feat: Add Prime Intellect provider with INTELLECT-3 model#780
Open
chindris-mihai-alexandru wants to merge 2 commits intoanomalyco:devfrom
Open
feat: Add Prime Intellect provider with INTELLECT-3 model#780chindris-mihai-alexandru wants to merge 2 commits intoanomalyco:devfrom
chindris-mihai-alexandru wants to merge 2 commits intoanomalyco:devfrom
Conversation
- Add Prime Intellect as a new provider using OpenAI-compatible API - Include INTELLECT-3 model (106B MoE, 12B active params) - Model features: 131K context, tool calling, reasoning support - Pricing: $0.20/M input, $1.10/M output tokens - API endpoint: https://api.pinference.ai/api/v1 - Env var: PRIME_API_KEY
Contributor
There was a problem hiding this comment.
Pull request overview
This PR adds Prime Intellect as a new provider to models.dev, along with their INTELLECT-3 reasoning model. The implementation uses OpenAI-compatible API integration and includes proper configuration for the provider's API endpoint and authentication.
Changes:
- Added Prime Intellect provider configuration with OpenAI-compatible API support
- Added INTELLECT-3 model configuration with pricing, context limits, and capability flags
- Configured model as a reasoning-enabled MoE model with 131K context window
Reviewed changes
Copilot reviewed 2 out of 3 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| providers/prime-intellect/provider.toml | Defines the Prime Intellect provider with API endpoint, authentication, and OpenAI-compatible SDK |
| providers/prime-intellect/models/intellect-3.toml | Configures the INTELLECT-3 model with capabilities, pricing, and token limits |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
rekram1-node
reviewed
Feb 3, 2026
providers/prime-intellect/logo.svg
Outdated
Contributor
There was a problem hiding this comment.
could you make this the same color & size as other logos
There was a problem hiding this comment.
@rekram1-node sure thing, 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
2 participants
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
This PR adds Prime Intellect as a new provider to models.dev, along with their flagship INTELLECT-3 model.
Changes
New Provider:
prime-intellect@ai-sdk/openai-compatible)https://api.pinference.ai/api/v1PRIME_API_KEYNew Model:
intellect-3About INTELLECT-3
INTELLECT-3 is Prime Intellect's flagship reasoning model, post-trained from GLM-4.5-Air-Base using SFT and RL. It achieves state-of-the-art performance for its size class across math, code, and reasoning benchmarks:
Verification
bun validatepassesReferences