GPT-5.2 Codex vs Jamba Large vs Command A Translate
GPT-5.2 Codex comes out ahead, 42 to 30 and 17 on our weighted score, though Jamba Large is 27% cheaper per token.
- Our pick
OpenAIGPT-5.2 Codex
42/100- ECI—
- Price$1.75 / $14.00
- Context400K
AI21 LabsJamba Large
30/100- ECI—
- Price$2.00 / $8.00
- Context256K
CohereCommand A Translate
17/100- ECI—
- Price$2.50 / $10.00
- Context8K
GPT-5.2 Codex is our pick
GPT-5.2 Codex is the better all-round choice, scoring 42/100 against Jamba Large (30) and Command A Translate (17). It leads on inputs & features and context window. Jamba Large wins on price. 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 priceJamba LargeJamba Large $3.50 · Command A Translate $4.38 · GPT-5.2 Codex $4.81 per 1M tokens (3:1 blend)
- Longest contextGPT-5.2 CodexGPT-5.2 Codex 400,000 · Jamba Large 256,000 · Command A Translate 8,000 tokens
- Widest inputsGPT-5.2 CodexGPT-5.2 Codex: Text, Images, PDFs · Jamba Large: Text · Command A Translate: Text
- Self-hostingJamba Large and Command A TranslatePublishes downloadable weights
| Measure | Weight | GPT-5.2 Codex | Jamba Large | Command A Translate |
|---|---|---|---|---|
| Price | 50% | 18 | 24 | 19 |
| Inputs & features | 30% | 80 | 35 | 25 |
| Context window | 20% | 44 | 36 | 0 |
| Overall | 100% | 42/100 | 30/100 | 17/100 |
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 | GPT-5.2 CodexOpenAI | Jamba LargeAI21 Labs | Command A TranslateCohere |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $1.75 (best) | $2.00 | $2.50 |
| Output | $14.00 | $8.00 (best) | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | $4.81 | $3.50 (best) | $4.38 |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Median of 11 providers | Official AI21 Labs API | Official Cohere API |
| Limits | |||
| Context window | 400,000 tokens (best) | 256,000 tokens | 8,000 tokens |
| Max output | 128,000 tokens (best) | 4,096 tokens | 8,000 tokens |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | No |
| PDFs | Yes | No | No |
| Audio | No | No | No |
| Video | No | No | No |
| Reasoning | Yes | No | No |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | Open | Open |
| API model ID | — | jamba-large | command-a-translate-08-2025 |
| API providers | 11 (best) | 1 | 1 |
| Released | Dec 11, 2025 | Jul 1, 2025 | Aug 28, 2025 |
| Knowledge cutoff | Aug 31, 2025 | Aug 22, 2024 | Jun 1, 2024 |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- GPT-5.2 Codex$45.50
- Jamba Large$36.00
- Command A Translate$45.00
Which should you choose?
Which is better: GPT-5.2 Codex, Jamba Large or Command A Translate?
GPT-5.2 Codex is the better all-round choice, scoring 42/100 against Jamba Large (30) and Command A Translate (17). It leads on inputs & features and context window. Jamba Large wins on price. 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, GPT-5.2 Codex, Jamba Large or Command A Translate?
Jamba Large is cheaper at $2.00 input / $8.00 output per million tokens (official AI21 Labs API price). Command A Translate costs $2.50 input / $10.00 output per million tokens (official Cohere API price); GPT-5.2 Codex costs $1.75 input / $14.00 output per million tokens (median across 11 API providers). At a typical mix of three input tokens to one output token, that is $3.50 per million tokens for Jamba Large versus $4.38 for Command A Translate (1.3× as much) and $4.81 for GPT-5.2 Codex (1.4× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. GPT-5.2 Codex has not been scored yet, Jamba Large has not been scored yet and Command A Translate has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for GPT-5.2 Codex, Jamba Large and Command A Translate 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-5.2 Codex has the largest context window at 400,000 tokens, against 256,000 for Jamba Large and 8,000 for Command A Translate. Maximum output per response: GPT-5.2 Codex up to 128,000, Jamba Large up to 4,096, Command A Translate up to 8,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5.2 Codex accepts text, images and PDFs; Jamba Large accepts text; Command A Translate accepts text. GPT-5.2 Codex handles the widest range of inputs.
Are any of these open source?
Jamba Large and Command A Translate publishes its weights and can be self-hosted; GPT-5.2 Codex is proprietary.
Which is newer?
GPT-5.2 Codex is the newest, released Dec 11, 2025. Command A Translate came out Aug 28, 2025; Jamba Large came out Jul 1, 2025. Knowledge cutoff: GPT-5.2 Codex Aug 31, 2025, Jamba Large Aug 22, 2024, Command A Translate Jun 1, 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.
