fix(ui): add Nano-GPT to dashboard provider list

[Brohammad]

Relevant issues

Fixes #34499

Linear ticket

Pre-Submission checklist

• I have added meaningful tests
• My PR passes all CI/CD checks (e.g., lint, format, unit tests)
• My PR's scope is as isolated as possible; it only solves 1 specific problem
• I have received a Greptile Confidence Score of at least 4/5 before requesting a maintainer review (Greptile reviews automatically once the PR is opened; only comment @greptileai to re-request a review after pushing changes)

Screenshots / Proof of Fix

Commit: 9a2508d8a8

Start the proxy:

python litellm/proxy/proxy_cli.py --config litellm/proxy/dev_config.yaml --detailed_debug --use_v2_migration_resolver

Confirm Nano-GPT is exposed on the public provider-fields endpoint the Add Model dropdown reads:

curl -s http://localhost:4000/public/providers/fields | python3 -c "import json,sys; providers=json.load(sys.stdin); print(json.dumps(next(p for p in providers if p['provider']=='NANOGPT'), indent=2))"

Output at 9a2508d8a8:

{
  "provider": "NANOGPT",
  "provider_display_name": "Nano-GPT",
  "litellm_provider": "nano-gpt",
  "credential_fields": [
    {
      "key": "api_base",
      "label": "API Base",
      "placeholder": "https://nano-gpt.com/api/v1",
      "tooltip": null,
      "required": false,
      "field_type": "text",
      "options": null,
      "default_value": "https://nano-gpt.com/api/v1"
    },
    {
      "key": "api_key",
      "label": "API Key",
      "placeholder": null,
      "tooltip": null,
      "required": false,
      "field_type": "password",
      "options": null,
      "default_value": null
    }
  ],
  "default_model_placeholder": "gpt-4o"
}

In the Admin UI, open Add Model and search the provider dropdown for "Nano-GPT"

Type

New Feature

Changes

Nano-GPT already worked in the SDK/proxy backend but was missing from the dashboard Add Model provider list because /public/providers/fields had no entry for it

This adds NANOGPT to provider_create_fields.json, wires the enum/slug/logo in provider_info_helpers.tsx, and adds a regression test so the provider stays selectable in the UI

Final Attestation

• The tests check the right things, including the edge cases, and regressions in the respective real-world customer use-cases are not possible after this PR

Made with Cursor

[Copilot]

Copilot was unable to review this pull request because the user who requested the review has reached their quota limit.

[greptile-apps]

Greptile Summary

Adds Nano-GPT to the dashboard provider catalog

• Defines its public provider metadata, credential fields, API base, and model placeholder
• Wires the dashboard enum, provider slug, and shared logo mapping
• Adds endpoint regression coverage for the new provider entry

Confidence Score: 5/5

The PR appears safe to merge

The public metadata, dashboard lookup key, provider slug, API base, and existing logo asset align with the current Nano-GPT backend and Add Model flow

Important Files Changed

Filename	Overview
litellm/proxy/public_endpoints/provider_create_fields.json	Adds Nano-GPT metadata consistent with the existing backend provider slug and API base
tests/test_litellm/proxy/public_endpoints/test_public_endpoints.py	Adds focused regression coverage confirming Nano-GPT is exposed through the public provider-fields endpoint
ui/litellm-dashboard/src/components/provider_info_helpers.tsx	Adds matching Nano-GPT enum, slug, and logo mappings used by the Add Model flow

_{Reviews (1): Last reviewed commit: "fix(ui): add Nano-GPT to dashboard provi..." | Re-trigger Greptile}

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 9a2508d8a8

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Create mappings for Nano-GPT free-text models

When this new provider is selected, getProviderModels returns an empty list because the model cost map has no litellm_provider: "nano-gpt" entries, so LiteLLMModelNameField falls back to the bare text input path. That path never populates model_mappings, and prepareModelAddRequest only creates deployments by iterating model_mappings, so typing a Nano-GPT model and clicking Add Model silently returns before modelCreateCall. Please either add Nano-GPT model-cost entries so the select/custom path is used, or handle the free-text provider case by creating a mapping from formValues.model.

Useful? React with 👍 / 👎.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.

📢 Thoughts on this report? Let us know!