I have Tier 4 rate limits on openAI. I add my api key and it does not give o1 as an option. I specifically would like to use bolt.diy to use this version of gpt
1 Like
Welcome @daniel.colaianni ,
these are hardcoded at the moment, but you code give it a try and add it yourself, within this file:
import { BaseProvider } from '~/lib/modules/llm/base-provider';
import type { ModelInfo } from '~/lib/modules/llm/types';
import type { IProviderSetting } from '~/types/model';
import type { LanguageModelV1 } from 'ai';
import { createOpenAI } from '@ai-sdk/openai';
export default class OpenAIProvider extends BaseProvider {
name = 'OpenAI';
getApiKeyLink = 'https://platform.openai.com/api-keys';
config = {
apiTokenKey: 'OPENAI_API_KEY',
};
staticModels: ModelInfo[] = [
{ name: 'gpt-4o', label: 'GPT-4o', provider: 'OpenAI', maxTokenAllowed: 8000 },
{ name: 'gpt-4o-mini', label: 'GPT-4o Mini', provider: 'OpenAI', maxTokenAllowed: 8000 },
{ name: 'gpt-4-turbo', label: 'GPT-4 Turbo', provider: 'OpenAI', maxTokenAllowed: 8000 },
{ name: 'gpt-4', label: 'GPT-4', provider: 'OpenAI', maxTokenAllowed: 8000 },
{ name: 'gpt-3.5-turbo', label: 'GPT-3.5 Turbo', provider: 'OpenAI', maxTokenAllowed: 8000 },
show original
if it works, feel free to open a feature request in github issues as well and post the link here. I will flag as feature then.