AllocateDeepSeek R1 0528 NVFP4 vs GLM 4.7 FP8
On provider list prices, GLM 4.7 FP8 costs $0.45 per million input tokens against $3 for DeepSeek R1 0528 NVFP4: 6.7x apart. Output is $2 against $7 (3.5x). On Allocate both bill at list plus the 7% transaction fee.
DeepSeek R1 0528 NVFP4G GLM 4.7 FP8Specifications and provider list prices from the Allocate catalog, checked 2026-07-08. Billed price is list plus the 7% transaction fee.
What the numbers say
Take 1,000,000 requests a month at 1,200 input and 350 output tokens each. That workload costs $1,240 a month on GLM 4.7 FP8 and $6,050 on DeepSeek R1 0528 NVFP4 at list: a gap of $4,810, or 4.9x.
GLM 4.7 FP8 reads 198K tokens per request against 160K for DeepSeek R1 0528 NVFP4, 1.2x the window. That decides which one can take whole documents without splitting them.
Choose DeepSeek R1 0528 NVFP4 for
- Fine-tuning under a permissive license (MIT)
Choose GLM 4.7 FP8 for
- The lower list price ($0.45 in / $2 out per M tokens)
- The longer context window (198K vs 160K tokens)
- Fine-tuning under a permissive license (MIT)
Common questions
Which is cheaper, DeepSeek R1 0528 NVFP4 or GLM 4.7 FP8?
GLM 4.7 FP8, on this workload shape. At list prices it is $0.45/$2 per million tokens in and out against $3/$7 for DeepSeek R1 0528 NVFP4. Billed on Allocate: $0.48/$2.14 against $3.21/$7.49, list plus 7%.
Which has the bigger context window?
GLM 4.7 FP8: 202,752 tokens (198K) against 163,840 (160K) for DeepSeek R1 0528 NVFP4.
Can I fine-tune DeepSeek R1 0528 NVFP4 or GLM 4.7 FP8?
Both publish open weights (DeepSeek R1 0528 NVFP4: MIT; GLM 4.7 FP8: MIT), so both can be fine-tuned. On Allocate the trained weights stay inside your boundary and belong to you.
Related comparisons
Run the numbers on your workload
Or don’t choose. On Allocate a route name is the contract: point yours at one model today, swap to the other tomorrow, and compare them on your live traffic with per-token metering.