Phi-3.5-mini-instruct

by Microsoft

Phi-3.5-mini-instruct is a model from Microsoft, released on August 23, 2024. It has a 128K-token context window and can generate up to 128K output tokens. API pricing is $0.1 per 1M input tokens and $0.1 per 1M output tokens. It ranks #204 of 220 models by Intelligence Score with a score of -3.8.

Phi-3.5-mini-instruct is a 3.8B-parameter model that supports up to 128K context tokens, with improved multilingual capabilities across over 20 languages. It underwent additional training and safety post-training to enhance instruction-following, reasoning, math, and code generation. Ideal for environments with memory or latency constraints, it uses an MIT license.

Key specs

ProviderMicrosoft
Release date2024-08-23
Licenseopen source
Context window128K tokens
Max output128K tokens
Input price$0.1 / 1M tokens
Output price$0.1 / 1M tokens
Intelligence Score-3.8
Coding index-6.9

Quick answers

What is the context window of Phi-3.5-mini-instruct?

Phi-3.5-mini-instruct has a context window of 128K tokens, with a maximum output of 128K tokens per response.

How much does Phi-3.5-mini-instruct cost?

Phi-3.5-mini-instruct costs $0.1 per 1M input tokens and $0.1 per 1M output tokens through the API.

Is Phi-3.5-mini-instruct open source?

Yes. Phi-3.5-mini-instruct is an open model released under the open source license.

When was Phi-3.5-mini-instruct released?

Microsoft released Phi-3.5-mini-instruct on August 23, 2024.

How does Phi-3.5-mini-instruct compare to Claude Opus 5.5 (Reasoning)?

Phi-3.5-mini-instruct scores -3.8 on the Intelligence Score versus 60.5 for Claude Opus 5.5 (Reasoning), the current #1. Input pricing is $0.1 vs $4 per 1M tokens.

Compare on the AI leaderboard · All AI models

More models from Microsoft