Mistral Large 2 vs GPT-4o Mini: Detailed Comparison
Choosing between Mistral Large 2 (Mistral AI) and
GPT-4o Mini (OpenAI) comes down to three things:
per-token pricing, context window, and which capability matters most for your workload.
Mistral Large 2 costs $2.00/M input vs
$0.15/M for GPT-4o Mini;
context windows are 128K vs
128K tokens. Detailed breakdown below.
Side-by-side specs
| Spec | Mistral Large 2 | GPT-4o Mini |
|---|
| Provider | Mistral AI | OpenAI |
|---|
| Released | 2024-07-24 | 2024-07-18 |
|---|
| Input price |
$2.00/M |
$0.15/M |
| Output price |
$6.00/M |
$0.60/M |
| Cached input |
— |
$0.0750/M |
| Context window |
128K |
128K |
| Max output |
8K |
16K |
| Modalities |
text |
text image |
| Tokenizer |
mistral |
o200k_base |
Capability matrix
| Capability | Mistral Large 2 | GPT-4o Mini |
|---|
| function calling |
Yes |
Yes |
| json mode |
Yes |
Yes |
| streaming |
Yes |
Yes |
| vision |
No |
Yes |
Benchmark comparison
Higher is better for all benchmarks shown.
| Benchmark | Category | Mistral Large 2 | GPT-4o Mini | Δ |
|---|
| MMLU |
general |
84.0 |
— |
— |
| HumanEval |
coding |
92.0 |
— |
— |
Per-call cost on typical workloads
| Workload (in/out tokens) | Mistral Large 2 | GPT-4o Mini | Cheaper by |
|---|
| Standard chat (1K / 500) |
$0.005000 |
$0.000450 |
GPT-4o Mini by $0.004550 |
| RAG (4K / 500) |
$0.011000 |
$0.000900 |
GPT-4o Mini by $0.010100 |
| Long doc (20K / 1K) |
$0.046000 |
$0.003600 |
GPT-4o Mini by $0.042400 |
| Very long context (100K / 2K) |
$0.209000 |
$0.015900 |
GPT-4o Mini by $0.193100 |
When to choose Mistral Large 2 over GPT-4o Mini
- Mistral Large 2 fits when your stack is already on Mistral AI (single billing, SDK, observability surface).
When to choose GPT-4o Mini over Mistral Large 2
- Per-token input cost is 93% lower than Mistral Large 2.
- Supports vision — Mistral Large 2 does not.
Related comparisons