Coding-optimized GPT model for repository edits, reviews, and agentic software workGPT-5.3 Codex by openai is offered by 38 providers on this page. Public prices are shown for 37 of them. Its official list price is $1.75 per 1M input tokens and $14.00 per 1M output tokens. The lowest paid channel is CommandCode at $2.00 / $8.00 per 1M, about 1.4× below the list price. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it. It also has 1 free ($0) channel; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.
Median output speed is 79 tokens per second, with 83.1s to the first token.
The context window is 400,000 tokens, with an output limit of 128,000 tokens. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Its training knowledge cuts off at 2025-08-31.
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| GitLab Duo duo-chat-gpt-5-3-codex | Cloud | Free | — | — | 400,000 | 128,000 | deprecated | |
| CommandCode | Gateway | $2.00 | $8.00 | $0.50 | $0 | 400,000 | 128,000 | |
| Poe | Gateway | $1.59 | $12.73 | $0.16 | — | 400,000 | 128,000 | |
| OpenAIOfficial | First-party | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 | |
| LLM Gateway | Gateway | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 | |
| LLM Gateway | Gateway | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 | |
| Requesty | Gateway | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 | |
| DigitalOcean openai-gpt-5.3-codex | Cloud | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 | |
| NanoGPT | Gateway | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 | |
| DevPass (LLM Gateway) | Gateway | $1.75 | $14.00 | $0.18 | — | 400,000 | 128,000 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Interleaved thinking (reasoning between tool calls) is declared by 2 of 38 providers.
3 / 38 providers expose no reasoning control (reasoning_options: []).
| Mode | Provider | Input | Output | Cache read | Cache write |
|---|---|---|---|---|---|
| fast | OpenAI | $3.50 | $28.00 | $0.35 | — |
1 more channels offer $0 (GitLab Duo); free tiers usually have rate limits and no SLA, excluded from ranking.
| Name | Conditions | Score | Metric | Source |
|---|---|---|---|---|
| SWE-Atlas Codebase QnA | harness: Codex | 32.6 | score | Source ↗ |
| SWE-Atlas Refactoring | harness: Codex | 42.38 | score | Source ↗ |
| SWE-Atlas Test Writing | harness: Codex | 38.98 | score | Source ↗ |
The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.
Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.