Command A Translate vs Ministral 14B vs GPT-5-Codex
Ministral 14B comes out ahead, 64 to 42 and 17 on our weighted score, and it is the cheaper option too.
CohereCommand A Translate
17/100- ECI—
- Price$2.50 / $10.00
- Context8K
- Our pick
Mistral AIMinistral 14B
64/100- ECI—
- Price$0.20 / $0.20
- Context262K
OpenAIGPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
Ministral 14B is our pick
Ministral 14B is the better all-round choice, scoring 64/100 against GPT-5-Codex (42) and Command A Translate (17). It leads on price. GPT-5-Codex wins on inputs & features and context window. 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 priceMinistral 14BMinistral 14B $0.20 · GPT-5-Codex $3.44 · Command A Translate $4.38 per 1M tokens (3:1 blend)
- Longest contextGPT-5-CodexGPT-5-Codex 400,000 · Ministral 14B 262,144 · Command A Translate 8,000 tokens
- Widest inputsMinistral 14B and GPT-5-CodexCommand A Translate: Text · Ministral 14B: Text, Images · GPT-5-Codex: Text, Images
- Self-hostingCommand A Translate and Ministral 14BPublishes downloadable weights (Apache-2.0)
| Measure | Weight | Command A Translate | Ministral 14B | GPT-5-Codex |
|---|---|---|---|---|
| Price | 50% | 19 | 83 | 24 |
| Inputs & features | 30% | 25 | 50 | 70 |
| Context window | 20% | 0 | 37 | 44 |
| Overall | 100% | 17/100 | 64/100 | 42/100 |
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 A TranslateCohere | Ministral 14BMistral AI | GPT-5-CodexOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.50 | $0.20 (best) | $1.25 |
| Output | $10.00 | $0.20 (best) | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | $4.38 | $0.20 (best) | $3.44 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Cohere API | Median of 1 providers | Median of 3 providers |
| Limits | |||
| Context window | 8,000 tokens | 262,144 tokens | 400,000 tokens (best) |
| Max output | 8,000 tokens | 262,144 tokens (best) | 128,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | No | Yes | Yes |
| PDFs | No | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | No | No | Yes |
| Tool calling | Yes | Yes | Yes |
| Structured output | No | No | Yes |
| Availability | |||
| Weights | Open | OpenApache-2.0 | Proprietary |
| API model ID | command-a-translate-08-2025 | — | — |
| API providers | 1 | 1 | 3 (best) |
| Released | Aug 28, 2025 | Dec 2, 2025 | Sep 15, 2025 |
| Knowledge cutoff | Jun 1, 2024 | — | Sep 30, 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 A Translate$45.00
- Ministral 14B$2.40
- GPT-5-Codex$32.50
Which should you choose?
Which is better: Command A Translate, Ministral 14B or GPT-5-Codex?
Ministral 14B is the better all-round choice, scoring 64/100 against GPT-5-Codex (42) and Command A Translate (17). It leads on price. GPT-5-Codex wins on inputs & features and context window. 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 A Translate, Ministral 14B or GPT-5-Codex?
Ministral 14B is cheaper at $0.20 input / $0.20 output per million tokens (median across 1 API provider). GPT-5-Codex costs $1.25 input / $10.00 output per million tokens (median across 3 API providers); Command A Translate 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 $0.20 per million tokens for Ministral 14B versus $3.44 for GPT-5-Codex (17× as much) and $4.38 for Command A Translate (22× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Command A Translate has not been scored yet, Ministral 14B has not been scored yet and GPT-5-Codex has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Command A Translate, Ministral 14B and GPT-5-Codex 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?
GPT-5-Codex has the largest context window at 400,000 tokens, against 262,144 for Ministral 14B and 8,000 for Command A Translate. Maximum output per response: Command A Translate up to 8,000, Ministral 14B up to 262,144, GPT-5-Codex up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Command A Translate accepts text; Ministral 14B accepts text and images; GPT-5-Codex accepts text and images. Ministral 14B handles the widest range of inputs.
Are any of these open source?
Command A Translate and Ministral 14B publishes its weights (Apache-2.0) and can be self-hosted; GPT-5-Codex is proprietary.
Which is newer?
Ministral 14B is the newest, released Dec 2, 2025. GPT-5-Codex came out Sep 15, 2025; Command A Translate came out Aug 28, 2025. Knowledge cutoff: Command A Translate Jun 1, 2024, GPT-5-Codex Sep 30, 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.
