GPT-3.5 Turbo Instruct vs Mistral Large 4

Price, context window & benchmark comparison

OpenAI

GPT-3.5 Turbo Instruct

OpenAI
$1.50 / $2.00
Input / Output · per 1M tokens
VS
Mistral AI

Mistral Large 4

Mistral AI
$0.70 / $2.10
Input / Output · per 1M tokens
Compare different models
OpenAI
Mistral AI
Verdict: Mistral Large 4 is 35% cheaper than GPT-3.5 Turbo Instruct on a typical 3:1 input/output mix. Mistral Large 4 has the larger context window (1M vs 4K).
GPT-3.5 Turbo InstructMistral Large 4
Input price / 1M$1.50$0.70
Output price / 1M$2.00$2.10
Blended price (3:1)$1.63$1.05
Cached input / 1M—$0.07
Context window4K1M
Max output4K262K
Intelligence index—26.1
Coding index——
Providers—2
Best provider uptime (30m)—100.0%
Vision inputNoYes
ReasoningNoYes
Tool callingNoYes
Released2023-09-282026-10-06
Retirement——

Cost calculator

FAQ

Which is cheaper, GPT-3.5 Turbo Instruct or Mistral Large 4?

Mistral Large 4 is 35% cheaper than GPT-3.5 Turbo Instruct on a typical 3:1 input/output mix.

GPT-3.5 Turbo Instruct vs Mistral Large 4: which has a bigger context window?

GPT-3.5 Turbo Instruct: 4,095 tokens. Mistral Large 4: 1,048,576 tokens.

How much would 1 million requests cost?

At 2,000 input + 500 output tokens per request: GPT-3.5 Turbo Instruct ≈ $4,000, Mistral Large 4 ≈ $2,450.

More comparisons