Skip to content
OpenKey

Granite 4.1 8B

IBMReleased Apr 30, 2026

Granite 4.1 8B is a dense, decoder-only 8-billion-parameter language model from IBM, part of the Granite 4.1 family. It supports a 131K-token context window and is designed for enterprise tasks...

Try in playground
Context window
131K tokens
Max output
131K tokens
Input
text
Output
text
Tokenizer
Other
Released
Apr 30, 2026

Pricing

Per 1M tokens. The provider price and our flat 3% fee are separate columns — what you pay is their sum.

Per 1M tokensProvider+ 3% feeYou pay
Input$0.050$0.0015$0.052
Output$0.100$0.0030$0.103
Cache read$0.050$0.0015$0.052

Benchmarks

Artificial Analysis

Intelligence index
Coding index
9.5
Agentic index

Supported parameters

  • frequency_penalty
  • logprobs
  • max_tokens
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Call it

OpenAI-compatible: point your SDK at api.openkey.ai/v1 and use model ibm-granite/granite-4.1-8b.

Code sample language
curl https://api.openkey.ai/v1/chat/completions \
  -H "Authorization: Bearer $OPENKEY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "ibm-granite/granite-4.1-8b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'
import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.openkey.ai/v1",
    api_key=os.environ["OPENKEY_API_KEY"],
)

completion = client.chat.completions.create(
    model="ibm-granite/granite-4.1-8b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(completion.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.openkey.ai/v1",
  apiKey: process.env.OPENKEY_API_KEY,
});

const completion = await client.chat.completions.create({
  model: "ibm-granite/granite-4.1-8b",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(completion.choices[0].message.content);

Questions

How much does Granite 4.1 8B cost via API?
Through OpenKey, Granite 4.1 8B costs $0.052 per 1M input tokens and $0.103 per 1M output tokens. That is the provider price ($0.050 / $0.100) plus a flat 3% fee — nothing else.
What is Granite 4.1 8B's context window?
Granite 4.1 8B accepts up to 131K tokens of context and returns up to 131K tokens per request.
Is Granite 4.1 8B OpenAI-compatible?
Yes. Send requests to OpenKey's /v1/chat/completions endpoint with model "ibm-granite/granite-4.1-8b" using any OpenAI SDK — only the base URL and API key change.
What inputs does Granite 4.1 8B support?
Granite 4.1 8B accepts text input and produces text output.

More from IBM

All IBM models →