AI model comparison
Mistral Large 4 vs Claude Sonnet 5
Side by side comparison of Mistral Large 4 and Claude Sonnet 5 on pricing, benchmark scores, context window, and more.
Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads.
- Input / 1M
- $1.36
- Output / 1M
- $4.18
- Context
- 1.05M
Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work.
- Input / 1M
- $2
- Output / 1M
- $10
- Context
- 1M
Comparing image generators? Compare image models
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Mistral Large 4
1.9x cheaper for a typical chat
Higher intelligence score
Mistral Large 4
38.4 vs 38.2 on Artificial Analysis
Larger context window
Mistral Large 4
1.05M vs 1M tokens
Newer release
Mistral Large 4
Released October 6, 2026
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mistral Large 438.4
Claude Sonnet 538.2Coding index
Mistral Large 4Not availableClaude Sonnet 571.5Agentic index
Mistral Large 4Not availableClaude Sonnet 543.6Pricing
Mistral Large 4 vs Claude Sonnet 5 API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mistral Large 4 | Claude Sonnet 5 |
|---|---|---|
| Input tokensPer 1M tokens | $1.36 | $2 |
| Output tokensPer 1M tokens | $4.18 | $10 |
| Cached input (read)Per 1M tokens | $0.14 | $0.20 |
| Cache writePer 1M tokens | Not available | $2.50 |
| Web searchPer request | Not available | $0.01 |
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 4$4.81Claude Sonnet 5$9Coding task
30K in, 4K out
Mistral Large 4$57.52$20.92 cachedClaude Sonnet 5$100$46 cachedLong document summary
150K in, 2K out
Mistral Large 4$212.36$29.36 cachedClaude Sonnet 5$320$50 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mistral Large 4 | Claude Sonnet 5 |
|---|---|---|
| Context window | 1.05M tokens | 1M tokens |
| Max output | 262K tokens | 128K tokens |
| Input types | Image, Text | File, Image, Text |
| Output types | Text | Text |
| Reasoning effort levels | High, None | Max, Extra high, High, Medium, Low, None |
| Default reasoning effort | High | High |
| Release date | October 6, 2026 | June 30, 2026 |
Features
Supported features
API features available for each model.
| Metric | Mistral Large 4 | Claude Sonnet 5 |
|---|---|---|
| Tool calling | Supported | Supported |
| Structured outputs | Supported | Supported |
| JSON mode | Supported | Supported |
| Reasoning | Supported | Supported |
| Temperature | Supported | Not supported |
| Stop sequences | Supported | Supported |
| Deterministic seed | Supported | Not supported |
| Verbosity control | Not supported | Supported |
Keep exploring
More on these models
Other head-to-heads, the full model page, and the alternatives list for each model.
Mistral Large 4View full model details- Mistral Large 4 vs Gemini 3.8 Flash
- Mistral Large 4 vs Qwen3.8 2.4T A95B
- Mistral Large 4 vs Gemini 3.7 Flash
- Mistral Large 4 vs DeepSeek V4.1 Flash 1017
- Mistral Large 4 vs Muse Spark 1.2
- Mistral Large 4 vs Grok 4.5
- Mistral Large 4 vs GPT-5.5
- Mistral Large 4 vs GPT-6 Luna
- Mistral Large 4 vs GPT-5.6 Luna
- Mistral Large 4 vs DeepSeek V4 Pro 0813
- Mistral Large 4 vs Gemini 3.6 Flash
- Mistral Large 4 vs Muse Spark 1.1
Claude Sonnet 5View full model details- Claude Sonnet 5 vs DeepSeek V4.1 Flash 1017
- Claude Sonnet 5 vs Kimi K3
- Claude Sonnet 5 vs Gemini 3.8 Flash
- Claude Sonnet 5 vs GPT-5.6 Terra
- Claude Sonnet 5 vs Claude Opus 4.8
- Claude Sonnet 5 vs GLM 5.2
- Claude Sonnet 5 vs Claude Opus 4.7
- Claude Sonnet 5 vs Qwen3.8 2.4T A95B
- Claude Sonnet 5 vs Gemini 3.7 Flash
- Claude Sonnet 5 vs Muse Spark 1.2
- Claude Sonnet 5 vs GPT-5.4
- Claude Sonnet 5 vs Grok 4.5
- Claude Sonnet 5 vs GPT-5.5
- Claude Sonnet 5 vs Gemini 3.5 Flash
- Claude Sonnet 5 vs GPT-5.3-Codex
- Claude Sonnet 5 vs Claude Opus 4.6
- Claude Sonnet 5 vs Claude Sonnet 4.6
- Claude Sonnet 5 vs Claude Opus 4.5
Our take
Mistral Large 4 is 1.9x cheaper for a typical chat. Mistral Large 4 scores higher on the Artificial Analysis Intelligence Index (38.4 vs 38.2). Mistral Large 4 has the larger context window (1.05M vs 1M 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 4 or Claude Sonnet 5 cheaper?
Mistral Large 4 is cheaper for a typical chat (2K input tokens and 500 output tokens). Mistral Large 4 costs $1.36 per 1M input tokens and $4.18 per 1M output tokens, while Claude Sonnet 5 costs $2 per 1M input tokens and $10 per 1M output tokens.
Which has a bigger context window, Mistral Large 4 or Claude Sonnet 5?
Mistral Large 4 supports up to 1.05M tokens of context, compared with 1M for Claude Sonnet 5.
Is Mistral Large 4 smarter than Claude Sonnet 5?
On the Artificial Analysis Intelligence Index, Mistral Large 4 scores 38.4 and Claude Sonnet 5 scores 38.2, putting Mistral Large 4 ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mistral Large 4 and Claude Sonnet 5 at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mistral Large 4 and Claude Sonnet 5 answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mistral Large 4 and Claude Sonnet 5 at the same time. Compare the answers side by side and keep the best one.