Skip to content

add gpt-5.4 models to azure-ai general and pricing configs#787

Open
muddhit-baid wants to merge 1 commit into
mainfrom
feat/azure-ai-gpt-5-4-models
Open

add gpt-5.4 models to azure-ai general and pricing configs#787
muddhit-baid wants to merge 1 commit into
mainfrom
feat/azure-ai-gpt-5-4-models

Conversation

@muddhit-baid
Copy link
Copy Markdown

@muddhit-baid muddhit-baid commented May 26, 2026

Summary

  • Adds general capabilities (params, response_format, type) for gpt-5.4, gpt-5.4-2026-03-05, gpt-5.4-mini, gpt-5.4-mini-2026-03-17, gpt-5.4-nano, gpt-5.4-nano-2026-03-17, and gpt-5.4-pro to general/azure-ai.json
  • Adds pricing entries for gpt-5.4, gpt-5.4-pro, gpt-5.4-mini, and gpt-5.4-nano to pricing/azure-ai.json (dated variants already existed)
  • Fixes gpt-5.4-mini-2026-03-17 cache_read_input_token price from 0.000008 to 0.0000075 (aligning with azure-openai source)
  • Mirrors the existing azure-openai configs for these models

Source Link: https://azure.microsoft.com/en-us/pricing/details/cognitive-services/openai-service/

Checklist

  • JSON is valid
  • Prices are in cents per token
  • Source pricing link included
  • Verified against azure-openai configs

Context

These models were available in Azure OpenAI but missing from the Azure AI (Foundry) provider, preventing users from seeing them in the Model Provisioning UI.

Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Adds Azure AI provider configurations for the GPT-5.4 family. The general config introduces seven new model entries (gpt-5.4, gpt-5.4-2026-03-05, mini and nano variants with their dated counterparts, and gpt-5.4-pro), and the pricing file adds the four entries that were not already present (the three dated variants existed previously). The pricing file also reformats four existing cache_read_input_token values from 0.0000005 to 5e-7.

Changes:

  • Add GPT-5.4 family general configs to general/azure-ai.json mirroring the structure used by neighboring GPT-5.x entries (chat models use max_completion_tokens + response_format; gpt-5.4-pro uses the responses primary type with playground disabled).
  • Add pricing entries for gpt-5.4, gpt-5.4-pro, gpt-5.4-mini, gpt-5.4-nano to pricing/azure-ai.json.
  • Convert four existing cache-read prices to scientific notation (5e-7).

Reviewed changes

Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.

File Description
general/azure-ai.json Adds seven GPT-5.4 model configs following existing Azure AI patterns.
pricing/azure-ai.json Adds four GPT-5.4 pricing entries and reformats four cache-read values to scientific notation.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread pricing/azure-ai.json Outdated
Comment on lines +4130 to +4140
"gpt-5.4-mini": {
"pricing_config": {
"pay_as_you_go": {
"request_token": {
"price": 0.000075
},
"response_token": {
"price": 0.00045
},
"cache_read_input_token": {
"price": 0.000008
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

Copilot reviewed 2 out of 2 changed files in this pull request and generated 2 comments.

Comment thread pricing/azure-ai.json
Comment on lines +4139 to +4141
"cache_read_input_token": {
"price": 0.0000075
},
Comment thread pricing/azure-ai.json
}
}
},
"gpt-5.4": {
Adds general capabilities and pricing for gpt-5.4, gpt-5.4-2026-03-05,
gpt-5.4-mini, gpt-5.4-mini-2026-03-17, gpt-5.4-nano, gpt-5.4-nano-2026-03-17,
and gpt-5.4-pro to the azure-ai provider.

Co-authored-by: Cursor <cursoragent@cursor.com>
@muddhit-baid muddhit-baid force-pushed the feat/azure-ai-gpt-5-4-models branch from 1ae5390 to 886c46d Compare May 26, 2026 09:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants