command-r-08-2024 is an update of the [Command R](/models/cohere/command-r) with improved performance for multilingual retrieval-augmented generation (RAG) and tool use. More broadly, it is better at math, code and reasoning and...
Model details →Cohere: Command R (08-2024) vs meta-llama/Llama-3.2-3B-Instruct
meta-llama/Llama-3.2-3B-Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
Llama 3.2 3B is a 3-billion-parameter multilingual large language model, optimized for advanced natural language processing tasks like dialogue generation, reasoning, and summarization. Designed with the latest transformer architecture, it.…
Model details →Side-by-side comparison
| Capability | Cohere: Command R (08-2024) | meta-llama/Llama-3.2-3B-Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 128K | 131K | 🏆 meta-llama/Llama-3.2-3B-Instruct |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.15 | $0.05 | 🏆 meta-llama/Llama-3.2-3B-Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $0.60 | $0.33 | 🏆 meta-llama/Llama-3.2-3B-Instruct |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | — | 🏆 Cohere: Command R (08-2024) |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Cohere: Command R (08-2024) better than meta-llama/Llama-3.2-3B-Instruct?
meta-llama/Llama-3.2-3B-Instruct wins on 3 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Cohere: Command R (08-2024) and meta-llama/Llama-3.2-3B-Instruct?
Input: $0.15 vs $0.05 per 1M tokens. Output: $0.60 vs $0.33 per 1M tokens.
What context windows do Cohere: Command R (08-2024) and meta-llama/Llama-3.2-3B-Instruct support?
Cohere: Command R (08-2024) supports up to 128K tokens. meta-llama/Llama-3.2-3B-Instruct supports up to 131K tokens.
Do both Cohere: Command R (08-2024) and meta-llama/Llama-3.2-3B-Instruct support tool calling?
Cohere: Command R (08-2024): yes. meta-llama/Llama-3.2-3B-Instruct: not advertised.