AI model
openai/gpt-5.3-codex:fast-reasoning
OpenAI: GPT-5.3-Codex (fast) (Reasoning) is a 400,000-token model served on Composite at $2.19 per million tokens in and $17.5 per million tokens out.
Try in Playground| Model ID | openai/gpt-5.3-codex:fast-reasoning |
|---|---|
| Provider | Azure |
| Context window | 400,000 tokens |
| Accepts | text, image, file |
| Returns | text |
| Input price | $2.19 per million tokens |
| Output price | $17.5 per million tokens |
| Prompt caching | Supported — cached input is billed at the provider's cache rate, on credits and plans alike |
| Web search | $0.0125 per result |
| Thinking | Optional - see "OpenAI: GPT-5.3-Codex (fast) (Reasoning) (Reasoning)" in the catalog to turn it on by default |
| Moderated | Yes - by the provider |
| Cost on a monthly plan | About 28 plan credits per typical call (8k in, 1k out) |
| Routing endpoints | 1 |
Make a Composite API key and type openai/gpt-5.3-codex:fast-reasoning as the model name. JanitorAI takes the full URL https://composite.lucidity.sh/v1/chat/completions; SillyTavern, ChubAI, Agnai and RisuAI take https://composite.lucidity.sh/v1. It runs on credits, a plan, or your own provider key.
JanitorAI setup · SillyTavern setup · Best Janitor AI proxies compared
This model has not carried enough traffic on Composite yet to publish a success rate, a latency figure or a traffic rank. The numbers appear here once it has.
$2.19 per million tokens input · $17.5 per million tokens output
Credits pay the provider’s price plus 25%; cache hits cost less.
On a monthly plan, a typical call (8k tokens in, 1k out) uses about 28 plan credits, at the provider's own price.
Azure
This is an OpenAI model, a dependable baseline with broad instruction-following and consistent formatting across long conversations.
With a 400,000-token context window, it can hold a long-running roleplay or a full lorebook in memory without losing earlier plot details, so it suits multi-session campaigns and character cards with heavy backstory.
It sits in the mid-range on price, a reasonable pick for regular roleplay use without going for the cheapest option available.
GPT-5.3-Codex is OpenAI’s most advanced agentic coding model, combining the frontier software engineering performance of GPT-5.2-Codex with the broader reasoning and professional knowledge capabilities of GPT-5.2. It achieves state-of-the-art results...
Supplied by Azure, not written by Composite.
Composite GPT Router · OpenAI: GPT-6.1 Terra Pro · OpenAI: GPT-6.1 Terra