impulse

Muse Glimmer 30B

Open weights

Muse Glimmer 30B is a dense, open-weight multimodal model from Meta Superintelligence Labs, distilled from Muse Spark and optimized for autonomous agents on consumer hardware.

API id Muse-Glimmer-30BReleased 9 Aug 2026 (Aug 2026)
Input / 1M
$0.30
at DeepInfra
Output / 1M
$1.20
at DeepInfra
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
6
7 listings
Released
Aug 2026
9 Aug 2026

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.30$1.20
Cached input
87% off input
$0.04

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out, cached$157
  • RAG over documents2,000 requests a day, 8K in / 0.6K out, cached$125
  • Coding agent1,000 requests a day, 40K in / 2K out, cached$214
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$1,008
Use your own numbers

Where to run it

6 hosts serve Muse Glimmer 30B. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
muse-glimmer-30b
$0.20 / $0.80
−33% vs headline
DeepInfraInference
Muse-Glimmer-30B
$0.30 / $1.20
Together AIInference
Muse-Glimmer-30B
$0.35 / $1.50
+21% vs headline
Fireworks AIInference
muse-glimmer-30b
$0.35 / $1.50
+21% vs headline
muse-glimmer-30b
$0.455 / $1.82
+52% vs headline
NVIDIA NIMInference
muse-glimmer-30b
-
Show 1 more listings: regions, snapshots and variants
Fireworks AI
Alias
muse-glimmer-30b
$0.35 / $1.50
+21% vs headline

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
Features
Prompt caching
Open weights
License: Apache-2.0
Runs in about 71.5 GB of GPU memory

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

  • EmpirioLabs AI
    muse-glimmer-30b
    $0.20 / $0.80
    33% less

Smaller Meta models

Other frontier labs

  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    12% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    62% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    62% less
  • GPT-4o Mini
    OpenAI · on OpenAI
    $0.15 / $0.60
    Lacks reasoning
    50% less

Open-weight picks

  • Qwen3.7 Plus
    Alibaba Qwen · on Replicate
    $0.276 / $1.10
    Has every key capability
    8% less
  • MiMo V2.6 Pro
    Xiaomi · on GMI Cloud
    $0.348 / $0.696
    Has every key capability
    17% less
  • Deepseekv4.1 Flash
    DeepSeek · on Sarvam
    $0.149 / $0.585
    Has every key capability
    51% less
  • Nemotron 3.5 Super VL
    NVIDIA · on Kyma API
    $0.081 / $0.472
    Has every key capability
    66% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Muse-Glimmer-30B",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Muse Glimmer 30B cost?

On DeepInfra, Muse Glimmer 30B costs $0.30 per million input tokens and $1.20 per million output tokens. Cached input costs $0.04 per million tokens. The cheapest host is EmpirioLabs AI, at $0.20 per million input tokens and $0.80 per million output tokens.

Which APIs offer Muse Glimmer 30B?

Muse Glimmer 30B runs on 6 APIs: EmpirioLabs AI, DeepInfra, Together AI, Fireworks AI, Kyma API and NVIDIA NIM.

What is Muse Glimmer 30B's context window?

131K tokens, with up to 131K tokens in one reply.

Is Muse Glimmer 30B being retired?

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

What are cheaper alternatives to Muse Glimmer 30B?

Models that cost less and keep most of what it can do: Muse Spark 1.3 Contributor on Meta Model API (76% less), GPT-5.4 Nano on OpenAI (12% less), Claude Haiku 5.5 on Anthropic (62% less) and Qwen3.7 Plus on Replicate (8% less). Muse Glimmer 30B itself costs 33% less on EmpirioLabs AI. Savings are on a mix of 3 input tokens to 1 output token.

When was Muse Glimmer 30B released?

Meta released it on 9 Aug 2026.

What is Muse Glimmer 30B's API model id?

Use Muse-Glimmer-30B with DeepInfra. Other hosts use their own ids: muse-glimmer-30b on EmpirioLabs AI, muse-glimmer-30b on Fireworks AI, muse-glimmer-30b on Kyma API, muse-glimmer-30b on NVIDIA NIM.

Sources

Raw catalog entry for Muse-Glimmer-30B on DeepInfra
{
  "max_output_tokens": 131072,
  "max_input_tokens": 131072,
  "input_cost_per_token": 3e-7,
  "output_cost_per_token": 0.0000012,
  "cache_read_input_token_cost": 4e-8,
  "supports_prompt_caching": true,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_function_calling": true,
  "supports_tool_choice": true,
  "supports_response_schema": true,
  "supports_reasoning": true,
  "supports_vision": true,
  "source": "https://deepinfra.com/pricing"
}