AI model comparison
Mistral Large 2407 vs GPT-4
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Mistral
Mistral Large 2407
This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more.
- Input / 1M
- $2
- Output / 1M
- $6
- Context
- 131K
OpenAI
GPT-4
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning
- Input / 1M
- $30
- Output / 1M
- $60
- Context
- 8K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mistral Large 2407
12.9x cheaper for a typical chat
Higher intelligence score
Mistral Large 2407
7.6 vs 6.7 on Artificial Analysis
Larger context window
Mistral Large 2407
131K vs 8K tokens
Newer release
Mistral Large 2407
Released November 19, 2024
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mistral Large 24077.6GPT-46.7Coding index
Mistral Large 2407Not availableGPT-413.1Agentic index
Mistral Large 2407Not availableGPT-4Not availablePricing
Mistral Large 2407 vs GPT-4 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mistral Large 2407 | GPT-4 |
|---|---|---|
| Input tokensPer 1M tokens | $2 | $30 |
| Output tokensPer 1M tokens | $6 | $60 |
| Cached input (read)Per 1M tokens | $0.20 | Not available |
| Cache writePer 1M tokens | Not available | Not available |
What it costs in practice
Estimated cost per 1,000 requests at standard rates. Coding and long-document figures also show the cost when the input is already cached.
Chat message
2K in, 500 out
Mistral Large 2407$7GPT-4$90Coding task
30K in, 4K out
Mistral Large 2407$84$30 cachedGPT-4$1140Long document summary
150K in, 2K out
Mistral Large 2407$312$42 cachedGPT-4$4620Specs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mistral Large 2407 | GPT-4 |
|---|---|---|
| Context window | 131K tokens | 8K tokens |
| Max output | 105K tokens | 4K tokens |
| Input types | File, Text | Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | November 19, 2024 | May 28, 2023 |
Features
Supported features
API features available for each model.
| Metric | Mistral Large 2407 | GPT-4 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Not supported | Not supported |
| Temperature | Supported | Supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Supported |
| Verbosity control | Not supported | Not supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Mistral Large 2407View full model details- Mistral Large 2407 vs Mistral Medium 3.1
- Mistral Large 2407 vs Nova Premier 1.0
- Mistral Large 2407 vs Mistral Medium 3
- Mistral Large 2407 vs Devstral 2 2512
- Mistral Large 2407 vs GPT-4o (2024-11-20)
- Mistral Large 2407 vs GPT-4o (2024-08-06)
- Mistral Large 2407 vs Sonar Pro
- Mistral Large 2407 vs Hermes 4 405B
- Mistral Large 2407 vs GPT-4o (2024-05-13)
- Mistral Large 2407 vs Nova Pro 1.0
- Mistral Large 2407 vs GPT-4 Turbo
- Mistral Large 2407 vs Mistral Large
- Mistral Large 2407 vs Mixtral 8x22B Instruct
Our take
Mistral Large 2407 is 12.9x cheaper for a typical chat. Mistral Large 2407 scores higher on the Artificial Analysis Intelligence Index (7.6 vs 6.7). Mistral Large 2407 has the larger context window (131K vs 8K tokens). The right pick depends on your workload, so the quickest way to settle it is to send the same prompt to both and compare.
FAQ
Frequently asked questions
Is Mistral Large 2407 or GPT-4 cheaper?
Mistral Large 2407 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mistral Large 2407 costs $2 per 1M input tokens and $6 per 1M output tokens, while GPT-4 costs $30 per 1M input tokens and $60 per 1M output tokens.
Which has a bigger context window, Mistral Large 2407 or GPT-4?
Mistral Large 2407 supports up to 131K tokens of context, compared with 8K for GPT-4.
Is Mistral Large 2407 smarter than GPT-4?
On the Artificial Analysis Intelligence Index, Mistral Large 2407 scores 7.6 and GPT-4 scores 6.7, putting Mistral Large 2407 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mistral Large 2407 and GPT-4 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Large 2407 and GPT-4 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mistral Large 2407 and GPT-4 at the same time. Compare the answers side by side and keep the best one.