O

GPT-3.5 Turbo vs Mistral Medium 3

M

OpenAI · 16k context | Mistral · 128k context

Pricing Comparison

Metric	GPT-3.5 Turbo	Mistral Medium 3
Input / 1M tokens	$0.5	$0.4
Output / 1M tokens	$1.5	$2
Cached input / 1M	—	—
Context window	16k	128k
Provider	OpenAI	Mistral

Cost Calculator

Input tokens

Output tokens

Requests/day

💰 GPT-3.5 Turbo saves $45.00/month (11% cheaper)

OGPT-3.5 TurboCHEAPER

Per request$0.001250

Daily$12.50

Monthly$375.00

Yearly$4,562.50

MMistral Medium 3

Per request$0.001400

Daily$14.00

Monthly$420.00

Yearly$5,110.00

O

Choose GPT-3.5 Turbo when…

✓ Cheaper for generation-heavy workloads (lower output cost)
✓ Optimized for: Legacy chat applications

M

Choose Mistral Medium 3 when…

✓ Cheaper for RAG & document retrieval (lower input cost)
✓ 20% cheaper per input token
✓ Larger context window (128k vs 16k) — better for long documents
✓ Optimized for: Budget frontier tasks

Related Comparisons

GPT-3.5 Turbo vs GPT-5 GPT-3.5 Turbo vs GPT-5 Mini GPT-3.5 Turbo vs GPT-4.1 GPT-3.5 Turbo vs GPT-4.1 Mini Mistral Medium 3 vs GPT-5 Mistral Medium 3 vs GPT-5 Mini