feat(nebius): switch to tokenfactory and sync model list - #2087
Merged
Merged
Conversation
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Deactivate nebius providers for models retired from Nebius (DeepSeek-R1-0528, Qwen2.5-Coder-7B-fast, Qwen3-Coder-30B-A3B-Instruct, Qwen3-30B-A3B-Thinking-2507, Kimi-K2-Instruct) and add nebius providers for active list models (MiniMax-M2.5, Qwen3.5-397B-A17B, Qwen3-Next-80B-A3B-Thinking, GLM-5, DeepSeek-V3.2, gpt-oss-120b). Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Contributor
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: Repository UI Review profile: CHILL Plan: Pro Run ID: 📒 Files selected for processing (1)
WalkthroughChange Nebius provider base URL from Changes
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~20 minutes Possibly related PRs
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
There was a problem hiding this comment.
Pull request overview
Updates Nebius integration to use the TokenFactory host and synchronizes the repo’s Nebius provider mappings with Nebius’s active model catalog so routing/pricing stays current.
Changes:
- Switched Nebius default base URL from
api.studio.nebius.comtoapi.tokenfactory.nebius.com. - Added/extended Nebius provider mappings for several existing model definitions (including new
kimi-k2.5pricing and additional Nebius availability for GLM-5, GPT OSS 120B, etc.). - Marked multiple Nebius mappings as deactivated as of
2026-04-25where those models are no longer in Nebius’s active list.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 1 comment.
Show a summary per file
| File | Description |
|---|---|
| packages/models/src/models/zai.ts | Adds Nebius provider mapping for glm-5. |
| packages/models/src/models/openai.ts | Adds Nebius provider mapping for gpt-oss-120b. |
| packages/models/src/models/moonshot.ts | Deactivates Nebius kimi-k2-instruct mapping; adds Nebius Kimi-K2.5 mapping with pricing. |
| packages/models/src/models/minimax.ts | Adds Nebius provider mapping for minimax-m2.5. |
| packages/models/src/models/deepseek.ts | Deactivates Nebius deepseek-r1-0528; adds Nebius provider mapping for deepseek-v3.2. |
| packages/models/src/models/alibaba.ts | Deactivates selected Nebius Qwen/DeepSeek mappings; adds Nebius mappings for additional active Qwen models. |
| packages/actions/src/get-provider-endpoint.ts | Updates Nebius base URL used for endpoint construction. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
226
to
228
| case "nebius": | ||
| url = "https://api.studio.nebius.com"; | ||
| url = "https://api.tokenfactory.nebius.com"; | ||
| break; |
There was a problem hiding this comment.
getProviderEndpoint() now hardcodes a different Nebius base URL, but there is no unit test asserting the Nebius default endpoint. Please add/update a test in packages/actions/src/get-provider-endpoint.spec.ts to lock in the expected Nebius URL (e.g. https://api.tokenfactory.nebius.com/v1/chat/completions) so future changes don’t silently break Nebius routing.
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against the current code and only fix it if needed.
Inline comments:
In `@packages/models/src/models/moonshot.ts`:
- Around line 278-292: Update the Nebius model entry where providerId is
"nebius" and modelName is "moonshotai/Kimi-K2.5": set the properties tools and
jsonOutput from false to true so the configuration reflects Nebius's support for
tool-calling and JSON response format; keep all other fields unchanged
(inputPrice, cachedInputPrice, outputPrice, requestPrice, contextSize,
maxOutput, streaming, reasoning, vision).
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Repository UI
Review profile: CHILL
Plan: Pro
Run ID: b3ad7c48-9229-4438-a6d0-90ae5e72a420
📒 Files selected for processing (7)
packages/actions/src/get-provider-endpoint.tspackages/models/src/models/alibaba.tspackages/models/src/models/deepseek.tspackages/models/src/models/minimax.tspackages/models/src/models/moonshot.tspackages/models/src/models/openai.tspackages/models/src/models/zai.ts
Streaming tool calls intermittently emit reasoning only without the tool_calls delta; response_format: json_object is not consistently honored (output is sometimes wrapped in markdown fences). Underlying capabilities exist, so flag tools/jsonOutput true and mark the provider unstable. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
Match the kimi-k2.5 fix: the model supports tools (Nebius lists it as an agentic coding model with interleaved-thinking tool calls) but Nebius' streaming tool calls and json_object enforcement are unreliable. Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
steebchen
added this pull request to the merge queue
Apr 26, 2026
steebchen
removed this pull request from the merge queue due to a manual request
Apr 26, 2026
This was referenced Apr 27, 2026
This was referenced May 7, 2026
2 tasks done
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
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.
Summary
api.studio.nebius.comtoapi.tokenfactory.nebius.comkimi-k2.5($0.50 / $2.50 per 1M, $0.02 / 1M cached input)deactivatedAt: 2026-04-25) Nebius entries no longer in the active list:deepseek-r1-0528,qwen25-coder-7b,qwen3-coder-30b-a3b-instruct,qwen3-30b-a3b-thinking-2507,kimi-k2-instructminimax-m2.5,qwen35-397b-a17b,qwen3-next-80b-a3b-thinking,glm-5,deepseek-v3.2,gpt-oss-120bNot included
Test plan
TEST_MODELS=nebius/kimi-k2.5 pnpm test:e2e— 67 passed, 0 failedpnpm build:core🤖 Generated with Claude Code
Summary by CodeRabbit
Updates
New Features