DeepSeek-R1 vs GLM 4.7
GLM 4.7 is cheaper on output tokens, while GLM 4.7 offers a larger context window. Choose DeepSeek-R1 or GLM 4.7 based on the trade-off between cost, context, and the benchmarks that matter for your use case.
| Spec | DeepSeek-R1 | GLM 4.7 |
|---|---|---|
| Provider | Azure | Z.ai |
| Input / 1M tokens | $1.35 | $0.60 |
| Output / 1M tokens | $5.40 | $2.20 |
| Context window | 164K | 205K |
| Parameters | 671B | 358B |
| Open weights | Yes | Yes |
| Released | Jan 2025 | Dec 2025 |
| LMArena (Chatbot Arena) Elo score | 1428 | 1435 |
| GPQA Diamond score | 76.3 | 83.3 |
| Epoch Capabilities Index score | 141 | 144 |
| LiveBench score | — | 57.3 |
| LMArena WebDev Elo score | — | 1435 |
| FrontierMath score | — | 2.4 |
FAQ
Is DeepSeek-R1 or GLM 4.7 cheaper?
GLM 4.7 is cheaper on output tokens ($2.20 vs $5.40 per 1M).
Which has the larger context window, DeepSeek-R1 or GLM 4.7?
GLM 4.7 has the larger context window (205K tokens).
Pricing is indicative — confirm with the provider before production use. Highlighted values indicate the better figure for that row.