Command R7B (12-2024)
Cohere · released Dec 14, 2024
- Type
- Proprietary
- Input
- $0.037
- Output
- $0.15
- Cached
- Not published
List price · per 1M tokens · Cohere at 128K context · source ↗
Our take
Written Aug 3, 2026Command R7B is a hosted-only text model from Cohere, released in late 2024 with a 128,000-token request limit. It follows instructions well but scores poorly on knowledge and reasoning tests, making it a narrow-use choice for formatting-heavy document work rather than general intelligence tasks.
Pick this for long-document processing where instruction formatting matters more than raw knowledge, or where you need predictable pricing across both tracked providers. Use it if 64 tokens per second meets your latency needs. Skip it if you need image or audio input, strong reasoning or broad factual knowledge, or if you want to download and self-host the weights.
The case for it
- Strong instruction-following compliance relative to its knowledge scores: a 48.5-point gap between IFEval and MMLU-Pro.
- Identical pricing across both tracked providers, so provider choice does not affect cost.
The case against it
- Very weak knowledge and reasoning scores, at 28.6% on MMLU-Pro and 7.8% on GPQA Diamond.
- Throughput on the secondary provider is unverified in our data.
- Parameter count is undisclosed, which limits hardware planning for anyone considering local deployment.
How good is it?
IntelligencePuzzles, maths, exam questions
Command R7B (12-2024) is not on Arena Text (overall), which is where the rating would come from, so there is no rating here. It is on GPQA Diamond, in 10th of 16 with 7.8.
CodingWriting and fixing code on its own
Nobody we watch has scored Command R7B (12-2024) for this. We would take the rating from Arena Coding.
AgenticPlanning, calling tools, staying on task
Nobody we watch has scored Command R7B (12-2024) for this. We would take the rating from Arena Agent (IPS).
WritingWe do not rate this
Nobody we watch has scored this model for writing. Two boards come close and neither tests writing: Arena Creative Writing asks people which of two replies they prefer, and LiveBench Language tests whether a model understood a passage.
These tests check whether a model follows instructions — a precondition for all the work above, but not a measure of how well that work is done, which is why they get no rating.
Or rent it from someone else
Why this differs from the header. The strip above quotes Cohere's own list price. This is the cheapest live offer at the widest standard context we hold, whoever is serving it — a reseller undercutting a lab is ordinary commerce, not an error.
- per 1M tokens
- $0.037 in / $0.15 out
- Context served
- 128K
- Throughput
- Not measured
| Provider | In / out per 1M tokens | Context | Throughput | Trains on prompts | Logs prompts | Zero retention |
|---|---|---|---|---|---|---|
| OpenRouter | $0.037 / $0.15 | 128K | not measured | Unknown | Unknown | Unknown |
| Cohere | $0.037 / $0.15 | 128K | 54 tok/s | No | Yes30 days | Unknown |
Across the 2 listings we hold: 1 say they do not train on prompts, 0 say they do and 1 do not say. 0 appear in the zero-retention registry we check; the rest are unknown to us rather than confirmed either way.
What each host's API supports
From the parameter list each endpoint publishes. Streaming is omitted: nothing we hold reports it, for any model.
- ✓
- Supported
- ✗
- Not supported
- Not published
- host gave no parameter list
| Provider | Tool calling | JSON output | Strict schema |
|---|---|---|---|
| OpenRouter | ✗ | ✓ | ✓ |
| Cohere | ✗ | ✓ | ✓ |
Tool calling: 0 of 2 listings say yes, 2 say no. JSON output: 2 of 2 listings say yes. Strict schema: 2 of 2 listings say yes.
When we formed this view
Dates behind this page
Prices last checked 9d ago
What we do not know about this model yet
- Nothing we hold says whether an endpoint streams, so we do not show it either way.
- 1 of 2 listings do not say whether they train on prompts.
- We hold no cached-input rate for any of its listings.
Licence and identifiers
What the licence allowsWe hold no licence record for this model. Inside are the identifiers you need to pull it — its Hugging Face repo where we have one, our slug and a machine-readable card.
Licence
Commercial API terms. We hold no licence record for this model, so there is nothing to summarise here.
Identifiers
- Modality record
- text->text
- Catalogue slug
- cohere-command-r7b-12-2024