Granite 3 8b Instruct

Provider: watsonx · watsonx/ibm/granite-3-8b-instruct

Pricing per million tokens

Component USD per 1M tokens
Input $0.20
Output $0.20

Monthly cost estimates

Assuming 30% prompt-cache hit rate where available. Adjust for your actual usage.

Small
1M in / 200k out
$0.24
per month
Medium
10M in / 2000k out
$2.40
per month
Large
100M in / 20000k out
$24.00
per month

Context

Input window
8,192 tokens
Max output
1,024 tokens

Capabilities

  • ⬜ Vision (image input)
  • ✅ Function / tool calling
  • ✅ Prompt caching
  • ⬜ Web search
  • ✅ JSON / response schema

Compare Granite 3 8b Instruct with similar models

Granite 3 3 8b Instruct
watsonx
$0.20 in / $0.20 out
Granite Guardian 3 2 2b
watsonx
$0.10 in / $0.10 out
Granite Guardian 3 3 8b
watsonx
$0.20 in / $0.20 out
Granite Vision 3 2 2b
watsonx
$0.10 in / $0.10 out
Gpt Oss 120b
watsonx
$0.15 in / $0.60 out
Flan T5 Xl 3b
watsonx
$0.60 in / $0.60 out

Pricing data sourced from LiteLLM and refreshed regularly. Last updated May 20, 2026. Always verify with the provider's official pricing page before making business decisions.