AI model comparison
Mixtral 8x22B Instruct vs Mistral Large
Pricing, context window, benchmarks, and features compared side by side. Or skip the guesswork and send one prompt to both.
Mistral
Mixtral 8x22B Instruct
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size.
- Input / 1M
- $2
- Output / 1M
- $6
- Context
- 66K
Mistral
Mistral Large
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
- 128K
At a glance
Quick verdict
How the two models stack up on the things people ask about most.
Lower price
Tie
Same price for a typical chat
Higher intelligence score
Mistral Large
5.8 vs 5.7 on Artificial Analysis
Larger context window
Mistral Large
128K vs 66K tokens
Newer release
Mixtral 8x22B Instruct
Released April 17, 2024
Benchmarks
Benchmark scores
Independent scores from Artificial Analysis. Higher is better.
Intelligence index
Mixtral 8x22B Instruct5.7Mistral Large5.8Coding index
Mixtral 8x22B InstructNot availableMistral LargeNot availableAgentic index
Mixtral 8x22B InstructNot availableMistral LargeNot availablePricing
Mixtral 8x22B Instruct vs Mistral Large API pricing
Per-token API rates. Cheaper option highlighted.
| Metric | Mixtral 8x22B Instruct | Mistral Large |
|---|---|---|
| Input tokensPer 1M tokens | $2 | $2 |
| Output tokensPer 1M tokens | $6 | $6 |
| Cached input (read)Per 1M tokens | $0.20 | $0.20 |
| 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
Mixtral 8x22B Instruct$7Mistral Large$7Coding task
30K in, 4K out
Mixtral 8x22B Instruct$84$30 cachedMistral Large$84$30 cachedLong document summary
150K in, 2K out
Mixtral 8x22B Instruct$312$42 cachedMistral Large$312$42 cachedSpecs
Context window and capabilities
How much each model can read, how much it can write, and what it accepts as input.
| Metric | Mixtral 8x22B Instruct | Mistral Large |
|---|---|---|
| Context window | 66K tokens | 128K tokens |
| Max output | 52K tokens | 102K tokens |
| Input types | File, Text | File, Text |
| Output types | Text | Text |
| Reasoning effort levels | Not available | Not available |
| Default reasoning effort | Not available | Not available |
| Release date | April 17, 2024 | February 26, 2024 |
Features
Supported features
API features available for each model.
| Metric | Mixtral 8x22B Instruct | Mistral Large |
|---|---|---|
| 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.
Mixtral 8x22B InstructView full model details- Mixtral 8x22B Instruct vs Mistral Medium 3.1
- Mixtral 8x22B Instruct vs Mistral Medium 3
- Mixtral 8x22B Instruct vs Devstral 2 2512
- Mixtral 8x22B Instruct vs GPT-4o (2024-11-20)
- Mixtral 8x22B Instruct vs GPT-4o (2024-08-06)
- Mixtral 8x22B Instruct vs Sonar Pro
- Mixtral 8x22B Instruct vs Mistral Large 2407
- Mixtral 8x22B Instruct vs Hermes 4 405B
- Mixtral 8x22B Instruct vs GPT-4o (2024-05-13)
- Mixtral 8x22B Instruct vs Nova Pro 1.0
- Mixtral 8x22B Instruct vs GPT-4 Turbo
Mistral LargeView full model details- Mistral Large vs Mistral Medium 3.1
- Mistral Large vs Mistral Medium 3
- Mistral Large vs Devstral 2 2512
- Mistral Large vs GPT-4o (2024-11-20)
- Mistral Large vs GPT-4o (2024-08-06)
- Mistral Large vs Sonar Pro
- Mistral Large vs Mistral Large 2407
- Mistral Large vs Hermes 4 405B
- Mistral Large vs GPT-4o (2024-05-13)
- Mistral Large vs Nova Pro 1.0
- Mistral Large vs GPT-4 Turbo
- Mistral Large vs GPT-4
Our take
Mistral Large scores higher on the Artificial Analysis Intelligence Index (5.8 vs 5.7). Mistral Large has the larger context window (128K vs 66K 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 Mixtral 8x22B Instruct or Mistral Large cheaper?
Mixtral 8x22B Instruct and Mistral Large cost the same for a typical chat (2K input tokens and 500 output tokens). Mixtral 8x22B Instruct costs $2 per 1M input tokens and $6 per 1M output tokens, and Mistral Large costs $2 per 1M input tokens and $6 per 1M output tokens.
Which has a bigger context window, Mixtral 8x22B Instruct or Mistral Large?
Mistral Large supports up to 128K tokens of context, compared with 66K for Mixtral 8x22B Instruct.
Is Mixtral 8x22B Instruct smarter than Mistral Large?
On the Artificial Analysis Intelligence Index, Mixtral 8x22B Instruct scores 5.7 and Mistral Large scores 5.8, putting Mistral Large ahead. Benchmarks don't capture everything, so the best test is running your own prompts through both.
Can I use Mixtral 8x22B Instruct and Mistral Large at the same time?
Yes. Shortcut Chat sends one prompt to multiple models at once, so you can see Mixtral 8x22B Instruct and Mistral Large answer side by side and keep the better response.
Why choose? Ask both.
Send one prompt to Mixtral 8x22B Instruct and Mistral Large at the same time. Compare the answers side by side and keep the best one.