Side by side
See the difference.
Scores, capabilities and costs for the models you’re considering.
Scroll to compare models →
| 2 models | cohereCohere: Command A+Remove × | liquidLiquidAI: LFM2.5-24B-A2BRemove × |
|---|---|---|
| What’s different | Command A+ is Cohere's flagship model for enterprise agentic workflows. It accepts text and image inputs with a 192K context window, supports native tool calling with strict tool schemas, structured... | 24B total, 2.45B active parameters; always reasons before answering, with GGUF and MLX releases for local deployment. |
| Date | Sep 22, 2026Listed | Oct 13, 2026Listed |
API prices USD · provider configuration shown below | ||
| Listed rate | $0.30 in / $1.50 out/ 1M tokensCohere · via OpenRouter · all routes ↗cohere | $0.05 in / $0.70 out/ 1M tokensLiquid · via OpenRouter · all routes ↗liquid/fp8 · quantization=fp8 |
| Provider endpoints | 2 endpoints → | 2 endpoints → |
Specifications | ||
| Context window | 192K | 128K |
| Max output | 64K | 8.2K |
| Parameters | — | 24B |
| Tool calling | Supported | Supported |
| Structured output | Supported | Supported |
| Image input | Supported | Not reported |
| Reasoning | Supported | Supported |
| Prompt caching | Supported | Supported |
| Open weights | Not reported | Supported |