token.app › Compare › GPT-3.5 Turbo Instruct vs Inkling Small

GPT-3.5 Turbo Instruct vs Inkling Small

Inkling Small is 2.5× 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
GPT-3.5 Turbo InstructInkling Small
ProviderOpenAIThinkingmachines
Input $/1M$1.50$0.450
Output $/1M$2.00$1.20
Blended $/1M$1.63$0.637
Context window4K524K
Max output4K262K
ReleasedSep 2023Jul 2026
LicenceProprietaryOpen weights
Choose GPT-3.5 Turbo Instruct if…
  • No clear advantage on the data we hold.
Choose Inkling Small if…
  • Costs less per token — $0.637 vs $1.63 blended
  • Larger context window (524K)
  • Open weights — self-hostable
  • Newer model (released Jul 2026)
FAQ
Which is better, GPT-3.5 Turbo Instruct or Inkling Small?
We do not hold independently-run benchmark scores covering both GPT-3.5 Turbo Instruct and Inkling Small, so we make no quality claim. Their pricing and specifications are compared on this page.
Is GPT-3.5 Turbo Instruct cheaper than Inkling Small?
Inkling Small is cheaper: $0.637 versus $1.63 per million tokens blended at 3:1 input:output. Input alone: $1.50 vs $0.450. Output alone: $2.00 vs $1.20.
What context windows do GPT-3.5 Turbo Instruct and Inkling Small have?
GPT-3.5 Turbo Instruct: 4,095 tokens. Inkling Small: 524,288 tokens.
Who makes GPT-3.5 Turbo Instruct and Inkling Small?
GPT-3.5 Turbo Instruct is made by OpenAI. Inkling Small is made by Thinkingmachines.
Related comparisons
GPT-3.5 Turbo Instruct full details Inkling Small full details GPT-3.5 Turbo Instruct vs Ling 3.0 Tiny (free) GPT-3.5 Turbo Instruct vs Muse Spark 1.2 GPT-3.5 Turbo Instruct vs Qwen3.8 Max GPT-3.5 Turbo Instruct vs DeepSeek V4 Flash Latest GPT-3.5 Turbo Instruct vs DeepSeek V4 Flash 0731 GPT-3.5 Turbo Instruct vs Qwen3.7 Flash