ibm-granite/granite-4.2-8b

deepinfra/ibm-granite-granite-4.2-8b

Mid-size Granite 4.2 model (dense 8B, August 2026) from IBM, with built-in chain-of-thought that can be switched to low-effort or off, tool calling for agent workflows and a 128K native context; Apache 2.0, aimed at cost-conscious enterprise use.

Get API Key Read the Docs

curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/ibm-granite-granite-4.2-8b",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'

Input Price: $0.051 / 1M tokens
Output Price: $0.2125 / 1M tokens
Context: 131.1K tokens
Output Cap: 16.4K tokens

Capabilities

Explore what ibm-granite/granite-4.2-8b supports, then use the API section for a request tailored to this model.

Max tokens

Model Information

Provider: DeepInfra
Product: Language Models
Release Date: Aug 25, 2026
Data Policy: Not specified
Region: US
Input: Text
Output: Text

Provider Documentation

Playground

Try ibm-granite/granite-4.2-8b by DeepInfra. Requests use the selected workspace’s credits and API pricing.

ibm-granite/granite-4.2-8b

Providers

Compare available endpoints, pricing, and context limits for ibm-granite/granite-4.2-8b.

Provider	Context	Output Cap	Input Price	Output Price	Endpoint
DeepInfra	131.1K tokens	16.4K tokens	$0.051 / 1M tokens	$0.2125 / 1M tokens	`ibm-granite/granite-4.2-8b`

Prices are catalog rates. Your workspace’s estimate and endpoint pricing determine the final charge.

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max input tokens	131072
Max output tokens	16384

Provider Notes

General LLM inference is an integration preview. Managed billing and deployment acceptance must be enabled before requests can be served.

Performance

Uptime100%

Time to First TokenMedianP90233 ms

Throughput—

Performance

Status

Current catalog availability. Your workspace’s access is checked separately before a request runs.

Checking availability…

A live availability check is not available right now.

Getting Started

Use your workspace API key and the exact model identifier below. Set the API URL to the endpoint shown in your workspace and keep credentials on your server.

curl "$AUDIOLAB_API_URL/v1/chat/completions" \
  -H "Authorization: Bearer $AUDIOLAB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepinfra/ibm-granite-granite-4.2-8b",
  "messages": [
    {
      "role": "user",
      "content": "Help me plan my next project."
    }
  ],
  "max_tokens": 256
}'

Read the Endpoint Reference

Request Parameters

Available parameters depend on the provider and request format. The endpoint reference explains accepted values and required fields.

Parameter	Details
`model`	`deepinfra/ibm-granite-granite-4.2-8b` — Required model identifier.
`max_tokens`	View Accepted Values

Input and Output Limits

Formats and limits AudioLab enforces on each request.

Limit	Value
Max input tokens	131072
Max output tokens	16384

Similar Models

Explore more language models and compare their capabilities.

Model	Context	Input Price	Output Price
inclusionAI/Ling-3.0-flash-VLDeepInfra	131.1K tokens	$0.051 / 1M tokens	$0.153 / 1M tokens
DeepSeek V4 Pro 0813DeepInfra	1M tokens	$1.105 / 1M tokens	$2.21 / 1M tokens
Muse Glimmer 30BDeepInfra	131.1K tokens	$0.255 / 1M tokens	$1.02 / 1M tokens
inclusionAI/Ling-3.0-flashDeepInfra	131.1K tokens	$0.051 / 1M tokens	$0.153 / 1M tokens
DeepSeek V4 Flash 0731DeepInfra	1M tokens	$0.051 / 1M tokens	$0.153 / 1M tokens
InklingDeepInfra	524.3K tokens	$0.8075 / 1M tokens	$3.4425 / 1M tokens

View All Language Models