LLM ReferenceLLM Reference
IBM watsonx

Granite 20B Code on IBM watsonx

Granite Code · IBM Research

Serverless

Last refreshed 2026-04-15. Next refresh: weekly.

Why use Granite 20B Code on IBM watsonx?

IBM watsonx offers Granite 20B Code with pay-as-you-go pricing at $0.60/1M input tokens. IBM offers a comprehensive AI platform that includes IBM watsonx, a next-generation enterprise AI and data platform.

Compare Granite 20B Code across 2 providers to find the best fit for your use case
Input / 1M
$0.60
Output / 1M
$0.60
Cache
Not sourced
Batch
Not sourced

Setup recipe

Docs fallback
Install
Use the provider REST API or SDK
Auth
Create a provider API key
Call
model: granite-20b-code
Model ID
granite-20b-code

Request example

Curated snippets for this provider are not sourced yet. Use IBM watsonx documentation with model ID granite-20b-code.

Gotchas

No curated gotchas have been sourced for this exact provider/model route yet.

Compare Granite 20B Code Across Providers

ProviderInput (per 1M)Output (per 1M)
RHEL AI
IBM watsonx$0.60$0.60

Pricing

TypePrice (per 1M)
Input tokens$0.60
Output tokens$0.60

Capabilities

No model capability flags are currently sourced.

FAQ

What does Granite 20B Code cost on IBM watsonx?

On IBM watsonx, Granite 20B Code costs $0.6 per 1M input tokens and $0.6 per 1M output tokens.

What is the context window for Granite 20B Code on IBM watsonx?

Granite 20B Code supports a 8,000 token context window on IBM watsonx.

How does IBM watsonx compare to other Granite 20B Code providers?

Granite 20B Code is available from 2 providers. The cheapest input pricing is $0.6/1M tokens from IBM watsonx.

Who created Granite 20B Code?

Granite 20B Code was created by IBM Research as part of the Granite Code model family.

Is Granite 20B Code open source?

Granite 20B Code's open source status is unknown in the seed data.

Get Started

Model Specs

Released2024-05-06
Parameters20B
Context8K
ArchitectureDecoder Only