feat(cost): add baseten model api pricing entries

[Sameerlite]

Add Baseten Model API pricing entries for Nemotron, GLM, Kimi, GPT OSS, and DeepSeek models with validated model slugs. Include a focused regression test to assert provider and per-token pricing values.

Fixes LIT-2147

Relevant issues

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:

Type

🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test

Changes

[vercel]

The latest updates on your projects. Learn more about Vercel for GitHub.

Project	Deployment	Actions	Updated (UTC)
litellm	Ready	Preview, Comment	Apr 8, 2026 4:41pm

[codspeed-hq]

Merging this PR will not alter performance

✅ 16 untouched benchmarks

---

_{Comparing litellm_baseten-model-api-pricing2 (5c5c899) with main (62757ff)}

[greptile-apps]

Greptile Summary

This PR adds pricing entries for 11 new Baseten Model API models — Nemotron, MiniMax, GLM (3 variants), Kimi (3 variants), GPT OSS, and DeepSeek (2 variants) — to both model_prices_and_context_window.json and its backup, along with a focused unit test to verify all entries. The changes also include minor Black-formatter-driven reformatting of existing test assertions.

• 11 new baseten/ model entries added to both JSON pricing files with litellm_provider, mode, input_cost_per_token, and output_cost_per_token fields
• New test test_baseten_model_api_pricing_entries in tests/test_litellm/test_cost_calculator.py verifies provider and per-token pricing for all 11 models using the local cost map (no network calls)
• Existing test assertions reformatted for Black compliance — logic is unchanged
• None of the new entries include max_tokens/max_input_tokens context window information, which is consistent with the existing pattern for Baseten models in this file

Confidence Score: 5/5

Safe to merge — pure data addition with matching unit test coverage and no logic changes.

All changes are additive: 11 new pricing entries in both JSON files and a new mock test that verifies them. The test uses LITELLM_LOCAL_MODEL_COST_MAP=True so no network calls are made. Existing test assertions were reformatted by Black with no semantic changes. No P0 or P1 issues found.

No files require special attention.

Vulnerabilities

No security concerns identified. Changes are limited to pricing data in JSON files and a read-only unit test against the local cost map.

Important Files Changed

Filename	Overview
model_prices_and_context_window.json	11 new baseten model pricing entries added; all follow the existing pattern for baseten (cost-only, no context window fields); pricing values are internally consistent
litellm/model_prices_and_context_window_backup.json	Identical 11 entries added as in the primary JSON file; kept in sync correctly
tests/test_litellm/test_cost_calculator.py	New mock-only test added for all 11 baseten entries; uses LITELLM_LOCAL_MODEL_COST_MAP=True (no network calls); remaining changes are Black reformatting with no logic changes

Flowchart

%%{init: {'theme': 'neutral'}}%%
flowchart TD
    A[PR: Add Baseten Pricing Entries] --> B[model_prices_and_context_window.json]
    A --> C[model_prices_and_context_window_backup.json]
    A --> D[tests/test_litellm/test_cost_calculator.py]

    B --> E[11 new baseten/ entries]
    C --> E

    E --> E1[baseten/nvidia/Nemotron-120B-A12B]
    E --> E2[baseten/MiniMaxAI/MiniMax-M2.5]
    E --> E3[baseten/zai-org/GLM-5/4.7/4.6]
    E --> E4[baseten/moonshotai/Kimi-K2.5/Thinking/Instruct]
    E --> E5[baseten/openai/gpt-oss-120b]
    E --> E6[baseten/deepseek-ai/DeepSeek-V3.1/V3-0324]

    D --> F[test_baseten_model_api_pricing_entries]
    F --> G{LITELLM_LOCAL_MODEL_COST_MAP=True}
    G --> H[litellm.get_model_cost_map url=empty]
    H --> I[Assert all 11 entries present with correct provider + pricing]

Loading

_{Reviews (1): Last reviewed commit: "feat(cost): add baseten model api pricin..." | Re-trigger Greptile}