GPT-4o vs Mistral Large 3: API pricing

OpenAI's GPT-4o against Mistral's Mistral Large 3 on price alone — per-token rates, caching, and context window. Run your own workload through both with the calculator below; capability differences are yours to judge on your evals.

	GPT-4o	Mistral Large 3
Input / 1M tokens	$2.50	$0.50
Cached input / 1M	$1.25	—
Output / 1M tokens	$10.00	$1.50
Context window	125K	256K
Max output	16K	256K
Vendor	OpenAI	Mistral

Prices last synced Aug 20, 2026 from the LiteLLM community price catalog — the same catalog Marginal prices real usage events against, refreshed daily. Spot an error? Tell us.

Price takeaways

Input: Mistral Large 3 is 5x cheaper.
Output: Mistral Large 3 is 7x cheaper.
Ratios shift with workload shape — output-heavy traffic weights the output rate, cache-friendly traffic weights the cached rate. The calculator below does the arithmetic on your numbers.

Your workload on both

Your monthly workload

Requests / month

Input tokens / request

Output tokens / request

Cache hit rate 40%

Cache hit rate = share of input tokens served from the provider's prompt cache, billed at the model's cached-input price. Estimates use standard per-token rates — batch discounts, service tiers, and long-context surcharges are not applied.

GPT-4oMistral Large 3

Model	Input	Cached input	Output	Per request	Monthly
Mistral Large 3cheapest	$300	$200*	$375	$0.00175	$875
GPT-4o	$1,500	$500	$2,500	$0.00900	$4,500

Rates used: GPT-4o $2.50 in / $10.00 out · Mistral Large 3 $0.50 in / $1.50 out

Related comparisons

GPT-5.6 vs GPT-4o GPT-5.6 vs Mistral Large 3 GPT-5.6 Terra vs GPT-4o GPT-5.6 Terra vs Mistral Large 3 GPT-5.6 Luna vs GPT-4o GPT-5.6 Luna vs Mistral Large 3 GPT-5 vs GPT-4o GPT-5 vs Mistral Large 3

Switching models? Watch the bill move in real time.

Marginal prices every call against that day's rates, so an A/B between these two shows up as dollars per customer and feature — not a surprise at month end.

Start tracking Read the docs