Price Per TokenPrice Per Token
Microsoft
Microsoft
vs
Mistral AI
Mistral AI

Phi-3 Mini 128K 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

Phi-3 Mini 128K Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
  • Higher intelligence benchmark

Mistral Medium 3.1 wins:

  • Larger context window
  • Faster response time
  • Better at coding
  • Better at math
  • Supports vision
Price Advantage
Phi-3 Mini 128K Instruct
Benchmark Advantage
Mistral Medium 3.1
Context Window
Mistral Medium 3.1
Speed
Mistral Medium 3.1

Pricing Comparison

Price Comparison

MetricPhi-3 Mini 128K InstructMistral Medium 3.1Winner
Input (per 1M tokens)$0.10$0.40 Phi-3 Mini 128K Instruct
Output (per 1M tokens)$0.10$2.00 Phi-3 Mini 128K Instruct
Using a 3:1 input/output ratio, Phi-3 Mini 128K Instruct is 88% cheaper overall.

Phi-3 Mini 128K Instruct Providers

No provider data available

Mistral Medium 3.1 Providers

No provider data available

Benchmark Comparison

7
Benchmarks Compared
1
Phi-3 Mini 128K Instruct Wins
2
Mistral Medium 3.1 Wins

Benchmark Scores

BenchmarkPhi-3 Mini 128K InstructMistral Medium 3.1Winner
Intelligence Index
Overall intelligence score
26.321.3
Coding Index
Code generation & understanding
-18.3-
Math Index
Mathematical reasoning
-38.3-
MMLU Pro
Academic knowledge
30.468.3
GPQA
Graduate-level science
9.158.8
LiveCodeBench
Competitive programming
-40.6-
BBH
Big-Bench Hard
37.1--
Mistral Medium 3.1 significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
Phi-3 Mini 128K Instruct
Other models

Context & Performance

Context Window

Phi-3 Mini 128K Instruct
128,000
tokens
Mistral Medium 3.1
131,072
tokens
Mistral Medium 3.1 has a 2% larger context window.

Speed Performance

MetricPhi-3 Mini 128K InstructMistral Medium 3.1Winner
Tokens/secondN/A78.1 tok/s
Time to First TokenN/A0.42s

Capabilities

Feature Comparison

FeaturePhi-3 Mini 128K InstructMistral Medium 3.1
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyPhi-3 Mini 128K InstructMistral Medium 3.1
LicenseOpen SourceProprietary
AuthorMicrosoftMistral AI
ReleasedUnknownAug 2025

Phi-3 Mini 128K Instruct Modalities

Input
Output

Mistral Medium 3.1 Modalities

Input
textimage
Output
text

Related Comparisons

Compare Phi-3 Mini 128K Instruct with:

Compare Mistral Medium 3.1 with:

Frequently Asked Questions

Phi-3 Mini 128K Instruct has cheaper input pricing at $0.10/M tokens. Phi-3 Mini 128K Instruct has cheaper output pricing at $0.10/M tokens.
Mistral Medium 3.1 scores higher on coding benchmarks with a score of 18.3, compared to Phi-3 Mini 128K Instruct's score of N/A.
Phi-3 Mini 128K Instruct has a 128,000 token context window, while Mistral Medium 3.1 has a 131,072 token context window.
Phi-3 Mini 128K Instruct does not support vision. Mistral Medium 3.1 supports vision.