Command R7B vs Ministral 8B Instruct vs Nova Micro
Too close to call on our weighted score (Command R7B 62, Nova Micro 62, Ministral 8B Instruct 57). The right pick depends on what you value most.
CohereCommand R7B
62/100- ECI—
- Price$0.037 / $0.15
- Context128K
Mistral AIMinistral 8B Instruct
57/100- ECI—
- Price$0.15 / $0.15
- Context131K
AmazonNova Micro
62/100- ECI—
- Price$0.035 / $0.14
- Context128K
Too close to call
It is close. Our weighted score puts them within a point (Command R7B 62/100, Nova Micro 62/100, Ministral 8B Instruct 57/100), so choose by what matters most for your work: Nova Micro on price and Ministral 8B Instruct for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
- CapabilityNot enough dataNo independent benchmark covers every model here yet
- Lowest priceNova MicroNova Micro $0.061 · Command R7B $0.066 · Ministral 8B Instruct $0.15 per 1M tokens (3:1 blend)
- Longest contextMinistral 8B InstructMinistral 8B Instruct 131,072 · Command R7B 128,000 · Nova Micro 128,000 tokens
- Widest inputsSame inputsCommand R7B: Text · Ministral 8B Instruct: Text · Nova Micro: Text
- Self-hostingCommand R7B and Ministral 8B InstructPublishes downloadable weights (Mistral Research License)
| Measure | Weight | Command R7B | Ministral 8B Instruct | Nova Micro |
|---|---|---|---|---|
| Price | 50% | 100 | 89 | 100 |
| Inputs & features | 30% | 25 | 25 | 25 |
| Context window | 20% | 24 | 24 | 24 |
| Overall | 100% | 62/100 | 57/100 | 62/100 |
Left out because at least one model lacks the data: capability. The remaining weights were rescaled.
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Command R7BCohere | Ministral 8B InstructMistral AI | Nova MicroAmazon |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| GPQA DiamondGraduate-level science questions | — | 27.2% | — |
| Price per million tokens | |||
| Input | $0.037 | $0.15 | $0.035 (best) |
| Output | $0.15 | $0.15 | $0.14 (best) |
| Cached input | — | — | $0.0088 |
| Blended (3:1) | $0.066 | $0.15 | $0.061 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Median of 1 providers | Official Amazon Bedrock API |
| Limits | |||
| Context window | 128,000 tokens | 131,072 tokens (best) | 128,000 tokens |
| Max output | 4,000 tokens | 8,192 tokens | 10,000 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | No |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | No |
| Availability | |||
| Weights | Open | OpenMistral Research License | Proprietary |
| API model ID | command-r7b-12-2024 | — | amazon.nova-micro-v1:0 |
| API providers | 5 (best) | 1 | 3 |
| Released | Dec 2, 2024 | Oct 16, 2024 | Dec 3, 2024 |
| Knowledge cutoff | Jun 1, 2024 | — | Oct 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Command R7B$0.675
- Ministral 8B Instruct$1.80
- Nova Micro$0.63
Which should you choose?
Which is better: Command R7B, Ministral 8B Instruct or Nova Micro?
It is close. Our weighted score puts them within a point (Command R7B 62/100, Nova Micro 62/100, Ministral 8B Instruct 57/100), so choose by what matters most for your work: Nova Micro on price and Ministral 8B Instruct for long inputs. The score weighs price 50%, inputs & features 30%, context window 20%. None of the shared benchmarks cover every model here yet, so capability is left out of this verdict.
Which is cheaper, Command R7B, Ministral 8B Instruct or Nova Micro?
Nova Micro is cheaper at $0.035 input / $0.14 output per million tokens (official Amazon Bedrock API price). Command R7B costs $0.037 input / $0.15 output per million tokens (official Cohere API price); Ministral 8B Instruct costs $0.15 input / $0.15 output per million tokens (median across 1 API provider). At a typical mix of three input tokens to one output token, that is $0.061 per million tokens for Nova Micro versus $0.066 for Command R7B (1.1× as much) and $0.15 for Ministral 8B Instruct (2.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Command R7B has not been scored yet, Ministral 8B Instruct has not been scored yet and Nova Micro has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Command R7B, Ministral 8B Instruct and Nova Micro yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. All three support tool calling for agent workflows.
Which has the bigger context window?
Ministral 8B Instruct has the largest context window at 131,072 tokens, against 128,000 for Command R7B and 128,000 for Nova Micro. Maximum output per response: Command R7B up to 4,000, Ministral 8B Instruct up to 8,192, Nova Micro up to 10,000 tokens.
Which can read images, PDFs, audio or video?
Command R7B accepts text; Ministral 8B Instruct accepts text; Nova Micro accepts text. They handle the same number of input types.
Are any of these open source?
Command R7B and Ministral 8B Instruct publishes its weights (Mistral Research License) and can be self-hosted; Nova Micro is proprietary.
Which is newer?
Nova Micro is the newest, released Dec 3, 2024. Command R7B came out Dec 2, 2024; Ministral 8B Instruct came out Oct 16, 2024. Knowledge cutoff: Command R7B Jun 1, 2024, Nova Micro Oct 2024.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Oct 4, 2026.
