Price Per TokenPrice Per Token
Meta-llama
Meta-llama
vs
Mistral AI
Mistral AI

Llama 3.1 405B Instruct vs Mistral Medium 3.1

A detailed comparison of pricing, benchmarks, and capabilities

108 out of our 483 tracked models have had a price change in March.

Get our weekly newsletter on pricing changes, new releases, and tools.

Key Takeaways

Llama 3.1 405B Instruct wins:

  • Cheaper output tokens

Mistral Medium 3.1 wins:

  • Cheaper input tokens
  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Supports vision
Price Advantage
Llama 3.1 405B Instruct
Benchmark Advantage
Mistral Medium 3.1
Context Window
Mistral Medium 3.1
Speed
Mistral Medium 3.1

Pricing Comparison

Price Comparison

MetricLlama 3.1 405B InstructMistral Medium 3.1Winner
Input (per 1M tokens)$0.90$0.40 Mistral Medium 3.1
Output (per 1M tokens)$0.90$2.00 Llama 3.1 405B Instruct
Cache Read (per 1M)$0.45N/A Llama 3.1 405B Instruct
Using a 3:1 input/output ratio, Mistral Medium 3.1 is 11% cheaper overall.

Llama 3.1 405B Instruct Providers

No provider data available

Mistral Medium 3.1 Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
1
Llama 3.1 405B Instruct Wins
5
Mistral Medium 3.1 Wins

Benchmark Scores

BenchmarkLlama 3.1 405B InstructMistral Medium 3.1Winner
Intelligence Index
Overall intelligence score
17.421.3
Coding Index
Code generation & understanding
14.518.3
Math Index
Mathematical reasoning
3.038.3
MMLU Pro
Academic knowledge
73.268.3
GPQA
Graduate-level science
51.558.8
LiveCodeBench
Competitive programming
30.540.6
Aider
Real-world code editing
66.2--
AIME
Competition math
21.3--
Mistral Medium 3.1 shows stronger mathematical reasoning abilities.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Llama 3.1 405B Instruct
Other models

Context & Performance

Context Window

Llama 3.1 405B Instruct
131,000
tokens
Mistral Medium 3.1
131,072
tokens
Mistral Medium 3.1 has a 0% larger context window.

Speed Performance

MetricLlama 3.1 405B InstructMistral Medium 3.1Winner
Tokens/second33.7 tok/s78.1 tok/s
Time to First Token0.71s0.42s
Mistral Medium 3.1 responds 132% faster on average.

Capabilities

Feature Comparison

FeatureLlama 3.1 405B InstructMistral Medium 3.1
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyLlama 3.1 405B InstructMistral Medium 3.1
LicenseOpen SourceProprietary
AuthorMeta-llamaMistral AI
ReleasedJul 2024Aug 2025

Llama 3.1 405B Instruct Modalities

Input
text
Output
text

Mistral Medium 3.1 Modalities

Input
textimage
Output
text

Related Comparisons

Compare Llama 3.1 405B Instruct with:

Compare Mistral Medium 3.1 with:

Frequently Asked Questions

Mistral Medium 3.1 has cheaper input pricing at $0.40/M tokens. Llama 3.1 405B Instruct has cheaper output pricing at $0.90/M tokens.
Mistral Medium 3.1 scores higher on coding benchmarks with a score of 18.3, compared to Llama 3.1 405B Instruct's score of 14.5.
Llama 3.1 405B Instruct has a 131,000 token context window, while Mistral Medium 3.1 has a 131,072 token context window.
Llama 3.1 405B Instruct does not support vision. Mistral Medium 3.1 supports vision.