Phi-3 Medium 128K Instruct Check detailed information and pricing for AI models

Context Length 128,000 tokens, microsoft from provided

128,000
Context Tokens
$1.00
Prompt Price
$1.00
Output Price
1/16
Feature Support

Model Overview

Phi-3 128K Medium is a powerful 14-billion parameter model designed for advanced language understanding, reasoning, and instruction following. Optimized through supervised fine-tuning and preference adjustments, it excels in tasks involving common sense, mathematics, logical reasoning, and code processing. At time of release, Phi-3 Medium demonstrated state-of-the-art performance among lightweight models. In the MMLU-Pro eval, the model even comes close to a Llama3 70B level of performance. For 4k context length, try [Phi-3 Medium 4K](/models/microsoft/phi-3-medium-4k-instruct).

Basic Information

Developer
microsoft
Model Series
Other
Release Date
2024-05-24
Context Length
128,000 tokens
Variant
standard

Pricing Information

Prompt Tokens
$1.00 / 1M tokens
Completion Tokens
$1.00 / 1M tokens

Supported Features

Supported (1)

Tool Usage

Unsupported (15)

Image Input
Top K
Seed
Frequency Penalty
Presence Penalty
Repetition Penalty
Response Format
Min P
Logit Bias
Logprobs
Top Logprobs
Structured Outputs
Reasoning
Web Search Options
Top A

Actual Usage Statistics

#301
Out of 353 total models
38.28M
Total Tokens Last 30 Days
1.28M
Daily Average Usage
92%
Weekly Usage Change

Usage Trend for the Last 30 Days

Models by Same Author (microsoft)

Phi 4 Reasoning Plus (free)
32,768 tokens
Free
Phi 4 Reasoning Plus
32,768 tokens
$0.07 / $0.35
Phi 4 Reasoning (free)
32,768 tokens
Free
Phi 4 Reasoning
32,768 tokens
$0.00 / $0.00
MAI DS R1 (free)
163,840 tokens
Free

Similar Price Range Models

Sonar
perplexity
127,072 tokens
$1.00 / $1.00
Dolphin 2.9.2 Mixtral 8x22B 🐬
cognitivecomputations
16,000 tokens
$0.90 / $0.90
Mixtral 8x22B Instruct
mistralai
65,536 tokens
$0.90 / $0.90
Weaver (alpha)
mancer
8,000 tokens
$1.13 / $1.13
Llama 3.1 405B Instruct
meta-llama
32,768 tokens
$0.80 / $0.80