added openai gpt4o mini model

[meetpateltech]

blog post

---

🚀	This description was created by Ellipsis for commit 6256a11

Summary:

Added support for the new OpenAI GPT-4o Mini model, including chat setting limits, model definition, and type updates.

Key points:

• Added gpt-4o-mini model to CHAT_SETTING_LIMITS in lib/chat-setting-limits.ts with specific temperature, token output length, and context length limits.
• Added GPT4oMini model definition to lib/models/llm/openai-llm-list.ts with pricing and other details.
• Updated OpenAILLMID type in types/llms.ts to include gpt-4o-mini.

---

Generated with ❤️ by ellipsis.dev

[ellipsis-dev]

👍 Looks good to me! Reviewed everything up to 6256a11 in 42 seconds

More details

• Looked at 67 lines of code in 3 files
• Skipped 0 files when reviewing.
• Skipped posting 1 drafted comments based on config settings.

1. lib/chat-setting-limits.ts:160

• Draft comment:
  The addition of gpt-4o-mini with a MAX_TEMPERATURE of 2.0 seems inconsistent with other models of similar capacity. Typically, models in this range have a MAX_TEMPERATURE of 1.0. Please verify if this is intended or if it should be aligned with similar models.

  MAX_TEMPERATURE: 1.0,

• Reason this comment was not posted:
  Confidence of 0% on close inspection, compared to threshold of 50%.

Workflow ID: wflow_v6463Dz8m4qzggNs

---

You can customize Ellipsis with 👍 / 👎 feedback, review rules, user-specific overrides, quiet mode, and more.

[xaptronic]

mini supports 16k output tokens - would this limit it to 4k?

[o-24]

it will.

It should be

const response = await openai.chat.completions.create({
  model: chatSettings.model as ChatCompletionCreateParamsBase["model"],
  messages: messages as ChatCompletionCreateParamsBase["messages"],
  temperature: chatSettings.temperature,
  max_tokens:
    chatSettings.model === "gpt-4-vision-preview" ||
    chatSettings.model === "gpt-4o"
      ? 4096
      : chatSettings.model === "gpt-4o-mini"
      ? 16383
      : null, 
  stream: true
});

[meetpateltech]

Yeah, it's fixed! Thanks.

[o-24]

Need to fix MAX_TOKEN_OUTPUT_LENGTH for gpt-4o mini in lib/chat-setting-limits.ts from 4096 tokens to 16383.
Everything else is good:)

[o-24]

By the way MAX_TOKEN_OUTPUT_LENGTH: 4096 will also limit gpt-4o mini maximum response length to 4k tokens, it should be 16383 tokens

[meetpateltech]

just updated it! thanks 🙌

[xingfanxia]

@mckaywrigley please merge this

[Davitcoin]

@mckaywrigley

[haydenkong]

@mckaywrigley