INTELLECT Models by Prime Intellect
1 model2026Up to 128k ctx
Details
ResearcherPrime Intellect
LicenseApache 2.0OSI-approved
Commercial useCommercial use: permitted
Models1
Released2026
Max context128k
Capabilities
ReasoningAll models
Function CallingAll models
Tool UseAll models
Structured OutputsAll models
Links
WebsiteAbout
INTELLECT is Prime Intellect's series of open-weights MoE models trained through decentralized community compute, targeting frontier reasoning performance.
Current Variants
Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.
1 in view
INTELLECT-3Current
Use when the workload needs 128k context, 106B parameters, and reasoning.
2026-04128k context106B parametersreasoning
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| INTELLECT-3 | Use when the workload needs 128k context, 106B parameters, and reasoning. | 2026-04 | 128k context106B parametersreasoning | Current |
Release Timeline
1 release group2026-04
1 current
INTELLECT-3
Current128k context106B parametersreasoning
Specifications(1 models)
| Model | Released | Context | Parameters | Reasoning | Fn Calling | Tool Use | Structured Outputs |
|---|---|---|---|---|---|---|---|
| INTELLECT-3 | 2026-04 | 128k | 106B | Yes | Yes | Yes | Yes |
Frequently Asked Questions
- What is INTELLECT used for?
- INTELLECT is used for reasoning, agent workflows and tool use, and structured outputs. The family description and listed model capabilities point to those workloads as the best fit.
- How does INTELLECT compare to Claude 3?
- INTELLECT by Prime Intellect is strongest where you need reasoning, while Claude 3 by Anthropic is the closest related family to check for vision and multimodal work. INTELLECT has 1 listed variant and reaches up to 128k context, while Claude 3 reaches up to 200k context, so compare the specs and pricing tables before choosing a production model.
- Which INTELLECT model should I use?
- If price is the main constraint, use the pricing table first because INTELLECT does not have complete provider pricing in the local data. For the most capable/latest local choice, evaluate INTELLECT-3 with 128k context and reasoning, tool use, function calling, and structured outputs.