Add OpenAI chat-latest model metadata

[PeterDaveHello]

Relevant issues

N/A

Linear ticket

N/A

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

• I have Added testing in the tests/test_litellm/ directory, Adding at least 1 test is a hard requirement - see details
• My PR passes all unit tests on make test-unit
• My PR's scope is as isolated as possible, it only solves 1 specific problem
• I have requested a Greptile review by commenting @greptileai and received a Confidence Score of at least 4/5 before requesting a maintainer review

Delays in PR merge?

If you're seeing a delay in your PR being merged, ping the LiteLLM Team on Slack (#pr-review).

CI (LiteLLM team)

CI status guideline:

• 50-55 passing tests: main is stable with minor issues.
• 45-49 passing tests: acceptable but needs attention
• <= 40 passing tests: unstable; be careful with your merges and assess the risk.

• Branch creation CI run
  Link:

• CI run for the last commit
  Link:

• Merge / cherry-pick CI run
  Links:

Screenshots / Proof of Fix

Tested locally:

uv run pytest tests/test_litellm/test_openai_chat_latest_model_metadata.py -vv
uv run pytest tests/test_litellm/test_utils.py -k "model_prices" -vv
uv run pytest tests/test_litellm/litellm_core_utils/llm_cost_calc/test_tool_call_cost_tracking.py -k "web_search or file_search" -vv

Automated review:

cr --agent
findings: 0

Reference docs:

• https://developers.openai.com/api/docs/models/chat-latest
• https://developers.openai.com/api/docs/pricing#tools

Type

✅ Test

Changes

Adds OpenAI chat-latest metadata to the root model pricing map and the
packaged backup map.

The new entry includes token limits, pricing, endpoint support, modal
support, and hosted tool capability metadata, including file search and
web search cost tracking.

Adds a focused test covering:

• chat-latest model metadata and routing through the OpenAI provider
• root model map and packaged backup map parity

[codecov]

Codecov Report

❌ Patch coverage is 91.28440% with 19 lines in your changes missing coverage. Please review.

Files with missing lines	Patch %	Lines
litellm/router.py	86.00%	7 Missing ⚠️
litellm/cost_calculator.py	14.28%	6 Missing ⚠️
litellm/integrations/opentelemetry.py	90.69%	4 Missing ⚠️
...integrations/opentelemetry_utils/gen_ai_semconv.py	98.50%	1 Missing ⚠️
litellm/proxy/proxy_server.py	80.00%	1 Missing ⚠️

📢 Thoughts on this report? Let us know!

[greptile-apps]

Greptile Summary

This PR adds chat-latest model metadata to the root and backup pricing JSON files, along with a focused test suite verifying the new entry.

• Token limits, pricing ($5.00/$0.50/$30.00 per M tokens confirmed against OpenAI docs), capability flags, and endpoint support are all present and match existing conventions (e.g., 272K input + 128K output for a 400K-window model follows the same pattern as other GPT-5.x entries).
• The uniform $0.01 per query for all three search_context_size tiers correctly reflects the flat $10.00/1k-call pricing for the standard web search tool (as opposed to the tiered per-context-size pricing used only by the dedicated search-preview models).
• The test file exercises metadata correctness, provider routing, and root/backup parity without making any real network calls.

Confidence Score: 5/5

Safe to merge — the change is a JSON metadata addition with no logic changes and a dedicated test confirming correctness.

All three files make isolated, additive changes: two JSON entries and one new test file. The pricing values were verified against the OpenAI pricing page, token limits follow the established GPT-5.x convention, and the backup JSON mirrors the root exactly as confirmed by the parity test. No existing behavior is modified.

No files require special attention.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	Adds chat-latest entry with correct pricing ($5/$0.50/$30 per M tokens), token limits (272K input / 128K output), and capability flags; consistent with existing GPT-5.x conventions.
litellm/model_prices_and_context_window_backup.json	Identical chat-latest entry as the root JSON; backup stays in sync, verified by the new parity test.
tests/test_litellm/test_openai_chat_latest_model_metadata.py	New focused tests: one validates all metadata fields for chat-latest and its provider routing; a second asserts parity between root and backup JSON. No network calls — passes the mock-only rule.

_{Reviews (2): Last reviewed commit: "Add OpenAI chat-latest model metadata" | Re-trigger Greptile}

[ishaan-berri]

@greptile review again

[PeterDaveHello]

@ishaan-berri, is there anything else I can do for it? Thanks.

[oss-pr-review-agent-shin]

🤖 litellm-agent: Auto-merge skipped — the staging branch shin_agent_oss_staging_05_15_2026 has 217 commit(s) not in your branch. Merging as-is would produce a confusing diff on the staging PR.

Please rebase your branch onto shin_agent_oss_staging_05_15_2026 and push; the agent will re-review automatically.

[PeterDaveHello]

@Sameerlite, is there anything I can do to make it right?

[PeterDaveHello]

Hi @Sameerlite, I opened a fresh replacement PR targeting litellm_internal_staging: #28649. Thanks again for the guidance.