GPT-5 Chat vs GPT-5-Codex
GPT-5-Codex comes out ahead, 42 to 34 on our weighted score.
OpenAIGPT-5 Chat
34/100- ECI—
- Price$1.25 / $10.00
- Context400K
- Our pickOpenAI
GPT-5-Codex
42/100- ECI—
- Price$1.25 / $10.00
- Context400K
Add a model
Make it a three-way comparison.
GPT-5-Codex is our pick
GPT-5-Codex is the better all-round choice, scoring 42/100 against GPT-5 Chat (34). 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 priceSame priceGPT-5 Chat $3.44 · GPT-5-Codex $3.44 per 1M tokens (3:1 blend)
- Longest contextAbout the sameGPT-5 Chat 400,000 · GPT-5-Codex 400,000 tokens
- Widest inputsSame inputsGPT-5 Chat: Text, Images · GPT-5-Codex: Text, Images
- Self-hostingNo open weightsBoth are available only through APIs
| Measure | Weight | GPT-5 Chat | GPT-5-Codex |
|---|---|---|---|
| Price | 50% | 24 | 24 |
| Inputs & features | 30% | 45 | 70 |
| Context window | 20% | 44 | 44 |
| Overall | 100% | 34/100 | 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 | GPT-5 ChatOpenAI | GPT-5-CodexOpenAI |
|---|---|---|
| Capability | ||
| Capabilities Index (ECI) | — | — |
| ECI rank | — | — |
| Price per million tokens | ||
| Input | $1.25 | $1.25 |
| Output | $10.00 | $10.00 |
| Cached input | — | — |
| Blended (3:1) | $3.44 | $3.44 |
| Long-context rate | Same rate | Same rate |
| Price source | Median of 2 providers | Median of 3 providers |
| Limits | ||
| Context window | 400,000 tokens | 400,000 tokens |
| Max output | 128,000 tokens | 128,000 tokens |
| Inputs and features | ||
| Text | Yes | Yes |
| Images | Yes | Yes |
| PDFs | No | No |
| Audio | No | No |
| Video | No | No |
| Reasoning | Yes | Yes |
| Tool calling | No | Yes |
| Structured output | Yes | Yes |
| Availability | ||
| Weights | Proprietary | Proprietary |
| API model ID | — | — |
| API providers | 2 | 3 (best) |
| Released | Aug 7, 2025 | Sep 15, 2025 |
| Knowledge cutoff | 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.
- GPT-5 Chat$32.50
- GPT-5-Codex$32.50
Which should you choose?
Which is better: GPT-5 Chat or GPT-5-Codex?
GPT-5-Codex is the better all-round choice, scoring 42/100 against GPT-5 Chat (34). 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, GPT-5 Chat or GPT-5-Codex?
GPT-5 Chat and GPT-5-Codex cost the same: $1.25 input / $10.00 output per million tokens.
Which scores higher on benchmarks?
There is no independent benchmark that covers both models yet. GPT-5 Chat 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 GPT-5 Chat and GPT-5-Codex 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 Chat and GPT-5-Codex share the same 400,000-token context window. Maximum output per response: GPT-5 Chat up to 128,000, GPT-5-Codex up to 128,000 tokens.
Which can read images, PDFs, audio or video?
GPT-5 Chat accepts text and images; GPT-5-Codex accepts text and images. They handle the same number of input types.
Are any of these open source?
No. GPT-5 Chat and GPT-5-Codex are proprietary and only available through APIs and apps.
Which is newer?
GPT-5-Codex is the newest, released Sep 15, 2025. GPT-5 Chat came out Aug 7, 2025. Knowledge cutoff: GPT-5 Chat Sep 30, 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.
