Add Tempr's OpenAI models - #7675
Open
chrissalomon wants to merge 2 commits into
Open
chrissalomon wants to merge 2 commits into
chrissalomon wants to merge 2 commits into
Conversation
31 models OpenAI currently serves that Tempr's Gateway can reach: 28 chat models and 3 embedding models, base_model-ing the lab entries with OpenAI's own pricing. The pro and codex variants are Responses-API-only at OpenAI; Tempr bridges chat completions and /v1/messages to them, so they need no [provider] override. Adds the missing models/openai lab files for the three embedding models. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Contributor
|
No actionable findings. |
github-actions
Bot
added
the
reviewer: ready
o3-pro and gpt-5.3-codex-spark answer 404 "does not exist or you do not have access to it" and are missing from /v1/models on a new organization's key (checked 2026-09-22), so a new Tempr customer can't reach them. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
github-actions
Bot
removed
the
reviewer: ready
Contributor
|
No actionable findings. |
github-actions
Bot
added
the
reviewer: ready
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Follow-up to #7638, which added Tempr as a provider: its OpenAI models, 29 in total (26 chat, 3 embedding). Tempr addresses them as
openai/<id>.Only models OpenAI currently serves that Tempr can reach (checked against OpenAI's deprecations page on 2026-09-21):
providers/openaimarks deprecated. Everything listed here is still served. The one scheduled change: OpenAI shuts down the snapshots behindgpt-5,gpt-5-mini,gpt-5-nano,gpt-5-proando3on 2026-12-11, so those entries will needstatus = "deprecated"at that point.o3-proandgpt-5.3-codex-spark: a new API organization gets 404 "does not exist or you do not have access to it" and doesn't see them in/v1/models(checked 2026-09-22), so a new Tempr customer can't reach them.gpt-image-2,gpt-image-1.5,gpt-image-1-mini,chatgpt-image-latest) andgpt-realtime-2.1: Tempr's Gateway serves chat completions,/v1/messages,/v1/responsesand/v1/embeddings, so nothing reaches them.gpt-5-pro,gpt-5.2-pro,gpt-5.4-pro,gpt-5.5-pro,gpt-5.3-codex) are Responses-API-only at OpenAI. Tempr bridges chat completions and/v1/messagesto the Responses API for them, so they need no[provider]override.The entries:
base_modelpoints at eachmodels/openai/entry with OpenAI's own pricing, since it's the same model on the caller's own key.reasoning_optionsare what Tempr'sGET /v1/modelsreports, and each file's leading comment lists the fields a caller sets. Reasoning docs: https://temprhq.io/docs/gateway-chat-completions#reasoningLab files:
text-embedding-3-small,text-embedding-3-largeandtext-embedding-ada-002had nomodels/openai/entry, so this adds them, copied fromproviders/openaiwithout the pricing. Embeddings docs: https://temprhq.io/docs/gateway-embeddingsbun validatepasses with this branch merged onto current dev.🤖 Generated with Claude Code