Cohere's RAG workhorse for long-context enterprise search and tool use
Specification
cohere listing
Context
128K
Max output
4K
Released
2024-08-30
Knowledge cutoff
2024-06-01
Retires
—
Open weights
yes
Input
text
Output
text
Price
US dollars per million tokens · cohere list price
Input
$2.50
Output
$10.00
Cache read
$1.428
Available from 9 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| coherevendor | $2.50 | $10.00 | — | — | 128K | 4K | — |
| oci · oci | $1.56 | $1.56 | — | — | 128K | 4K | — |
| cohere_chat | $2.50 | $10.00 | — | — | 128K | 4K | — |
| edenai | $2.50 | $10.00 | — | — | 128K | 4K | — |
| kilo | $2.50 | $10.00 | — | — | 128K | 4K | — |
| merge-gateway | $2.50 | $10.00 | — | — | 128K | 4K | — |
| openrouter | $2.50 | $10.00 | — | — | 128K | 4K | — |
| nano-gpt | $2.856 | $14.246 | $1.428 | — | 128K | 4K | — |
| anyapi | — | — | — | — | 128K | 4K | — |
More from Cohere
most-hosted first