GPT-4o vs Mistral Large 2: Detailed Comparison
Choosing between GPT-4o (OpenAI) and
Mistral Large 2 (Mistral AI) comes down to three things:
per-token pricing, context window, and which capability matters most for your workload.
GPT-4o costs $2.50/M input vs
$2.00/M for Mistral Large 2;
context windows are 128K vs
128K tokens. Detailed breakdown below.
Side-by-side specs
| Spec | GPT-4o | Mistral Large 2 |
|---|
| Provider | OpenAI | Mistral AI |
|---|
| Released | 2024-05-13 | 2024-07-24 |
|---|
| Input price |
$2.50/M |
$2.00/M |
| Output price |
$10.00/M |
$6.00/M |
| Cached input |
$1.2500/M |
— |
| Context window |
128K |
128K |
| Max output |
16K |
8K |
| Modalities |
text image audio |
text |
| Tokenizer |
o200k_base |
mistral |
Capability matrix
| Capability | GPT-4o | Mistral Large 2 |
|---|
| function calling |
Yes |
Yes |
| json mode |
Yes |
Yes |
| vision |
Yes |
No |
| streaming |
Yes |
Yes |
| audio |
Yes |
No |
Benchmark comparison
Higher is better for all benchmarks shown.
| Benchmark | Category | GPT-4o | Mistral Large 2 | Δ |
|---|
| MMLU |
general |
88.7 |
84.0 |
+4.7 |
| HumanEval |
coding |
90.2 |
92.0 |
-1.8 |
| MMMU |
multimodal |
69.1 |
— |
— |
Per-call cost on typical workloads
| Workload (in/out tokens) | GPT-4o | Mistral Large 2 | Cheaper by |
|---|
| Standard chat (1K / 500) |
$0.007500 |
$0.005000 |
Mistral Large 2 by $0.002500 |
| RAG (4K / 500) |
$0.015000 |
$0.011000 |
Mistral Large 2 by $0.004000 |
| Long doc (20K / 1K) |
$0.060000 |
$0.046000 |
Mistral Large 2 by $0.014000 |
| Very long context (100K / 2K) |
$0.265000 |
$0.209000 |
Mistral Large 2 by $0.056000 |
When to choose GPT-4o over Mistral Large 2
- Supports vision — Mistral Large 2 does not.
- Supports audio — Mistral Large 2 does not.
When to choose Mistral Large 2 over GPT-4o
- Per-token input cost is 20% lower than GPT-4o.
Related comparisons