chore(pricing): Update openai pricing

[siddharthsambharia-portkey]

🔄 Pricing Update: openai

📊 Summary (complete_diff mode)

Change Type	Count
➕ Models added	0
🔄 Models updated (merged)	20

🔄 Updated Models

• gpt-4.1-nano
• gpt-4.1-nano-2025-04-14
• codex-mini-latest
• o4-mini-deep-research-2025-06-26
• gpt-realtime
• gpt-realtime-2025-08-28
• gpt-realtime-mini
• gpt-4o-mini-realtime-preview
• gpt-4o-mini-realtime-preview-2024-12-17
• gpt-audio-mini
• gpt-4o-audio-preview
• gpt-4o-mini-audio-preview-2024-12-17
• gpt-4o-mini-tts
• gpt-4o-transcribe
• gpt-4o-mini-transcribe
• whisper-1
• gpt-image-1
• gpt-image-1-mini
• gpt-image-1.5
• chatgpt-image-latest

Model Coverage (130 models)

Data Sources

• Models API: get_openai_models — 128 models returned
• Pricing Page: https://platform.openai.com/docs/pricing (Standard tier)

Batch Summary

Batch	Models	Count
1	GPT-5.4, GPT-5.3, GPT-5.2, GPT-5.1, GPT-5 core family	25
2	GPT-5 pro/nano/mini/codex + GPT-4.1 + GPT-4o + Computer Use	25
3	GPT-4 legacy + O-series (o1, o3, o4) + GPT-3.5	25
4	Realtime (gpt-realtime, gpt-4o-realtime) + Audio + TTS (gpt-4o-mini-tts)	25
5	Transcription + Whisper + TTS-1/HD + gpt-image + chatgpt-image + DALL-E + Sora + Embeddings + Moderation + Instruct	25
6	gpt-4-1106, gpt-3.5-turbo-16k, davinci-002, babbage-002, o1-mini	5

Special Pricing Notes

• Realtime models: Include both text AND audio token prices (input/output/cache)
• TTS models: response_audio_price per 1M audio tokens; tts-1/tts-1-hd billed per million characters
• Whisper: Billed per minute of audio
• Image models (gpt-image-1.5, gpt-image-1, gpt-image-1-mini): Per-image prices by quality (low/medium/high) + per-token text/image prices
• DALL-E 3: standard/hd per-image pricing by size
• DALL-E 2: standard per-image pricing (256/512/1024)
• Sora: per-second video pricing by resolution
• Embeddings/Moderation: Free or low per-token rates

---

Generated by Pricing Agent on 2026-03-12