Granite 4 H Small vs Granite 4 H Medium
Side-by-side comparison of API pricing, specs, benchmarks, and capabilities
Granite 4 H Small is 59% cheaper on blended cost ($0.107 vs $0.262/Mtok) — note: different model classes (budget vs mid tier)
| Specification |
by IBM
|
by IBM
|
|---|---|---|
| Overview | ||
| Status | Current budget Open weights | Current mid tier Open weights |
| Released | Oct 19, 2025 | Oct 19, 2025 |
| Pricing per million tokens | ||
| Input | $0.060/Mtok | $0.150/Mtok |
| Output | $0.250/Mtok | $0.600/Mtok |
| Blended avg | $0.107/Mtok | $0.262/Mtok |
| Specifications | ||
| Context window | 128K tokens | 128K tokens |
| Parameters | Proprietary | Proprietary |
| Speed (TPS) | — | — |
| Modalities | ||
| Input |
text
|
text
|
| Benchmarks sources: Artificial Analysis, IBM model card, IBM model card (5-shot) / IBM model card | ||
| MMMLU | 69.69 vendor | 68 vendor |
| BFCL | 64.69 vendor | 48 vendor |
| HumanEval | 88 vendor | 72 vendor |
| GPQA Diamond | — | 35 vendor |
| SWE-Bench Verified | — | 15 vendor |
| Humanity's Last Exam | — | 7 vendor |
| ARC-AGI 2 | — | 5 vendor |
| AIME 2025 | — | 28 vendor |
| MATH 500 | — | 50 vendor |
| Independent composite scores each on its own scale — not part of the average above | ||
| AA Intelligence Index | 5 | — |
| Providers | ||
| Available from |
IBM — $0.060/$0.250/Mtok
|
IBM — $0.150/$0.600/Mtok
|
Cost at scale
1M tokens · 50/50 input/output| Volume | Granite 4 H Small | Granite 4 H Medium | Savings |
|---|---|---|---|
| 1M tokens | $0.11 | $0.26 | $0.15 (57.1%) |
| 10M tokens | $1.08 | $2.62 | $1.55 (59%) |
| 100M tokens | $10.75 | $26.25 | $15.5 (59%) |
| 1000M tokens | $107.5 | $262.5 | $155 (59%) |
When to pick which
distilled from the pricing and spec data above
Pick Granite 4 H Small if…
- cost dominates: $0.107/Mtok blended vs $0.262 — 59% less on the same 50/50 token mix
Pick Granite 4 H Medium if…
- this pairing gives Granite 4 H Medium no edge on price, context, cache discount, or measured performance — pick it only for qualitative fit (ecosystem, compliance, model behavior on your prompts)
Try Granite 4 H Small on IBM
The cheaper option here — Granite 4 H Small costs $0.107/Mtok blended on IBM.
Summary
Granite 4 H Small by IBM costs $0.060/Mtok input and $0.250/Mtok output, with a 128K-token context window. It supports text input.
Granite 4 H Medium by IBM costs $0.150/Mtok input and $0.600/Mtok output, with a 128K-token context window. It supports text input.
On a blended cost basis, Granite 4 H Small is 59% cheaper than Granite 4 H Medium.
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 Mistral Large 3
65% price gap
Granite 4 H Medium vs Qwen3.7-Plus
63% price gap
Granite 4 H Medium vs Qwen-Plus
56% price gap
Granite 4 H Medium vs DeepSeek V4 Pro
52% price gap
Granite 4 H Medium vs GPT-5.6 Luna
42% price gap
Granite 4 H Medium vs Solar Pro 3
Claude Fable 5 vs DeepSeek V4 Pro
97% price gap
Claude Opus 5 vs DeepSeek V4 Pro
95% price gap