AI Observatory / Model Radar
Prime Intellect / prime-intellect/intellect-3
Prime Intellect: INTELLECT-3
INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...
131,072
Context
131,072
Max output
$0.20 / 1M
Prompt price
2025-11-27
Created
01 / Snapshot
Pricing, context, modalities, and parameters.
Model Radar detail pages stay neutral and operator-readable: core metadata first, then workflow fit.
| Provider | Prime Intellect | Input modalities | text |
|---|---|---|---|
| Output modalities | text | Prompt price | $0.20 / 1M |
| Completion price | $1.10 / 1M | Request price | N/A |
| Context length | 131,072 | Max completion tokens | 131,072 |
| Supported parameters | frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, structured_outputs, temperature, tool_choice, tools, top_k, top_p | ||
Best for
prime-intellect/intellect-3
Prime Intellect: INTELLECT-3
INTELLECT-3 is a 106B-parameter Mixture-of-Experts model (12B active) post-trained from GLM-4.5-Air-Base using supervised fine-tuning (SFT) followed by large-scale reinforcement learning (RL). It offers state-of-the-art performance for its size across math,...
High-volume usage
Coding workflows
tool-capable
low-cost
03 / Colophon
Routes and exits.
Each model page stays simple: overview, compare, related models, then back to the public hub.