Claude 3.5 Sonnet vs Command R+: Detailed Comparison
Choosing between Claude 3.5 Sonnet (Anthropic) and
Command R+ (Cohere) comes down to three things:
per-token pricing, context window, and which capability matters most for your workload.
Claude 3.5 Sonnet costs $3.00/M input vs
$2.50/M for Command R+;
context windows are 200K vs
128K tokens. Detailed breakdown below.
Side-by-side specs
| Spec | Claude 3.5 Sonnet | Command R+ |
|---|
| Provider | Anthropic | Cohere |
|---|
| Released | 2024-10-22 | 2024-04-04 |
|---|
| Input price |
$3.00/M |
$2.50/M |
| Output price |
$15.00/M |
$10.00/M |
| Cached input |
$0.3000/M |
— |
| Context window |
200K |
128K |
| Max output |
8K |
4K |
| Modalities |
text image |
text |
| Tokenizer |
claude-3 |
cohere |
Capability matrix
| Capability | Claude 3.5 Sonnet | Command R+ |
|---|
| function calling |
Yes |
Yes |
| json mode |
Yes |
Yes |
| vision |
Yes |
No |
| streaming |
Yes |
Yes |
| tool use |
Yes |
No |
| rag |
No |
Yes |
| citations |
No |
Yes |
Per-call cost on typical workloads
| Workload (in/out tokens) | Claude 3.5 Sonnet | Command R+ | Cheaper by |
|---|
| Standard chat (1K / 500) |
$0.010500 |
$0.007500 |
Command R+ by $0.003000 |
| RAG (4K / 500) |
$0.019500 |
$0.015000 |
Command R+ by $0.004500 |
| Long doc (20K / 1K) |
$0.075000 |
$0.060000 |
Command R+ by $0.015000 |
| Very long context (100K / 2K) |
$0.322500 |
$0.265000 |
Command R+ by $0.057500 |
When to choose Claude 3.5 Sonnet over Command R+
- Larger context window (200K vs 128K) — relevant when whole documents or long histories must fit in a single call.
- Supports vision — Command R+ does not.
- Supports tool use — Command R+ does not.
When to choose Command R+ over Claude 3.5 Sonnet
- Per-token input cost is 17% lower than Claude 3.5 Sonnet.
- Supports rag — Claude 3.5 Sonnet does not.
- Supports citations — Claude 3.5 Sonnet does not.
Related comparisons