token.app › Compare › Mixtral 8x22B Instruct vs Inkling Small

Mixtral 8x22B Instruct vs Inkling Small

Inkling Small leads on 1 of 1 shared benchmarks. Inkling Small is 4.7× 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
Mixtral 8x22B InstructInkling Small
ProviderMistral AIThinkingmachines
Input $/1M$2.00$0.450
Output $/1M$6.00$1.20
Blended $/1M$3.00$0.637
Context window66K524K
Max output52K262K
ReleasedApr 2024Jul 2026
LicenceOpen weightsOpen weights
GPQA Diamond 34.1% 88.5%
Benchmark scores independently run and published by Epoch AI, 'AI Benchmarking Hub', used under CC BY 4.0. Only benchmarks with a score for BOTH models are compared.
Choose Mixtral 8x22B Instruct if…
  • No clear advantage on the data we hold.
Choose Inkling Small if…
  • Costs less per token — $0.637 vs $3.00 blended
  • Higher GPQA Diamond (88.5% vs 34.1%)
  • Larger context window (524K)
  • Newer model (released Jul 2026)
FAQ
Which is better, Mixtral 8x22B Instruct or Inkling Small?
Across the 1 benchmark both models have independently-run scores for, Mixtral 8x22B Instruct leads on 0 and Inkling Small leads on 1. Benchmarks are one input — price and context window are on this page too.
Is Mixtral 8x22B Instruct cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $3.00 per million tokens blended at 3:1 input:output. Input alone: $2.00 vs $0.450. Output alone: $6.00 vs $1.20.
What context windows do Mixtral 8x22B Instruct and Inkling Small have?
Mixtral 8x22B Instruct: 65,536 tokens. Inkling Small: 524,288 tokens.
Who makes Mixtral 8x22B Instruct and Inkling Small?
Mixtral 8x22B Instruct is made by Mistral AI. Inkling Small is made by Thinkingmachines.
Related comparisons
Mixtral 8x22B Instruct full details Inkling Small full details Mixtral 8x22B Instruct vs Flint (free) Mixtral 8x22B Instruct vs MiniMax M3.1 Flash (free) Mixtral 8x22B Instruct vs DeepSeek V4.1 Flash 1017 Mixtral 8x22B Instruct vs Glimpse Mixtral 8x22B Instruct vs Xing4.0 29B A4B (free) Mixtral 8x22B Instruct vs Beam 1.0 501B A23B