Skip to main content
Glama

phi-3.5-mini-128k-instruct vs command-r-plus-08-2024

Pricing, Performance & Features Comparison

Price unit:
Authormicrosoft
Context Length128K
Reasoning
-
Providers1
ReleasedAug 2024
Knowledge CutoffOct 2023
LicenseMIT License

Phi-3.5-mini-128k-instruct is a compact, advanced language model that can handle up to 128K tokens in context, enabling tasks such as lengthy document summarization, multi-turn conversation, and complex reasoning. It is optimized for logic, code, and math, and provides robust multi-lingual capabilities. With 3.8 billion parameters, it uses a dense decoder-only transformer architecture that balances performance and efficiency.

Input$0.1
Output$0.1
Latency (p50)-
Output Limit128K
Function Calling
-
JSON Mode
-
InputText
OutputText
in$0.1out$0.1--
Flag of Canada (Pantone colours)
command-r-plus-08-2024
Authorcohere
Context Length128K
Reasoning
-
Providers1
ReleasedAug 2024
Knowledge CutoffFeb 2023
License-

cohere/command-r-plus-08-2024 is a powerful large language model optimized for conversational interactions, multi-step tool usage, and retrieval-augmented generation workflows. It supports a 128K token context window and demonstrates notable improvements in throughput while maintaining low latency. This multilingual model excels in complex reasoning, instruction-following, and grounded text generation across various languages.

Input$2.4
Output$9.5
Latency (p50)1.4s
Output Limit4K
Function Calling
JSON Mode
InputText
OutputText
Flag of Canada (Pantone colours)
cohere
in$2.4out$9.5--
Latency (24h)
Success Rate (24h)