LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Qwen3.5 35B-A3B Base

alibaba·alibaba/qwen3.5-35b-a3b-base·GA·Open weights·qwen series
Pre-trained Qwen3.5 base checkpoint for fine-tuning and research, without instruction tuning

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·Thinking MachinesFirst-party
$0.54 / $1.34
Blended $0.74
Context
65,536
Output limit
65,536
Knowledge cutoff
—
Released / updated
2026-02-24 / 2026-02-24
Capabilities
ReasoningTool use? Structured output✓ Temperature✓ Attachments
Modalities
Text
License
Apache-2.0
Weights
Hugging Face

Available at 1 providers1 with public prices

  • ProviderInput / Output
  • Thinking MachinesFirst-party
    Qwen/Qwen3.5-35B-A3B-Base
    $0.54 / $1.34
    Cache read $0.11Context 65,536Output limit 65,536
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Thinking Machines
Qwen/Qwen3.5-35B-A3B-Base
First-party$0.54$1.34$0.11—65,53665,536

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Thinking Machines$122.91
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list —Output list —Min blended $0.74

Price history accumulates from each data sync; currently only 1 sample(s) (2026-10-21). Each future sync adds a point, and once accumulated a line is drawn here.

Related models

Qwen4 Maxsame series—Qwen 3.6 Plus Uncensoredsame series—Qwen 3.8 27B Uncensoredsame series—
Data partly from models.dev (MIT)