Meta Muse Glimmer 30B API in India

Muse Glimmer 30B is an open-weight agentic model from Meta, live on unoblox as meta-models/muse-glimmer-30b. It accepts text and image input, supports reasoning and tools, and bills in rupees with GST.

What Muse Glimmer 30B is

Meta released Muse Glimmer in August 2026 as a 30 billion parameter model under the Apache 2.0 licence, designed for agent workflows and built to run on consumer hardware. Meta emphasises tool use, multi-step reasoning and long-horizon task trajectories. unoblox lists a context length of 131,072 tokens, with text and image input and text output.

On unoblox you get it as a hosted API, so there is no GPU to manage.

Where it fits

• Tool-using agents that plan and call functions across many turns.
• LLM-as-a-judge evaluation for scoring other models' outputs.
• Coding assistance at a mid-size price point.

Choose Muse Glimmer for a mid-sized open model with agent focus. For bigger context or more raw capability, look at the larger models in the catalogue.

₹ pricing for Muse Glimmer 30B

On unoblox, Muse Glimmer 30B costs ₹28.88 per million input tokens and ₹115.54 per million output tokens. That displayed price is what you are billed per token; nothing is added on top. Cached input tokens are listed at ₹3.85 per million. The model's context length on unoblox is 131,072 tokens.

Model	Input (₹ / 1M tokens)	Output (₹ / 1M tokens)
Muse Glimmer 30B	₹28.88	₹115.54
Qwen3.6 35B A3B	₹9.63	₹91.47
gpt-oss 20B	₹2.89	₹13.48
Llama 3.3 70B Instruct Turbo	₹9.63	₹30.81

As a worked example, a month with 20 million input tokens and 4 million output tokens comes to about ₹1,039.76 on Muse Glimmer 30B (₹577.60 for input plus ₹462.16 for output). Live rates are always on the model page, and each request is rounded up to the nearest paisa.

Calling Muse Glimmer 30B from the unoblox endpoint

unoblox is OpenAI-compatible, so any OpenAI SDK works by changing the base URL and key.

curl https://api.unoblox.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_UNOBLOX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "meta-models/muse-glimmer-30b",
    "messages": [{"role": "user", "content": "Summarise this support ticket in two lines."}],
    "max_tokens": 512
  }'

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_UNOBLOX_API_KEY",
    base_url="https://api.unoblox.ai/v1",
)
resp = client.chat.completions.create(
    model="meta-models/muse-glimmer-30b",
    messages=[{"role": "user", "content": "Summarise this support ticket in two lines."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

For image input, pass an image_url content part:

resp = client.chat.completions.create(
    model="meta-models/muse-glimmer-30b",
    messages=[{"role": "user", "content": [
        {"type": "text", "text": "What does this chart show?"},
        {"type": "image_url", "image_url": {"url": "https://example.com/chart.png"}},
    ]}],
    max_tokens=512,
)

Get a key at https://unoblox.ai/sign-in and top up your wallet in rupees.

Notes on parameters, billing and data

Use max_tokens for output limits and image_url parts for images. The model runs at an external provider and not in India, so we make no data-residency claim. unoblox provides rupee pricing, GST invoicing and one endpoint.

Frequently asked questions

Is Muse Glimmer 30B available in India? Yes, as meta-models/muse-glimmer-30b on https://api.unoblox.ai/v1.

Who makes it? Meta.

Is it open weight? Yes, under Apache 2.0.

What context length is listed? 131,072 tokens.

Does it take images? unoblox lists text and image input.

Does it support reasoning and tools? Yes, both are listed.

Get started in rupees → https://unoblox.ai/sign-in