Custom Models

Manage the model registry to add custom models, sync from the API, and configure per-provider defaults.

Built-In Models

Each provider comes with a set of built-in models:

prompts-gpt models --provider codex

Codex (OpenAI)

gpt-5.5
gpt-5.4
gpt-5.4-mini
gpt-5.4-nano
o3

Claude (Anthropic)

claude-opus-4-1-20250805
claude-opus-4-20250514
claude-sonnet-4-20250514
claude-3-7-sonnet-20250219
claude-3-5-haiku-20241022
claude-3-haiku-20240307

Cursor

Uses Claude and GPT models via Cursor's model routing

Copilot

Uses models via GitHub's model routing

Adding Custom Models

prompts-gpt models --add my-fine-tuned-model --provider codex

Custom models are stored in .prompts-gpt/models.json.

Removing Custom Models

prompts-gpt models --remove my-fine-tuned-model --provider codex

Syncing Model Registry

Fetch the latest models from the API:

prompts-gpt sync-models

Per-Provider Defaults

Set in config.json:

{
  "modelOverrides": {
    "codex": "gpt-5.5",
    "claude": "claude-sonnet-4-20250514",
    "cursor": "auto"
  }
}

Command-Line Override

prompts-gpt run task.md --provider codex --model gpt-5.4

The --model flag takes highest precedence.

Model Resolution Order

--model CLI flag
PROMPTS_GPT_MODEL environment variable
modelOverrides[provider] in config
Provider default

Programmatic Access

import { resolveModelAlias, getModelCostTier, estimateTokenCost } from "prompts-gpt";

const model = resolveModelAlias("gpt-5.5", "codex");
const tier = getModelCostTier(model);
const cost = estimateTokenCost(model, 1000, 3000);

console.log(`Model: ${model}, Tier: ${tier}, Est. cost: $${cost}`);