Granite 4 H Large vs GLM-4.5
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
Granite 4 H Large is 46.4% cheaper on blended cost ($0.750 vs $1.40/Mtok)
| Specification |
by IBM
|
by Z.AI
|
|---|---|---|
| Overview | ||
| Status | Current mid tier Open weights | Current mid tier Open weights |
| Released | Oct 19, 2025 | Jan 1, 2025 |
| Pricing per million tokens | ||
| Input | $0.300/Mtok | $0.600/Mtok |
| Output | $1.20/Mtok | $2.20/Mtok |
| Blended avg | $0.750/Mtok | $1.40/Mtok |
| Cached input | — | $0.110/Mtok |
| Specifications | ||
| Context window | 128K tokens | 128K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: IBM model card / LMSYS Chatbot Arena (UC Berkeley) | ||
| GPQA Diamond | 42 vendor | — |
| SWE-Bench Verified | 20 vendor | — |
| Humanity's Last Exam | 10 vendor | — |
| ARC-AGI 2 | 8 vendor | — |
| AIME 2025 | 35 vendor | — |
| MMMLU | 70 vendor | — |
| BFCL | 52 vendor | — |
| HumanEval | 75 vendor | — |
| MATH 500 | 55 vendor | — |
| Independent composite scores each on its own scale — not part of the average above | ||
| LMSYS Chatbot Arena | — | 1410.7 ELO |
| Providers | ||
| Available from |
IBM — $0.300/$1.20/Mtok
|
Z.AI — $0.600/$2.20/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Granite 4 H Large | GLM-4.5 | Savings |
|---|---|---|---|
| 1M tokens | $0.75 | $1.4 | $0.65 (46.4%) |
| 10M tokens | $7.5 | $14 | $6.5 (46.4%) |
| 100M tokens | $75 | $140 | $65 (46.4%) |
| 1000M tokens | $750 | $1400 | $650 (46.4%) |
Try Granite 4 H Large on IBM
The cheaper option here — Granite 4 H Large costs $0.750/Mtok blended on IBM.
Summary
Granite 4 H Large by IBM costs $0.300/Mtok input and $1.20/Mtok output, with a 128K-token context window. It supports text input.
GLM-4.5 by Z.AI costs $0.600/Mtok input and $2.20/Mtok output, with a 128K-token context window. It supports text input.
On a blended cost basis, Granite 4 H Large is 46.4% cheaper than GLM-4.5.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.
More comparisons
pairs sharing a model with this page
Granite 4 H Medium vs GLM-4.5
73% price gap
DeepSeek V4 Pro vs GLM-4.5
53% price gap
Granite 4 H Large vs Reka Flash
46% price gap
Qwen-Plus vs GLM-4.5
43% price gap
Mistral Large 3 vs GLM-4.5
29% price gap
Sonar vs GLM-4.5
29% price gap
Granite 4 H Large vs Mistral Large 3
25% price gap
Granite 4 H Large vs Sonar
25% price gap