impulse

Granite Guardian 3.2 2B

Open weightsModeration
API id granite-guardian-3-2-2b
Input / 1M
$0.10
at IBM watsonx.ai
Output / 1M
$0.10
at IBM watsonx.ai
Context window
8K
tokens
Max output
8K
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at IBM watsonx.ai, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.10$0.10

What it costs a month

At IBM watsonx.ai list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$37.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$51.60
  • Coding agent1,000 requests a day, 40K in / 2K out$126
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$264
Use your own numbers

Where to run it

1 host serve Granite Guardian 3.2 2B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
granite-guardian-3-2-2b
$0.10 / $0.10

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runtimes: Ollama, llama.cpp, vLLM

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than IBM watsonx.ai.

Smaller IBM models

No cheaper IBM model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Llama Guard 3 8B
    Meta · on Nebius AI Studio
    $0.02 / $0.06
    Has every key capability
    70% less

Call it

Using IBM watsonx.ai's API.

Python
from litellm import completion

response = completion(
    model="watsonx/granite-guardian-3-2-2b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Granite Guardian 3.2 2B cost?

On IBM watsonx.ai, Granite Guardian 3.2 2B costs $0.10 per million input tokens and $0.10 per million output tokens.

Which APIs offer Granite Guardian 3.2 2B?

Granite Guardian 3.2 2B runs on 1 API: IBM watsonx.ai.

What is Granite Guardian 3.2 2B's context window?

8K tokens, with up to 8K tokens in one reply.

Is Granite Guardian 3.2 2B being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Granite Guardian 3.2 2B?

Models that cost less and keep most of what it can do: Llama Guard 3 8B on Nebius AI Studio (70% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Granite Guardian 3.2 2B's API model id?

Use granite-guardian-3-2-2b with IBM watsonx.ai.

Sources

Raw catalog entry for granite-guardian-3-2-2b on IBM watsonx.ai
{
  "max_input_tokens": 8192,
  "max_output_tokens": 8192,
  "input_cost_per_token": 1e-7,
  "output_cost_per_token": 1e-7,
  "litellm_provider": "watsonx",
  "mode": "chat",
  "supports_function_calling": false,
  "supports_parallel_function_calling": false,
  "supports_vision": false
}