token.app › Compare › Qwen3.5 397B A17B vs Inkling Small

Qwen3.5 397B A17B vs Inkling Small

Inkling Small is 1.4× cheaper per token on a blended 3:1 basis. Inkling Small accepts the larger context window (524K).

Head to head
Blended price uses a 3:1 input:output mix
Qwen3.5 397B A17BInkling Small
ProviderAlibabaThinkingmachines
Input $/1M$0.390$0.450
Output $/1M$2.34$1.20
Blended $/1M$0.877$0.637
Context window262K524K
Max output66K262K
ReleasedFeb 2026Jul 2026
LicenceOpen weightsOpen weights
Choose Qwen3.5 397B A17B if…
  • No clear advantage on the data we hold.
Choose Inkling Small if…
  • Costs less per token — $0.637 vs $0.877 blended
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Qwen3.5 397B A17B or Inkling Small?
We do not hold independently-run benchmark scores covering both Qwen3.5 397B A17B and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Qwen3.5 397B A17B cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $0.877 per million tokens blended at 3:1 input:output. Input alone: $0.390 vs $0.450. Output alone: $2.34 vs $1.20.
What context windows do Qwen3.5 397B A17B and Inkling Small have?
Qwen3.5 397B A17B: 262,144 tokens. Inkling Small: 524,288 tokens.
Who makes Qwen3.5 397B A17B and Inkling Small?
Qwen3.5 397B A17B is made by Alibaba. Inkling Small is made by Thinkingmachines.
Related comparisons