# OpenAI

> OpenAI Inference Provider Support

Source: https://tokenmojo.ai/providers/openai

## Stats

- Models published: 13
- Average quality: 14.7
- Median speed: 32.7 tok/s
- Average reliability: 15.4%
- Total samples: 2034

## Description

This integration enables direct access to OpenAI models through the standard API specification. Compare latency and pricing across vendors.

## Models

- [gpt-4.1-mini](https://tokenmojo.ai/models/openai/gpt-4-1-mini): OpenAI GPT-4.1 Mini: Efficient language model for scalable application deployment.
- [gpt-4.1-nano](https://tokenmojo.ai/models/openai/gpt-4-1-nano): OpenAI GPT-4.1 Nano: Efficient inference for scalable deployment.
- [gpt-5.3-chat-latest](https://tokenmojo.ai/models/openai/gpt-5-3-chat-latest)
- [gpt-5.4](https://tokenmojo.ai/models/openai/gpt-5-4): OpenAI GPT-5.4 Model Specification
- [gpt-5.4-mini](https://tokenmojo.ai/models/openai/gpt-5-4-mini): Compare GPT-5.4-mini performance metrics objectively.
- [gpt-5.4-nano](https://tokenmojo.ai/models/openai/gpt-5-4-nano): OpenAI GPT-5.4 Nano: Lightweight inference option for efficiency-focused workflows
- [gpt-5.4-pro](https://tokenmojo.ai/models/openai/gpt-5-4-pro)
- [gpt-5.5-pro](https://tokenmojo.ai/models/openai/gpt-5-5-pro): OpenAI gpt-5.5-pro provides reasoning capabilities for complex enterprise tasks.
- [gpt-5.6-luna](https://tokenmojo.ai/models/openai/gpt-5-6-luna)
- [gpt-5.6-sol](https://tokenmojo.ai/models/openai/gpt-5-6-sol)
- [gpt-5.6-terra](https://tokenmojo.ai/models/openai/gpt-5-6-terra)
- [gpt-5-codex](https://tokenmojo.ai/models/openai/gpt-5-codex): gpt-5-codex: OpenAI's code-focused LLM for technical tasks.
- [o4-mini](https://tokenmojo.ai/models/openai/o4-mini)