Command R+ vs Codestral vs Qwen2.5-VL 72B Instruct
Codestral comes out ahead, 48 to 30 and 22 on our weighted score, and it is the cheaper option too.
CohereCommand R+
22/100- ECI—
- Price$2.50 / $10.00
- Context128K
- Our pick
Mistral AICodestral
48/100- ECI—
- Price$0.30 / $0.90
- Context256K
Alibaba (Qwen)Qwen2.5-VL 72B Instruct
30/100- ECI—
- Price$2.80 / $8.40
- Context131K
Codestral is our pick
Codestral is the better all-round choice, scoring 48/100 against Qwen2.5-VL 72B Instruct (30) and Command R+ (22). It leads on price and context window. Qwen2.5-VL 72B Instruct wins on inputs & features. 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 priceCodestralCodestral $0.45 · Qwen2.5-VL 72B Instruct $4.20 · Command R+ $4.38 per 1M tokens (3:1 blend)
- Longest contextCodestralCodestral 256,000 · Qwen2.5-VL 72B Instruct 131,072 · Command R+ 128,000 tokens
- Widest inputsQwen2.5-VL 72B InstructCommand R+: Text · Codestral: Text · Qwen2.5-VL 72B Instruct: Text, Images
- Self-hostingAll open weightsEvery model here can be downloaded and run on your own hardware
| Measure | Weight | Command R+ | Codestral | Qwen2.5-VL 72B Instruct |
|---|---|---|---|---|
| Price | 50% | 19 | 66 | 20 |
| Inputs & features | 30% | 25 | 25 | 50 |
| Context window | 20% | 24 | 36 | 24 |
| Overall | 100% | 22/100 | 48/100 | 30/100 |
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 R+Cohere | CodestralMistral AI | Qwen2.5-VL 72B InstructAlibaba (Qwen) |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.50 | $0.30 (best) | $2.80 |
| Output | $10.00 | $0.90 (best) | $8.40 |
| Cached input | — | $0.03 | — |
| Blended (3:1) | $4.38 | $0.45 (best) | $4.20 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Official Mistral API | Official Alibaba API |
| Limits | |||
| Context window | 128,000 tokens | 256,000 tokens (best) | 131,072 tokens |
| Max output | 4,000 tokens | 4,096 tokens | 8,192 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | No | Yes |
| 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 | Open | Open |
| API model ID | command-r-plus-08-2024 | codestral-latest | qwen2-5-vl-72b-instruct |
| API providers | 7 (best) | 3 | 1 |
| Released | Aug 30, 2024 | May 29, 2024 | Sep 2024 |
| Knowledge cutoff | Jun 1, 2024 | Oct 2024 | Apr 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 R+$45.00
- Codestral$4.80
- Qwen2.5-VL 72B Instruct$44.80
Which should you choose?
Which is better: Command R+, Codestral or Qwen2.5-VL 72B Instruct?
Codestral is the better all-round choice, scoring 48/100 against Qwen2.5-VL 72B Instruct (30) and Command R+ (22). It leads on price and context window. Qwen2.5-VL 72B Instruct wins on inputs & features. 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 R+, Codestral or Qwen2.5-VL 72B Instruct?
Codestral is cheaper at $0.30 input / $0.90 output per million tokens (official Mistral API price). Qwen2.5-VL 72B Instruct costs $2.80 input / $8.40 output per million tokens (official Alibaba API price); Command R+ costs $2.50 input / $10.00 output per million tokens (official Cohere API price). At a typical mix of three input tokens to one output token, that is $0.45 per million tokens for Codestral versus $4.20 for Qwen2.5-VL 72B Instruct (9.3× as much) and $4.38 for Command R+ (9.7× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Command R+ has not been scored yet, Codestral has not been scored yet and Qwen2.5-VL 72B Instruct has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Command R+, Codestral and Qwen2.5-VL 72B Instruct 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?
Codestral has the largest context window at 256,000 tokens, against 131,072 for Qwen2.5-VL 72B Instruct and 128,000 for Command R+. Maximum output per response: Command R+ up to 4,000, Codestral up to 4,096, Qwen2.5-VL 72B Instruct up to 8,192 tokens.
Which can read images, PDFs, audio or video?
Command R+ accepts text; Codestral accepts text; Qwen2.5-VL 72B Instruct accepts text and images. Qwen2.5-VL 72B Instruct handles the widest range of inputs.
Are any of these open source?
Yes, all three publish their weights, so you can self-host them.
Which is newer?
Qwen2.5-VL 72B Instruct is the newest, released Sep 2024. Command R+ came out Aug 30, 2024; Codestral came out May 29, 2024. Knowledge cutoff: Command R+ Jun 1, 2024, Codestral Oct 2024, Qwen2.5-VL 72B Instruct Apr 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.
