Prime Intellect: INTELLECT-3
Prime-intellectINTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervise
High value
Text
Specifications
| Vendor | Prime-intellect |
| Family | prime-intellect |
| Context | 131.1K · 98.3k words（≈ a thesis） |
| Max output | 131.1K · 98.3k words（≈ a thesis） |
| Released | 2026-06-19 |
| Open source | No |
| Tool use | — |
Pricing across channels
per 1M tokens, USD
| Channel | Type | Input | Output | → |
|---|---|---|---|---|
| OpenRouter (auto) | Aggregator | $0.20 | $1.10 | visitAd |
OpenRouter API (auto-fetched)· 2026-06-19
Related models
Similar tier, vendor or price range