impulse

Granite Vision 3.3 2B

Open weights
API id granite-vision-3.3-2b
Input / 1M
$0.00
at Replicate
Output / 1M
$0.25
at Replicate
Context window
-
tokens
Max output
-
tokens per reply
Hosts
1
1 listings
Released
-
date not published

Pricing

List prices at Replicate, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.00$0.25

What it costs a month

At Replicate list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$18.75
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$9.00
  • Coding agent1,000 requests a day, 40K in / 2K out$15.00
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$60.00
Use your own numbers

Where to run it

1 host serve Granite Vision 3.3 2B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
ReplicateInference
granite-vision-3.3-2b
$0.00 / $0.25

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: 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 Replicate.

Smaller IBM models

No cheaper IBM model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Gemma 3 4B IT
    Google · on Amazon Bedrock
    $0.04 / $0.08
    Has every key capability
    20% less
  • Qwen3.7 Flash Variant1
    Alibaba Qwen · on EmpirioLabs AI
    $0.028 / $0.11
    Has every key capability
    22% less
  • Ministral 3B
    Mistral AI · on Azure AI Foundry
    $0.04 / $0.04
    Has every key capability
    36% less
  • Gemma 4 E2B
    Google · on Amazon Bedrock
    $0.04 / $0.08
    Has every key capability
    20% less

Model line

Newer and older versions, at each lab's own price.

  1. UndatedGranite Vision 3.3 2BLatest$0.00 / $0.25
  2. UndatedGranite Vision 3.2 2B$0.10 / $0.10

Call it

Using Replicate's API.

Python
from litellm import completion

response = completion(
    model="replicate/granite-vision-3.3-2b",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Granite Vision 3.3 2B cost?

On Replicate, Granite Vision 3.3 2B costs $0.25 per million output tokens.

Which APIs offer Granite Vision 3.3 2B?

Granite Vision 3.3 2B runs on 1 API: Replicate.

Is Granite Vision 3.3 2B being retired?

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

Is there a newer version of Granite Vision 3.3 2B?

No. Granite Vision 3.3 2B is the newest model in its line.

What are cheaper alternatives to Granite Vision 3.3 2B?

Models that cost less and keep most of what it can do: Gemma 3 4B IT on Amazon Bedrock (20% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Granite Vision 3.3 2B's API model id?

Use granite-vision-3.3-2b with Replicate.

Sources

Raw catalog entry for granite-vision-3.3-2b on Replicate
{
  "input_cost_per_token": 0,
  "litellm_provider": "replicate",
  "mode": "chat",
  "output_cost_per_token": 2.5e-7,
  "source": "https://replicate.com/ibm-granite/granite-vision-3.3-2b",
  "supports_system_messages": true,
  "supports_vision": true
}