token.app › Compare › Voxtral Small 24B 2507 vs Inkling Small

Voxtral Small 24B 2507 vs Inkling Small

Voxtral Small 24B 2507 is 4.2× 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
Voxtral Small 24B 2507Inkling Small
ProviderMistral AIThinkingmachines
Input $/1M$0.100$0.450
Output $/1M$0.300$1.20
Blended $/1M$0.150$0.637
Context window32K524K
Max output—262K
ReleasedOct 2025Jul 2026
LicenceOpen weightsOpen weights
Choose Voxtral Small 24B 2507 if…
  • Costs less per token — $0.150 vs $0.637 blended
Choose Inkling Small if…
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Voxtral Small 24B 2507 or Inkling Small?
We do not hold independently-run benchmark scores covering both Voxtral Small 24B 2507 and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is Voxtral Small 24B 2507 cheaper than Inkling Small?
Voxtral Small 24B 2507 is cheaper: $0.150 versus $0.637 per million tokens blended at 3:1 input:output. Input alone: $0.100 vs $0.450. Output alone: $0.300 vs $1.20.
What context windows do Voxtral Small 24B 2507 and Inkling Small have?
Voxtral Small 24B 2507: 32,000 tokens. Inkling Small: 524,288 tokens.
Who makes Voxtral Small 24B 2507 and Inkling Small?
Voxtral Small 24B 2507 is made by Mistral AI. Inkling Small is made by Thinkingmachines.
Related comparisons
Voxtral Small 24B 2507 full details Inkling Small full details Voxtral Small 24B 2507 vs Ling 3.0 Tiny (free) Voxtral Small 24B 2507 vs Muse Spark 1.2 Voxtral Small 24B 2507 vs Qwen3.8 Max Voxtral Small 24B 2507 vs DeepSeek V4 Flash Latest Voxtral Small 24B 2507 vs DeepSeek V4 Flash 0731 Voxtral Small 24B 2507 vs Qwen3.7 Flash