Granite 4.0 H Small API pricing
Updated
IBM watsonx.ai is the only provider we checked (prices read 2026-11-15) that lists a standard price for Granite 4.0 H Small: USD 0.0636 per 1M input tokens and USD 0.265 per 1M output tokens. That is IBM watsonx.ai's own API. Each price is read from the provider's own pricing page.
What does IBM watsonx.ai charge for Granite 4.0 H Small?
- Input
- USD 0.0636
- Cached input
- not published
- Output
- USD 0.265
- Blended 3:1
- USD 0.114
USD per 1M tokens on IBM watsonx.ai, model granite-4h-small, standard tier. Source, checked 2026-11-15.
Is a host cheaper than IBM watsonx.ai? Only IBM watsonx.ai publishes a standard price for Granite 4.0 H Small: USD 0.0636 input and USD 0.265 output per 1M tokens. No third-party host lists it on its own pricing page yet.
Granite 4.0 H Small price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | IBM watsonx.ai cheapest makergranite-4h-smallNotes and source quote“granite-4h-small IBM USD 0.0636 per 1M tokens input USD 0.265 per 1M tokens output” | USD 0.0636 | not published | USD 0.265 | USD 0.114 | not stated | not stated | IBM watsonx.ai page checked 2026-11-15 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Granite 4.0 H Small cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| IBM watsonx.ai (maker) | USD 10.49 | USD 19.24 | USD 138.33 |
Estimate your own bill
- LLM API cost calculator with Granite 4.0 H Small preloaded: your traffic and cache rate, against any of 428 models.
- Token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Granite 4.0 H Small compare with other IBM models?
The IBM models whose cheapest standard price is closest to Granite 4.0 H Small's (USD 0.114 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| IBM Granite 4.2 8B | USD 0.06 | USD 0.15 | 131,072 | 2 |
Priced closest from other makers: Qwen3.5 9B (Qwen, USD 0.1125) · DeepSeek V4 Flash (DeepSeek, USD 0.1125) · GLM 5.3 Flash (Z.ai, USD 0.1187).
All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Granite 4.0 H Small API cost per token?
From USD 0.0636 per 1M input tokens (USD 0.0000000636 per token) and USD 0.265 per 1M output tokens (USD 0.000000265 per token) at the lowest standard prices we found. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Granite 4.0 H Small?
IBM watsonx.ai is the only provider we checked (prices read 2026-11-15) with a paid standard price, USD 0.0636 input and USD 0.265 output per 1M tokens, so there is nothing to rank yet.
Is Granite 4.0 H Small cheaper from a host than from IBM watsonx.ai?
Only IBM watsonx.ai publishes a standard price for Granite 4.0 H Small: USD 0.0636 input and USD 0.265 output per 1M tokens. No third-party host lists it on its own pricing page yet.
Does Granite 4.0 H Small have cached input pricing?
The only standard price has no cached-input price, so budget repeated prompts at the full input price.
How much does a coding agent cost per month on Granite 4.0 H Small?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 138.33 a month at IBM watsonx.ai. Most of the input is cached, so the cache price matters as much as the input price. Try your own numbers.
Is Granite 4.0 H Small free to use through an API?
No provider in our data lists a free price for Granite 4.0 H Small as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.