Inworld has acquired Ultravox to accelerate its speech-to-speech research and voice agent capabilities.Read the announcement

Inworld has acquired UltravoxRead announcement →

Get started

Muse Glimmer 30B

Name: Muse Glimmer 30B
Brand: Meta
Price: 0.3 USD
Availability: InStock

Muse Glimmer 30B is a reasoning model by Meta with function calling, structured output — designed for complex, multi-step problem solving where accuracy matters more than speed. It supports a 131K token context window with up to 16K tokens of output. Priced at $0.3 per million input tokens and $1.2 per million output tokens, it is one of the most cost-efficient options in its class. Access Muse Glimmer 30B through Inworld Router with OpenAI SDK compatibility, built-in failover, and intelligent routing across providers.

→Function CallingReasoningResponse SchemareasoningCapabilityresponseFormatCapability

Use This Model

Step 1 — Create Router

curl --location 'https://api.inworld.ai/router/v1/routers' \
--header 'Authorization: Basic <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
  "name": "compare-frontier-models",
  "defaultRoute": {
    "route_id": "default",
    "variants": [
      {
        "variant": {
          "variant_id": "deepinfra/meta-models/Muse-Glimmer-30B-a",
          "model_id": "deepinfra/meta-models/Muse-Glimmer-30B"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "meta/muse-spark-1.3-contributor-b",
          "model_id": "meta/muse-spark-1.3-contributor"
        },
        "weight": 33
      },
      {
        "variant": {
          "variant_id": "meta/muse-spark-1.3-c",
          "model_id": "meta/muse-spark-1.3"
        },
        "weight": 34
      }
    ]
  }
}'

import requests

response = requests.post(
    "https://api.inworld.ai/router/v1/routers",
    headers={
        "Authorization": "Basic <your-api-key>",
        "Content-Type": "application/json",
    },
    json={
        "name": "compare-frontier-models",
        "defaultRoute": {
            "route_id": "default",
            "variants": [
                {
                    "variant": {
                        "variant_id": "deepinfra/meta-models/Muse-Glimmer-30B-a",
                        "model_id": "deepinfra/meta-models/Muse-Glimmer-30B"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "meta/muse-spark-1.3-contributor-b",
                        "model_id": "meta/muse-spark-1.3-contributor"
                    },
                    "weight": 33
                },
                {
                    "variant": {
                        "variant_id": "meta/muse-spark-1.3-c",
                        "model_id": "meta/muse-spark-1.3"
                    },
                    "weight": 34
                }
            ]
        }
    },
)
print(response.json())

const response = await fetch(
  "https://api.inworld.ai/router/v1/routers",
  {
    method: "POST",
    headers: {
      Authorization: "Basic <your-api-key>",
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      name: "compare-frontier-models",
      defaultRoute: {
        route_id: "default",
        variants: [
          {
            variant: {
              variant_id: "deepinfra/meta-models/Muse-Glimmer-30B-a",
              model_id: "deepinfra/meta-models/Muse-Glimmer-30B",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "meta/muse-spark-1.3-contributor-b",
              model_id: "meta/muse-spark-1.3-contributor",
            },
            weight: 33,
          },
          {
            variant: {
              variant_id: "meta/muse-spark-1.3-c",
              model_id: "meta/muse-spark-1.3",
            },
            weight: 34,
          },
        ],
      },
    }),
  }
);
const data = await response.json();
console.log(data);

Step 2 — Chat Completion

curl --location 'https://api.inworld.ai/v1/chat/completions' \
--header 'Authorization: Basic <your-api-key>' \
--header 'Content-Type: application/json' \
--data '{
  "model": "inworld/compare-frontier-models",
  "messages": [{"role": "user", "content": "Hello!"}]
}'

Muse Glimmer 30B pricing and providers

Access Muse Glimmer 30B through DeepInfra via Inworld Router or Realtime API. By using the AI provider(s) below you acknowledge you reviewed and agree to their terms listed in the Legal section under the AI provider's name.

							Capabilities	Input modalities	Output modalities
DeepInfra	$0.30	$1.20	$0.04	—	131.1K	16.4K	+2

Prices in USD per 1M tokens.

Other Meta models available through Inworld

Compare Muse Glimmer 30B with other Meta models available through Inworld Router or Realtime API.

							Capabilities
Muse Spark 1.3 Contributor	$0.10	$0.20	$0.002	—	1M	943.7K	+4
Muse Spark 1.3	$1.25	$4.25	$0.15	—	1M	943.7K	+4
Llama 3.3 70B Instruct Turbo	$0.10	$0.32	—	—	131.1K	131.1K
Meta Llama 3.1 8B Instruct Turbo	$0.02	$0.04	—	—	131.1K	131.1K