Jamba Large vs GPT-5-Codex vs GPT-5 Chat
GPT-5-Codex comes out ahead, 42 to 34 and 30 on our weighted score.
AI21 LabsJamba Large
30/100- ECI—
- Price$2.00 / $8.00
- Context256K
- Our pick
OpenAIGPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
- OpenAI
GPT-5 Chat
34/100- ECI—
- Price$1.25 / $10.00
- Context400K
GPT-5-Codex is our pick
GPT-5-Codex is the better all-round choice, scoring 42/100 against GPT-5 Chat (34) and Jamba Large (30). It leads 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 priceGPT-5-Codex and GPT-5 ChatGPT-5-Codex $3.44 · GPT-5 Chat $3.44 · Jamba Large $3.50 per 1M tokens (3:1 blend)
- Longest contextGPT-5-Codex and GPT-5 ChatGPT-5-Codex 400,000 · GPT-5 Chat 400,000 · Jamba Large 256,000 tokens
- Widest inputsGPT-5-Codex and GPT-5 ChatJamba Large: Text · GPT-5-Codex: Text, Images · GPT-5 Chat: Text, Images
- Self-hostingJamba LargePublishes downloadable weights
| Measure | Weight | Jamba Large | GPT-5-Codex | GPT-5 Chat |
|---|---|---|---|---|
| Price | 50% | 24 | 24 | 24 |
| Inputs & features | 30% | 35 | 70 | 45 |
| Context window | 20% | 36 | 44 | 44 |
| Overall | 100% | 30/100 | 42/100 | 34/100 |
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 | Jamba LargeAI21 Labs | GPT-5-CodexOpenAI | GPT-5 ChatOpenAI |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | — | — | — |
| ECI rank | — | — | — |
| Price per million tokens | |||
| Input | $2.00 | $1.25 (best) | $1.25 (best) |
| Output | $8.00 (best) | $10.00 | $10.00 |
| Cached input | — | — | — |
| Blended (3:1) | $3.50 | $3.44 (best) | $3.44 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official AI21 Labs API | Median of 3 providers | Median of 2 providers |
| Limits | |||
| Context window | 256,000 tokens | 400,000 tokens (best) | 400,000 tokens (best) |
| Max output | 4,096 tokens | 128,000 tokens (best) | 128,000 tokens (best) |
| 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 | Yes | Yes |
| Tool calling | Yes | Yes | No |
| Structured output | Yes | Yes | Yes |
| Availability | |||
| Weights | Open | Proprietary | Proprietary |
| API model ID | jamba-large | — | — |
| API providers | 1 | 3 (best) | 2 |
| Released | Jul 1, 2025 | Sep 15, 2025 | Aug 7, 2025 |
| Knowledge cutoff | Aug 22, 2024 | Sep 30, 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.
- Jamba Large$36.00
- GPT-5-Codex$32.50
- GPT-5 Chat$32.50
Which should you choose?
Which is better: Jamba Large, GPT-5-Codex or GPT-5 Chat?
GPT-5-Codex is the better all-round choice, scoring 42/100 against GPT-5 Chat (34) and Jamba Large (30). It leads 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, Jamba Large, GPT-5-Codex or GPT-5 Chat?
GPT-5-Codex is cheaper at $1.25 input / $10.00 output per million tokens (median across 3 API providers). GPT-5 Chat costs $1.25 input / $10.00 output per million tokens (median across 2 API providers); Jamba Large costs $2.00 input / $8.00 output per million tokens (official AI21 Labs API price). At a typical mix of three input tokens to one output token, that is $3.44 per million tokens for GPT-5-Codex versus $3.44 for GPT-5 Chat (1× as much) and $3.50 for Jamba Large (1× as much).
Which scores higher on benchmarks?
There is no independent benchmark that covers all three models yet. Jamba Large has not been scored yet, GPT-5-Codex has not been scored yet and GPT-5 Chat has not been scored yet.
Which is better for coding?
There are no published SWE-bench Verified results for Jamba Large, GPT-5-Codex and GPT-5 Chat yet, so there is no like-for-like coding score. Test both on a sample of your own tasks. Note that GPT-5 Chat does not support tool calling, which most coding agents need.
Which has the bigger context window?
GPT-5-Codex and GPT-5 Chat have the largest context windows (400,000 and 400,000 tokens), against 256,000 for Jamba Large. Maximum output per response: Jamba Large up to 4,096, GPT-5-Codex up to 128,000, GPT-5 Chat up to 128,000 tokens.
Which can read images, PDFs, audio or video?
Jamba Large accepts text; GPT-5-Codex accepts text and images; GPT-5 Chat accepts text and images. GPT-5-Codex handles the widest range of inputs.
Are any of these open source?
Jamba Large publishes its weights and can be self-hosted; GPT-5-Codex and GPT-5 Chat is proprietary.
Which is newer?
GPT-5-Codex is the newest, released Sep 15, 2025. GPT-5 Chat came out Aug 7, 2025; Jamba Large came out Jul 1, 2025. Knowledge cutoff: Jamba Large Aug 22, 2024, GPT-5-Codex Sep 30, 2024, GPT-5 Chat 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.
