Granite 4.0 Micro with Jev
Granite 4.0 Micro is a model from IBM, released 2025-10-20. It costs $0.017 per million input tokens and $0.112 per million output tokens, reads up to 131K tokens of context, and writes up to 117,900 tokens in one reply. Through llm11, set model to ibm-granite/granite-4.0-h-micro.
- Input price
- $0.017 / 1M
- Output price
- $0.112 / 1M
- Context window
- 131K tokens
- Max output
- 118K tokens
- Released
- 2025-10-20
- Accepts
- text
Read from the live catalogue and refreshed daily. At blended list price, 98% of the 332 priced models we can call cost more.
Using Granite 4.0 Micro with Jev
Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Granite 4.0 Micro does the answering when Jev sends it work, or when you name it yourself. At list price Granite 4.0 Micro falls in the llm11-fast band, but no pack routes to it because IBM is not one of the labs the packs draw from. You can still pin it: pass ibm-granite/granite-4.0-h-micro as model and routing steps aside while verification still runs.
Jev is new, so we have not published results for Granite 4.0 Micro with and without it, and this page does not invent any. Every response comes with a receipt that names the model that answered and what it cost against your most expensive model, so you can measure the pairing on your own traffic.
What a request costs
List price arithmetic, the same sum a receipt does. llm11 adds nothing per request; the only fee is on buying credits.
| Request | Tokens in / out | One | A thousand |
|---|---|---|---|
| Short chat turn | 500 / 200 | $0.00003 | $0.031 |
| Question over retrieved documents | 4,000 / 500 | $0.00012 | $0.124 |
| Long document summary | 30,000 / 1,000 | $0.00062 | $0.622 |
Cheaper models to try
The catalogue has no benchmark score for Granite 4.0 Micro, so this is a price ordering. It does not claim these answer as well.
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| OpenAI gpt-oss-20b | $0.018 | $0.090 | 131K | |
| Mistral Mistral Nemo | $0.019 | $0.030 | 131K |
Call it
Same OpenAI request shape. Naming the model pins it, so nothing is routed, and the answer is still checked.
python
from openai import OpenAI
client = OpenAI(base_url="https://www.llm11.com/v1", api_key="llm11_live_...")
res = client.chat.completions.create(
model="ibm-granite/granite-4.0-h-micro",
messages=[{"role": "user", "content": "Hello"}],
)More from IBM
| Model | Input / 1M | Output / 1M | Context | Released |
|---|---|---|---|---|
| Granite 4.2 8B | $0.060 | $0.250 | 131K |
Questions
- What is Granite 4.0 Micro with Jev?
- Jev is TypeSafe AI's System One model. It reads each request first and decides which model in your pool answers, with a calibrated confidence on that call. Granite 4.0 Micro does the answering when Jev sends it work, or when you name it yourself. At list price Granite 4.0 Micro falls in the llm11-fast band, but no pack routes to it because IBM is not one of the labs the packs draw from. You can still pin it: pass ibm-granite/granite-4.0-h-micro as model and routing steps aside while verification still runs. Routing decisions are made by Jev, TypeSafe AI's System One model.
- Is Granite 4.0 Micro a System One model?
- No. Granite 4.0 Micro answers requests. The System One model is Jev, which decides which model answers each one, so the two do different jobs and llm11 uses both.
- How much does Granite 4.0 Micro cost?
- $0.017 per million input tokens and $0.112 per million output tokens. A 4,000 token prompt with a 500 token answer costs about $0.00012, so a thousand of them is about $0.124. llm11 passes provider list price through and charges 5% when you buy credits.
- What is the Granite 4.0 Micro context window?
- 131,000 tokens, with up to 117,900 tokens in a single reply.
- Does Granite 4.0 Micro support tool calling and structured output?
- The catalogue lists structured output, but it does not list tool calling and reasoning controls.
- Can I use Granite 4.0 Micro through llm11?
- Yes. Set model to ibm-granite/granite-4.0-h-micro on the OpenAI-compatible endpoint and the request goes to it directly, with verification still running.
- Does Jev route to Granite 4.0 Micro?
- Routing decisions are made by Jev, TypeSafe AI's System One model. At list price Granite 4.0 Micro falls in the llm11-fast band, but no pack routes to it because IBM is not one of the labs the packs draw from. You can still pin it: pass ibm-granite/granite-4.0-h-micro as model and routing steps aside while verification still runs.
- What is a cheaper alternative to Granite 4.0 Micro?
- Nearest in price and below it: OpenAI gpt-oss-20b at $0.018 in and $0.090 out and Mistral Mistral Nemo at $0.019 in and $0.030 out. The catalogue has no benchmark score for Granite 4.0 Micro, so this is a price ordering. It does not claim these answer as well.