OpenAI
GPT-5-Codex
Coding-optimized GPT model for repository edits, reviews, and agentic software work
Model facts
- Context window
- 4K tokens
- Maximum output
- 128K tokens
- Cheapest paid input
- $1.07 per 1M tokens
- Cheapest paid output
- $8.5 per 1M tokens
- Open weights
- no
- Providers
- 11
Capabilities and modalities
reasoning, tool calling, structured output, attachments, temperature control, text, image, pdf.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| high | 37.0 | not measured | 98.7 | not measured |
Observed price history
- 2026-08-24: $0.625 input / $5 output per 1M tokens
- 2026-08-28: $1.07 input / $8.5 output per 1M tokens
API providers
- GitLab Duo — model id duo-chat-gpt-5-codex; free input / free output per 1M tokens; provider documentation
- OpenCode Zen — model id gpt-5-codex; $1.07 input / $8.5 output per 1M tokens; provider documentation
- Poe — model id openai/gpt-5-codex; $1.1 input / $9 output per 1M tokens; provider documentation
- Jiekou.AI — model id gpt-5-codex; $1.12 input / $9 output per 1M tokens; provider documentation
- Abacus — model id gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation
- Azure — model id gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation
- Azure Cognitive Services — model id gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation
- Helicone — model id gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation
- Impossibl — model id openai/gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation
- Vercel AI Gateway — model id openai/gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation
- ZenMux — model id openai/gpt-5-codex; $1.25 input / $10 output per 1M tokens; provider documentation