IBM

Granite 20B

Estimated pricingSmall memory

Granite 20B is IBM's small-memory model. This page shows current pricing, an interactive cost calculator, and a side-by-side with similar models.

Input

$0.80/1M tokens

Output

$0.80/1M tokens

Cached

—

Batch

—

Interactive

Calculate your Granite 20B bill.

Adjust the workload below and watch the monthly cost update in real time.

What would Granite 20B cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Granite 20B at a glance.

Memory

8,192

tokens

Max reply

4,096

tokens

Memory tier

Small

a few emails or a short document

Tokenizer

default

Released

—

Training cutoff

—

Availability

Estimated

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Granite 20B

  • High-volume workloads where unit cost matters.
  • Code generation, review, or refactoring.

When to look elsewhere

  • Your workload involves images — pick a vision-capable model instead.
  • You need tool-use / function calling for agent workflows.
  • Your inputs routinely exceed short documents.

Alternatives

Similar models to compare.

FAQ

Granite 20B — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Granite 20B costs roughly $92 per month. Input is $0.80 /1M tokens and output is $0.80 /1M tokens.
Granite 20B has a 8,192-token context window (small memory — a few emails or a short document). That means you can fit about 1,536 words of input and history in a single call.
Models in a similar class include Qwen 2.5, GPT-5, GPT-5.1. The "Similar models" section below this FAQ links into each.
Open-weight model — price from a common hosting provider (Together, Fireworks, Replicate). We source estimates from the cheapest public hosting provider for that model and note it on the page.

Still unsure?

Compare Granite 20B against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizardBook a call