Price Per TokenPrice Per Token
Deepseek
Deepseek
vs
Microsoft
Microsoft

DeepSeek V3.1 Terminus vs Phi-3 Mini 128K Instruct

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

DeepSeek V3.1 Terminus wins:

  • Larger context window
  • Faster response time
  • Higher intelligence benchmark
  • Better at coding
  • Better at math
  • Has reasoning mode

Phi-3 Mini 128K Instruct wins:

  • Cheaper input tokens
  • Cheaper output tokens
Price Advantage
Phi-3 Mini 128K Instruct
Benchmark Advantage
DeepSeek V3.1 Terminus
Context Window
DeepSeek V3.1 Terminus
Speed
DeepSeek V3.1 Terminus

Pricing Comparison

Price Comparison

MetricDeepSeek V3.1 TerminusPhi-3 Mini 128K InstructWinner
Input (per 1M tokens)$0.21$0.10 Phi-3 Mini 128K Instruct
Output (per 1M tokens)$0.79$0.10 Phi-3 Mini 128K Instruct
Cache Read (per 1M)$0.12N/A DeepSeek V3.1 Terminus
Using a 3:1 input/output ratio, Phi-3 Mini 128K Instruct is 72% cheaper overall.

DeepSeek V3.1 Terminus Providers

No provider data available

Phi-3 Mini 128K Instruct Providers

No provider data available

Benchmark Comparison

7
Benchmarks Compared
3
DeepSeek V3.1 Terminus Wins
0
Phi-3 Mini 128K Instruct Wins

Benchmark Scores

BenchmarkDeepSeek V3.1 TerminusPhi-3 Mini 128K InstructWinner
Intelligence Index
Overall intelligence score
28.526.3
Coding Index
Code generation & understanding
31.9--
Math Index
Mathematical reasoning
53.7--
MMLU Pro
Academic knowledge
83.630.4
GPQA
Graduate-level science
75.19.1
LiveCodeBench
Competitive programming
52.9--
BBH
Big-Bench Hard
-37.1-
DeepSeek V3.1 Terminus significantly outperforms in coding benchmarks.

Cost vs Quality

X-axis:
Y-axis:
Loading chart...
DeepSeek V3.1 Terminus
Other models

Context & Performance

Context Window

DeepSeek V3.1 Terminus
163,840
tokens
Phi-3 Mini 128K Instruct
128,000
tokens
DeepSeek V3.1 Terminus has a 22% larger context window.

Speed Performance

MetricDeepSeek V3.1 TerminusPhi-3 Mini 128K InstructWinner
Tokens/second0.0 tok/sN/A
Time to First Token0.00sN/A

Capabilities

Feature Comparison

FeatureDeepSeek V3.1 TerminusPhi-3 Mini 128K Instruct
Vision (Image Input)
Tool/Function Calls
Reasoning Mode
Audio Input
Audio Output
PDF Input
Prompt Caching
Web Search

License & Release

PropertyDeepSeek V3.1 TerminusPhi-3 Mini 128K Instruct
LicenseOpen SourceOpen Source
AuthorDeepseekMicrosoft
ReleasedSep 2025Unknown

DeepSeek V3.1 Terminus Modalities

Input
text
Output
text

Phi-3 Mini 128K Instruct Modalities

Input
Output

Related Comparisons

Compare DeepSeek V3.1 Terminus with:

Compare Phi-3 Mini 128K Instruct 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.
DeepSeek V3.1 Terminus scores higher on coding benchmarks with a score of 31.9, compared to Phi-3 Mini 128K Instruct's score of N/A.
DeepSeek V3.1 Terminus has a 163,840 token context window, while Phi-3 Mini 128K Instruct has a 128,000 token context window.
DeepSeek V3.1 Terminus does not support vision. Phi-3 Mini 128K Instruct does not support vision.