command-r-plus-08-2024 is an update of the [Command R+](/models/cohere/command-r-plus) with roughly 50% higher throughput and 25% lower latencies as compared to the previous Command R+ version, while keeping the hardware footprint the same.…
Model details →Cohere: Command R+ (08-2024) vs Mistral: Mixtral 8x22B Instruct
Mistral: Mixtral 8x22B Instruct wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
Mistral's official instruct fine-tuned version of [Mixtral 8x22B](/models/mistralai/mixtral-8x22b). It uses 39B active parameters out of 141B, offering unparalleled cost efficiency for its size. Its strengths include: - strong math, coding,…
Model details →Side-by-side comparison
| Capability | Cohere: Command R+ (08-2024) | Mistral: Mixtral 8x22B Instruct | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 128K | 66K | 🏆 Cohere: Command R+ (08-2024) |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $2.50 | $2.00 | 🏆 Mistral: Mixtral 8x22B Instruct |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $10.00 | $6.00 | 🏆 Mistral: Mixtral 8x22B Instruct |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | 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 R+ (08-2024) better than Mistral: Mixtral 8x22B Instruct?
Mistral: Mixtral 8x22B Instruct wins on 2 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 Mistral: Mixtral 8x22B Instruct?
Input: $2.50 vs $2.00 per 1M tokens. Output: $10.00 vs $6.00 per 1M tokens.
What context windows do Cohere: Command R+ (08-2024) and Mistral: Mixtral 8x22B Instruct support?
Cohere: Command R+ (08-2024) supports up to 128K tokens. Mistral: Mixtral 8x22B Instruct supports up to 66K tokens.
Do both Cohere: Command R+ (08-2024) and Mistral: Mixtral 8x22B Instruct support tool calling?
Cohere: Command R+ (08-2024): yes. Mistral: Mixtral 8x22B Instruct: yes.