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,...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Nebiusfp8 | $0.200 | $1.10 | 131K | — |
INTELLECT-3 costs $0.200 per million input tokens and $1.10 per million output tokens via OpenRouter, making it 97th cheapest of 298 paid models.
INTELLECT-3 scores 22.2 on the Artificial Analysis Intelligence Index, ranking 112th of 178 benchmarked models, with a GPQA Diamond score of 76%.
INTELLECT-3 generates around 58 tokens per second with 183ms time-to-first-token (p50), the 142nd fastest tracked model.
INTELLECT-3 supports a 131K-token context window and can output up to 131K tokens. It accepts text input.