token.app › Compare › GPT-3.5 Turbo Instruct vs Mercury 3

GPT-3.5 Turbo Instruct vs Mercury 3

Mercury 3 is 10× cheaper per token on a blended 3:1 basis. Mercury 3 accepts the larger context window (1M).

Head to head
Blended price uses a 3:1 input:output mix
GPT-3.5 Turbo InstructMercury 3
ProviderOpenAIInception
Input $/1M$1.50$0.100
Output $/1M$2.00$0.350
Blended $/1M$1.63$0.163
Context window4K1M
Max output4K131K
ReleasedSep 2023Oct 2026
LicenceProprietaryProprietary
Choose GPT-3.5 Turbo Instruct if…
  • No clear advantage on the data we hold.
Choose Mercury 3 if…
  • Costs less per token — $0.163 vs $1.63 blended
  • Larger context window (1M)
  • Newer model (released Oct 2026)
FAQ
Which is better, GPT-3.5 Turbo Instruct or Mercury 3?
We do not hold independently-run benchmark scores covering both GPT-3.5 Turbo Instruct and Mercury 3, so we make no quality claim. Their pricing and specifications are compared on this page.
Is GPT-3.5 Turbo Instruct cheaper than Mercury 3?
Mercury 3 is cheaper: $0.163 versus $1.63 per million tokens blended at 3:1 input:output. Input alone: $1.50 vs $0.100. Output alone: $2.00 vs $0.350.
What context windows do GPT-3.5 Turbo Instruct and Mercury 3 have?
GPT-3.5 Turbo Instruct: 4,095 tokens. Mercury 3: 1,000,000 tokens.
Who makes GPT-3.5 Turbo Instruct and Mercury 3?
GPT-3.5 Turbo Instruct is made by OpenAI. Mercury 3 is made by Inception.
Related comparisons
GPT-3.5 Turbo Instruct full details Mercury 3 full details GPT-3.5 Turbo Instruct vs Flint (free) GPT-3.5 Turbo Instruct vs MiniMax M3.1 Flash (free) GPT-3.5 Turbo Instruct vs DeepSeek V4.1 Flash 1017 GPT-3.5 Turbo Instruct vs Glimpse GPT-3.5 Turbo Instruct vs Xing4.0 29B A4B (free) GPT-3.5 Turbo Instruct vs Beam 1.0 501B A23B