Model Library
OpenAIReleased September 23, 2025GPT-5 Codex (high)
OpenAI · Released September 23, 2025
Intelligence score
36
At a glance
- Intelligence
- 36
- Speed
- 190.6tokens/sec
- Latency
- 20.75stime to first token
- Input price
- $1.25per 1M tokens
- Output price
- $10.00per 1M tokens
- Context window
- 400Ktokens
- Parameters
- —
Summary
Comparison summary
GPT-5 Codex (high) scores 36 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 28). GPT-5 Codex (high) generates output at 190.6 tokens per second (based on OpenAI's API), which is well above average compared to other reasoning models in a similar price tier (median: 81.2 t/s). GPT-5 Codex (high) costs $1.25 per 1M input tokens (better than average, median: $1.50) and $10.00 per 1M output tokens (somewhat higher than average, median: $8.40), based on OpenAI's API.
Specifications
Technical specifications
| Model name | GPT-5 Codex (high) |
|---|---|
| Provider | OpenAI |
| Release date | September 23, 2025 |
| Intelligence score | 36 |
| Speed | 190.6 tokens/sec |
| Latency (TTFT) | 20.75s |
| Input price | $1.25 / 1M tokens |
| Output price | $10.00 / 1M tokens |
| Context window | 400,000 tokens |
| Parameters | — |
| Reasoning | Yes |
| Input modalities | text, image |
| Output modalities | — |
| Open weights | No |
| License | — |
| API availability | — |
| Source | Model Intelligence legacy profile: gpt-5-codex |
Pricing
Token prices
Price per 1M tokens
GPT-5 Codex (high), as listed in the catalog record
- Input$1.25
- Output$10.00
| Token type | Price per 1M |
|---|---|
| Input | $1.25 |
| Output | $10.00 |
Model Intelligence legacy profile: gpt-5-codex
FAQ · 19
Frequently asked questions
GPT-5 Codex (high) was released on September 23, 2025.
GPT-5 Codex (high) was created by OpenAI.
GPT-5 Codex (high) scores 36 (estimated) on the Artificial Analysis Intelligence Index, placing it above average among other reasoning models in a similar price tier (median: 28).
GPT-5 Codex (high) generates output at 190.6 tokens per second (based on OpenAI's API), which is well above average compared to other reasoning models in a similar price tier (median: 81.2 t/s).
GPT-5 Codex (high) has a time to first token (TTFT) of 20.75s (based on OpenAI's API), which is at the higher end compared to other reasoning models in a similar price tier (median: 2.78s).
GPT-5 Codex (high) costs $1.25 per 1M input tokens (better than average, median: $1.50) and $10.00 per 1M output tokens (somewhat higher than average, median: $8.40), based on OpenAI's API.
GPT-5 Codex (high) costs $1.25 per 1M input tokens and $10.00 per 1M output tokens (based on OpenAI's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $1.34 per 1M tokens. Pricing may vary by provider.
Yes, GPT-5 Codex (high) is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.
GPT-5 Codex (high) supports text and image input.
GPT-5 Codex (high) supports text output.
Yes, GPT-5 Codex (high) supports image input and can analyze, describe, and answer questions about images.
Yes, GPT-5 Codex (high) is multimodal. It can process text and image input and generate text output.
GPT-5 Codex (high) has a context window of 400k tokens. This determines how much text and conversation history the model can process in a single request.
No, GPT-5 Codex (high) is proprietary. The model weights are not publicly available.
GPT-5 Codex (high) is a proprietary model and OpenAI has not disclosed the model size or parameter count.
GPT-5 Codex (high) achieves a score of 36 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.
GPT-5 Codex (high) has a knowledge cutoff of September 2024. The model's training data includes information up to this date.
Yes, GPT-5 Codex (high) is available via API through 2 providers.
GPT-5 Codex (high) is available through 2 API providers.