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

Llama 3.3 70B 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 3.3 70B Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Faster response time

Mistral Medium 3.1 wins:

  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Supports vision
Price Advantage
Llama 3.3 70B Instruct
Benchmark Advantage
Mistral Medium 3.1
Context Window
Mistral Medium 3.1
Speed
Llama 3.3 70B Instruct

Pricing Comparison

Price Comparison

MetricLlama 3.3 70B InstructMistral Medium 3.1Winner
Input (per 1M tokens)$0.10$0.40 Llama 3.3 70B Instruct
Output (per 1M tokens)$0.32$2.00 Llama 3.3 70B Instruct
Cache Read (per 1M)$0.13N/A Llama 3.3 70B Instruct
Using a 3:1 input/output ratio, Llama 3.3 70B Instruct is 81% cheaper overall.

Llama 3.3 70B Instruct Providers

No provider data available

Mistral Medium 3.1 Providers

No provider data available

Benchmark Comparison

8
Benchmarks Compared
1
Llama 3.3 70B Instruct Wins
5
Mistral Medium 3.1 Wins

Benchmark Scores

BenchmarkLlama 3.3 70B InstructMistral Medium 3.1Winner
Intelligence Index
Overall intelligence score
14.521.3
Coding Index
Code generation & understanding
10.718.3
Math Index
Mathematical reasoning
7.738.3
MMLU Pro
Academic knowledge
71.368.3
GPQA
Graduate-level science
49.858.8
LiveCodeBench
Competitive programming
28.840.6
Aider
Real-world code editing
59.4--
AIME
Competition math
30.0--
Mistral Medium 3.1 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Llama 3.3 70B Instruct
Other models

Context & Performance

Context Window

Llama 3.3 70B Instruct
131,072
tokens
Mistral Medium 3.1
131,072
tokens

Speed Performance

MetricLlama 3.3 70B InstructMistral Medium 3.1Winner
Tokens/second99.5 tok/s78.1 tok/s
Time to First Token0.54s0.42s
Llama 3.3 70B Instruct responds 27% faster on average.

Capabilities

Feature Comparison

FeatureLlama 3.3 70B 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 3.3 70B InstructMistral Medium 3.1
LicenseOpen SourceProprietary
AuthorMeta-llamaMistral AI
ReleasedDec 2024Aug 2025

Llama 3.3 70B Instruct Modalities

Input
text
Output
text

Mistral Medium 3.1 Modalities

Input
textimage
Output
text

Related Comparisons

Compare Llama 3.3 70B Instruct with:

Compare Mistral Medium 3.1 with:

Frequently Asked Questions

Llama 3.3 70B Instruct has cheaper input pricing at $0.10/M tokens. Llama 3.3 70B Instruct has cheaper output pricing at $0.32/M tokens.
Mistral Medium 3.1 scores higher on coding benchmarks with a score of 18.3, compared to Llama 3.3 70B Instruct's score of 10.7.
Llama 3.3 70B Instruct has a 131,072 token context window, while Mistral Medium 3.1 has a 131,072 token context window.
Llama 3.3 70B Instruct does not support vision. Mistral Medium 3.1 supports vision.