1M tokens)
$1.34
Cached input (per 1M)
$0.11

Specifications

Provider
Thinking Machines
Context window
66K tokens
Parameters
—
Released
Feb 2026
Open weights
Yes
Frontier model
No

Compare Qwen3.5 35B-A3B Base with…

Qwen3.5 35B-A3B Base vs Qwen3.8 27B$1.35/1MQwen3.5 35B-A3B Base vs GLM 5.3$1.40/1MQwen3.5 35B-A3B Base vs Qwen3 14B$1.40/1MQwen3.5 35B-A3B Base vs GPT-5.4 Nano$1.25/1MQwen3.5 35B-A3B Base vs Claude 3 Haiku$1.25/1MQwen3.5 35B-A3B Base vs INTELLECT 3$1.20/1M

FAQ

How much does Qwen3.5 35B-A3B Base cost?

Qwen3.5 35B-A3B Base is priced at $0.54 per 1M input tokens and $1.34 per 1M output tokens. Output tokens cost more than input.

What is Qwen3.5 35B-A3B Base's context window?

Qwen3.5 35B-A3B Base supports a context window of 66K tokens — the maximum prompt plus response length it can handle in a single request.

Is Qwen3.5 35B-A3B Base open weight?

Yes — Qwen3.5 35B-A3B Base has openly available weights.

Data as of 2026-10-21. Source: models.dev (open). Pricing is per 1M tokens (USD); confirm with the provider before production use.