Model Card
Molmo 2 8B is an open vision-language model from AI2 built on Qwen3-8B with SigLIP 2 vision backbone, supporting image, video, and multi-image understanding with state-of-the-art grounding and tracking capabilities. It outperforms larger models on video pointing benchmarks and excels at counting and captioning tasks.
Context Window N/A
tokens
Max Output 37K
tokens
Input Cost $0.2
per million tokens
Output Cost $0.2
per million tokens
Release Date Dec 14, 2025
API Usage Example
Add AI to your app with just a few lines of code.
No backend, no configuration required.
// npm install @heyputer/puter.js
import { puter } from '@heyputer/puter.js';
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
<html>
<body>
<script src="https://js.puter.com/v2/"></script>
<script>
puter.ai.chat("Explain quantum computing in simple terms").then(response => {
document.body.innerHTML = response.message.content;
});
</script>
</body>
</html>
# pip install openai
from openai import OpenAI
client = OpenAI(
base_url="https://api.puter.com/puterai/openai/v1/",
api_key="YOUR_PUTER_AUTH_TOKEN",
)
response = client.chat.completions.create(
model="MODEL_ID",
messages=[
{"role": "user", "content": "Explain quantum computing in simple terms"}
],
)
print(response.choices[0].message.content)
curl https://api.puter.com/puterai/openai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_PUTER_AUTH_TOKEN" \
-d '{
"model": "MODEL_ID",
"messages": [
{"role": "user", "content": "Explain quantum computing in simple terms"}
]
}'
More AI Models From Allen AI
Olmo 3.1 32B Instruct
OLMo 3.1 32B Instruct is AI2's most capable fully open chat model, optimized for multi-turn conversation, instruction-following, and tool use. It represents the strongest fully open 32B-scale instruct model in AI2's evaluations, built on Dolma 3 with extended RL training.
ChatOlmo 3.1 32B Think
OLMo 3.1 32B Think is the updated flagship reasoning model from AI2 with an additional three weeks of reinforcement learning training beyond OLMo 3. It uses long chain-of-thought thinking for complex reasoning tasks and remains fully open with all training artifacts publicly available.
ChatOlmo 3 32B Think
OLMo 3 32B Think is AI2's flagship open reasoning model that uses long chain-of-thought thinking to improve performance on math and coding tasks. Trained on the Dolma 3 dataset with reinforcement learning from verifiable rewards, it's one of the strongest fully open reasoning models in its class.
Frequently Asked Questions
You can access Molmo2 8B by Allen AI through Puter.js AI API. Include the library in your web app or Node.js project and start making calls with just a few lines of JavaScript — no backend and no configuration required. You can also use it with Python or cURL via Puter's OpenAI-compatible API.
Yes, it is free if you're using it through Puter.js. With the User-Pays Model, you can add Molmo2 8B to your app at no cost — your users pay for their own AI usage directly, making it completely free for you as a developer.
| Price per 1M tokens | |
|---|---|
| Input | $0.2 |
| Output | $0.2 |
Molmo2 8B was created by Allen AI and released on Dec 14, 2025.
Molmo2 8B can generate up to 37K tokens in a single response.
Yes — the Molmo2 8B API works with any JavaScript framework, Node.js, or plain HTML through Puter.js. Just include the library and start building. See the documentation for more details.
Get started with Puter.js
Add AI to your application without worrying about API keys or setup.
Explore Models View Tutorials