Granite 4.0 H Small API Pricing
IBM · released 2025-09-22
Also searched as: 4.0 H Small pricing
Granite 4.0 H Small price
< 0.01¢ / 1K
0.025¢ / 1K
0.011¢ / 1K
What it actually costs
| Workload | Tokens | Cost |
|---|---|---|
| Short chat reply | 500 in / 300 out | 0.0105¢ |
| RAG query | 4,000 in / 500 out | 0.0365¢ |
| Long document summary | 50,000 in / 1,000 out | 0.325¢ |
| Code review of a 2k-line file | 30,000 in / 2,000 out | 0.23¢ |
| 1,000 chat replies/day for 30 days | 30,000 × (500 in / 300 out) | $3.15 |
Cost = (input tokens ÷ 1,000,000 × $0.06) + (output tokens ÷ 1,000,000 × $0.25).
Benchmarks
#444 of 547
#205 of 249
Similar intelligence, lower price
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Gemma 4 E4B (Reasoning) | 8.9 | $0.04 |
| Llama 3.1 Instruct 8B | 6.9 | $0.043 |
| Sarvam 30B (High) | 6.6 | $0.047 |
| Mistral Small 3 | 6.7 | $0.058 |
| Nova Micro | 5.9 | $0.061 |
Leaderboard neighbours
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Jamba 1.7 Large | 6.1 | — |
| Qwen3.5 0.8B (Reasoning) | 6.1 | — |
| DeepSeek-Coder-V2 | 6.0 | — |
| Granite 4.0 H Small | 6.0 | $0.107 |
| Hermes 3 - Llama-3.1 70B | 6.0 | $0.70 |
| Jamba 1.5 Large | 6.0 | $3.50 |
| Jamba 1.6 Large | 6.0 | — |
More from IBM
| Model | Intelligence | Blended $/1M |
|---|---|---|
| Granite 4.2 30B | 12.7 | $0.282 |
| Granite 4.2 8B | 11.1 | $0.107 |
| Granite 4.2 3B | 9.1 | $0.052 |
| Granite 4.1 30B | 7.4 | — |
| Granite 4.1 8B | 6.6 | — |
| Granite 4.1 3B | 5.9 | — |
| Granite 4.0 H 1B | 5.2 | — |
| Granite 4.0 Micro | 5.1 | — |
Count tokens & estimate cost for Granite 4.0 H Small See Granite 4.0 H Small on the leaderboard
Source: Artificial Analysis · last synced 2026-10-15
FAQ
Who develops Granite 4.0 H Small?
Granite 4.0 H Small is developed by IBM, released 2025-09-22.
How much does Granite 4.0 H Small cost per million tokens?
Granite 4.0 H Small costs $0.06 per 1M input tokens and $0.25 per 1M output tokens ($0.107 blended), per Artificial Analysis's official pricing data.
What is the Granite 4.0 H Small API price?
The Granite 4.0 H Small API price is $0.06 per 1M input tokens and $0.25 per 1M output tokens ($0.107 per 1M blended).
How much does Granite 4.0 H Small cost for a typical request?
A short chat reply (500 in / 300 out tokens) costs about 0.0105¢ on Granite 4.0 H Small, at $0.06/1M input and $0.25/1M output.
Is Granite 4.0 H Small free?
Granite 4.0 H Small's official API list price is $0.06 per 1M input tokens and $0.25 per 1M output tokens. This site tracks list prices only, not free tiers or trial credits — check IBM's site for those.
How does Granite 4.0 H Small rank on benchmarks?
Granite 4.0 H Small scores 6.0 on the Artificial Analysis Intelligence Index, ranking #444 of 547 models we track.
Is there a cheaper model with similar intelligence to Granite 4.0 H Small?
Yes — Gemma 4 E4B (Reasoning) scores similar intelligence (8.9) at $0.04/1M blended, versus $0.107/1M for Granite 4.0 H Small.
Where does this data come from?
Pricing and benchmark data for Granite 4.0 H Small comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-10-15.