Command R+.
Cohere's open-weight RAG-optimized LLM — multilingual + tool use.
1× Nvidia A100 · $0.48/hr.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
| Provider | Access | $/M in | $/M out | |
|---|---|---|---|---|
| Cohere API | api direct | $2.5 | $10.0 | Launch ↗ |
Speed across providers.
Tokens/sec and time-to-first-token measured against the same prompt template on each provider's API.
| Provider | Tokens/sec | TTFT | Total |
|---|---|---|---|
| OpenRouter | 31.9 | 855 ms | 3979 ms |
Frequently asked.
How do I run Command R+?
Where can I access Command R+?
How much does it cost to run Command R+?
Is Command R+ open-source or proprietary?
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
288 GB | — | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
141 GB | — | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
80 GB | $0.48/hr | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Command R+ across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
Rent the GPU instead of paying per token.
For an open-weights model like Command R+, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
What it's best at.
Scores normalised against benchmark ceilings (100 = perfect). Coloured by tier — coral 80+ frontier, lavender 65+ strong, sage 50+ solid, slate below.
About Command R+.
Command R+ is Cohere's open-weight model optimised for retrieval-augmented generation (RAG) and tool use — 104B parameters, dense, trained with a strong emphasis on grounded generation (citing source documents inline) and structured tool calling. Available on Hugging Face under CC-BY-NC-4.0 (non-commercial research only; commercial use requires Cohere's API or enterprise license). Strong multilingual coverage (10+ languages). Particularly popular in enterprise RAG deployments because of its explicit citation feature.