Mistral-Small-24B-Instruct-2501 vs GPT-4 Turbo

API pricing, benchmark indices and specs — updated 19 October 2026.

mistralai · A · Open weights

Params

23.6 B

Context

32,768

30d

74 K

apache-2.0 · commercial OK

openai · B · API-only

Input / 1M

$10.00

Output / 1M

$30.00

AA index

proprietary · 128K context

Specification comparison

Differences are highlighted; identical values are muted.

Specification	Mistral-Small-24B-Instruct-2501	GPT-4 Turbo
Deployment	Open weights · also via API	API-only (closed weights)
Parameters	23.6 B	n/a — API-only
Architecture	MistralForCausalLM	n/a — API-only
Context length	32,768	128,000
Licence	apache-2.0	Proprietary
Commercial use	Allowed	Per API terms
Languages	10	n/a — API-only
Downloads 30d	73,988	n/a — API-only
Downloads all time	7.4 M	n/a — API-only
Quantizations on the Hub	SAFETENSORS	n/a — API-only
Gated	No	n/a — API-only
First seen on the Hub	2025-01-28	n/a — API-only
API input price / 1M tokens	$0.05	$10.00
API output price / 1M tokens	$0.08	$30.00
Est. cost per 1M input + 1M output tokens	$0.13	$40.00
Cached input / 1M tokens	—	—
AA Intelligence Index	6.7	7
AA Coding Index	—	21.5
AA Agentic Index	—	—
Max output tokens	16,384	4,096
API providers	1	1
Tool calling	No	Yes
Reasoning mode	No	No

Estimated cost of 1M input + 1M output tokens via OpenRouter

Mistral-Small-24B-Instruct-2501 $0.13

GPT-4 Turbo $40.00

Mistral-Small-24B-Instruct-2501 is 307.7× cheaper at list price.

On RTX 4090 · 24 GB · 8K context unless noted

Mistral-Small-24B-Instruct-2501 · fp16 107.8 GB / 24 GB

❌ Won’t fit