May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass.…
Model details →DeepSeek: R1 0528 vs Prime Intellect: INTELLECT-3
Prime Intellect: INTELLECT-3 wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
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 …
Model details →Side-by-side comparison
| Capability | DeepSeek: R1 0528 | Prime Intellect: INTELLECT-3 | Winner |
|---|---|---|---|
| Context window Maximum number of input tokens the model can attend to in a single request. | 164K | 131K | 🏆 DeepSeek: R1 0528 |
| Input price (per 1M) Cost per million input tokens billed by the provider. | $0.45 | $0.20 | 🏆 Prime Intellect: INTELLECT-3 |
| Output price (per 1M) Cost per million output tokens billed by the provider. | $2.15 | $1.10 | 🏆 Prime Intellect: INTELLECT-3 |
| Tool / function calling First-class support for emitting structured tool calls. | Yes | Yes | Tie |
| Vision input Accepts image inputs alongside text. | — | — | Tie |
| Reasoning mode Internal chain-of-thought / extended-thinking support. | Yes | Yes | Tie |
Frequently asked questions
Is DeepSeek: R1 0528 better than Prime Intellect: INTELLECT-3?
Prime Intellect: INTELLECT-3 wins on 2 of 6 axes — pricing and capability skew in its favour for most workloads.
What's the price difference between DeepSeek: R1 0528 and Prime Intellect: INTELLECT-3?
Input: $0.45 vs $0.20 per 1M tokens. Output: $2.15 vs $1.10 per 1M tokens.
What context windows do DeepSeek: R1 0528 and Prime Intellect: INTELLECT-3 support?
DeepSeek: R1 0528 supports up to 164K tokens. Prime Intellect: INTELLECT-3 supports up to 131K tokens.
Do both DeepSeek: R1 0528 and Prime Intellect: INTELLECT-3 support tool calling?
DeepSeek: R1 0528: yes. Prime Intellect: INTELLECT-3: yes.