Command A is an open-weights 111B parameter model with a 256k context window focused on delivering great performance across agentic, multilingual, and coding use cases. Compared to other leading proprietary and open-weights models Command A…
Model details →Cohere: Command A vs Relace: Relace Apply 3
Relace: Relace Apply 3 wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Relace Apply 3 is a specialized code-patching LLM that merges AI-suggested edits straight into your source files. It can apply updates from GPT-4o, Claude, and others into your files at 10,000 tokens/sec on average. The model requires the …
Model details →Side-by-side comparison
| Capability | Cohere: Command A | Relace: Relace Apply 3 | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 256K | 256K | Tie |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $2.50 | $0.85 | 🏆 Relace: Relace Apply 3 |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $10.00 | $1.25 | 🏆 Relace: Relace Apply 3 |
| Tool / function calling First-class support for emitting structured tool calls. | — | — | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | — | — | Tie |
Frequently asked questions
Is Cohere: Command A better than Relace: Relace Apply 3?
Relace: Relace Apply 3 wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between Cohere: Command A and Relace: Relace Apply 3?
Input: $2.50 vs $0.85 per 1M tokens. Output: $10.00 vs $1.25 per 1M tokens.
What context windows do Cohere: Command A and Relace: Relace Apply 3 support?
Cohere: Command A supports up to 256K tokens. Relace: Relace Apply 3 supports up to 256K tokens.
Do both Cohere: Command A and Relace: Relace Apply 3 support tool calling?
Cohere: Command A: not advertised. Relace: Relace Apply 3: not advertised.