impulse

Llama Guard 3 11B Vision

Open weightsModeration
API id llama-guard-3-11b-vision
Input / 1M
$0.35
at IBM watsonx.ai
Output / 1M
$0.35
at IBM watsonx.ai
Context window
128K
tokens
Max output
128K
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$0.35$0.35

What it costs a month

At IBM watsonx.ai list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$131
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$181
  • Coding agent1,000 requests a day, 40K in / 2K out$441
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$924
Use your own numbers

Where to run it

1 host serve Llama Guard 3 11B Vision. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
llama-guard-3-11b-vision
$0.35 / $0.35

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
TextImages
Produces
Text
Open weights
License: Llama Community License
Runtimes: Ollama, TGI, 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 Meta models

No cheaper Meta model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

No cheaper open-weight match.

Call it

Using IBM watsonx.ai's API.

Python
from litellm import completion

response = completion(
    model="watsonx/llama-guard-3-11b-vision",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Llama Guard 3 11B Vision cost?

On IBM watsonx.ai, Llama Guard 3 11B Vision costs $0.35 per million input tokens and $0.35 per million output tokens.

Which APIs offer Llama Guard 3 11B Vision?

Llama Guard 3 11B Vision runs on 1 API: IBM watsonx.ai.

What is Llama Guard 3 11B Vision's context window?

128K tokens, with up to 128K tokens in one reply.

Is Llama Guard 3 11B Vision being retired?

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

What is Llama Guard 3 11B Vision's API model id?

Use llama-guard-3-11b-vision with IBM watsonx.ai.

Sources

Raw catalog entry for llama-guard-3-11b-vision on IBM watsonx.ai
{
  "max_input_tokens": 128000,
  "max_output_tokens": 128000,
  "input_cost_per_token": 3.5e-7,
  "output_cost_per_token": 3.5e-7,
  "litellm_provider": "watsonx",
  "mode": "chat",
  "supports_function_calling": false,
  "supports_parallel_function_calling": false,
  "supports_vision": true
}