Cohere: Command R+ (08-2024) vs Mistral: Devstral Medium
Head-to-head API pricing and cost comparison between Cohere’s Cohere: Command R+ (08-2024) and Mistral’s Mistral: Devstral Medium. Prices auto-refresh daily from OpenRouter.
Mistral: Devstral Medium is 84% cheaper for input tokens; Mistral: Devstral Medium also wins on output tokens.
Side-by-side comparison
| Spec | Cohere: Command R+ (08-2024) | Mistral: Devstral Medium |
|---|---|---|
| Input price (per 1M) | $2.50 | $0.40 |
| Cached input (per 1M) | — | $0.04 |
| Output price (per 1M) | $10.00 | $2.00 |
| Batch input (per 1M) | — | — |
| Batch output (per 1M) | — | — |
| Reasoning price (per 1M) | — | — |
| Context window | 128K | 131K |
| Vision support | No | No |
| Caching support | No | Yes |
| Batch API | No | No |
| Reasoning capability | No | No |
Monthly cost at volume
Estimated monthly API spend at common production traffic levels (input/output tokens per request shown).
| Volume | Cohere: Command R+ (08-2024) | Mistral: Devstral Medium | Savings |
|---|---|---|---|
1K req/day 500in / 200out tokens | $97.50 | $18.00 | $79.50 Mistral: Devstral Medium wins |
10K req/day 1500in / 500out tokens | $2,625 | $480.00 | $2,145 Mistral: Devstral Medium wins |
100K req/day 3000in / 800out tokens | $46,500 | $8,400 | $38,100 Mistral: Devstral Medium wins |
1M req/day 8000in / 2000out tokens | $1,200,000 | $216,000 | $984,000 Mistral: Devstral Medium wins |
Adjust input/output token counts, request volume, batch & cached pricing.
Related comparisons
- Anthropic: Claude Haiku 4.5 vs Cohere: Command R+ (08-2024)Compare pricing →
- Anthropic: Claude Opus 4.7 vs Cohere: Command R+ (08-2024)Compare pricing →
- Anthropic: Claude Sonnet 4.6 vs Cohere: Command R+ (08-2024)Compare pricing →
- Cohere: Command R (08-2024) vs Mistral: Devstral MediumCompare pricing →
Frequently asked questions
Which is cheaper, Cohere: Command R+ (08-2024) or Mistral: Devstral Medium?
For input tokens, Mistral: Devstral Medium is roughly 84% cheaper at $0.40/1M vs $2.50/1M. For output tokens, Mistral: Devstral Medium wins at $2.00/1M. Real-world cost depends on your input/output ratio — use the calculator to model your actual workload.
What’s the context window difference?
Cohere: Command R+ (08-2024) has a context window of 128K tokens. Mistral: Devstral Medium offers 131K tokens. Larger context windows are valuable for long documents, RAG pipelines, and multi-turn conversations — but they come with higher input-token bills if you fill them every request.
Should I use Cohere: Command R+ (08-2024) or Mistral: Devstral Medium?
Choose Cohere: Command R+ (08-2024) if you’re already on the Cohere stack, want broad ecosystem support, or prefer its feature set. Choose Mistral: Devstral Medium for Mistral’s ecosystem, or its cheaper input tokens. Run a small benchmark on your own prompts before committing — price is only one axis.
How are these prices kept current?
Prices are pulled directly from OpenRouter’s public models API once every 24 hours via a Convex cron job, then normalized to per-1M-token figures. Last refresh: Apr 21, 2026.