by Microsoft· 10 months ago
Chain-of-thought reasoning variant of Phi-4, competitive with much larger models on math and logic tasks.
Context Window
32K
Max Output
8K
TTFT
150ms
Speed
130 tok/s
Input Price
$0.04/M tokens
Output Price
$0.04/M tokens
Performance Profile
Strong mid-tier performance balancing capability and cost
32K token context window for substantial input processing
Fully open source — self-host, fine-tune, and customize without restrictions
14B parameter architecture for deep reasoning
vs similar-tier models
| Model | Input | Output | Context | Avg Score |
|---|---|---|---|---|
Phi-4-reasoningCurrent Microsoft | $0.04 | $0.04 | 32K | 78.6 |
o3-mini OpenAI | $1.10 | $4.40 | 200K | 86.3 |
DeepSeek-R1 DeepSeek | $0.55 | $2.19 | 128K | 87.0 |
Summarize an email
<$0.001~300 word email → short summary
400 in · 100 out
Analyze a 1,000-word article
<$0.001Blog post or news article → detailed analysis
1,333 in · 500 out
Chatbot conversation (10 turns)
<$0.001Full customer support interaction
4,000 in · 2,000 out
Summarize a 50-page report
$0.0016Legal contract or research paper → key points
37,500 in · 2,000 out
Review a 5,000-line codebase
$0.0011Full code review with suggestions
25,000 in · 3,000 out
Process a full novel
$0.0050~90,000 words → detailed summary & analysis
120,000 in · 5,000 out
Email summaries
$0.60/mo
$0.02/day
Chat conversations
$7/mo
$0.24/day
Document analysis
$47/mo
$2/day
No ratings yet. Be the first to rate this model!
Sign in to rate this model and share your experience.
Sign in to leave a comment and join the discussion.
Microsoft
Microsoft's compact open-source model with 128K context. Great for on-device inference.
Input
$0.01/M
Output
$0.01/M
Context
128K
Microsoft
Microsoft's open-source MoE model with 42B total params and only 6.6B active.
Input
$0.06/M
Output
$0.06/M
Context
128K
Microsoft
Microsoft's 14B open-source model with 128K context and strong reasoning capabilities.
Input
$0.04/M
Output
$0.04/M
Context
128K
OpenAI
OpenAI's efficient reasoning model, optimized for speed while maintaining strong analytical capabilities.
Input
$1.10/M
Output
$4.40/M
Context
200K
DeepSeek
DeepSeek's reasoning model with transparent chain-of-thought. Open-source and highly competitive.
Input
$0.55/M
Output
$2.19/M
Context
128K
Anthropic
Anthropic's best balance of intelligence and speed. Excellent for production workloads.
Input
$3.00/M
Output
$15.00/M
Context
200K