meta-models/Muse-Glimmer-30B
Text LLMmeta-models/Muse-Glimmer-30BA 30B text model for responsive chat and assistant workflows.
Muse Glimmer 30B is available for text generation through AIGrid's OpenAI-compatible chat endpoint. Use the deployment id exactly as shown when integrating raw HTTP clients or agent frameworks.
Best for
Chat workflows
Mode
Text LLM
Reasoning
Standard reasoning
Tools / coding
Tools
Throughput
No throughput info
Model pricing
Token prices are shown in Algerian dinars per one million tokens.
Input price
73 DA / 1M tokens
Output price
148 DA / 1M tokens
At a glance
- Modalities: Text
- Designed for chat and assistant workloads
- Works with OpenAI-compatible SDKs
- Use the exact case-sensitive model id
Integration examples
These snippets are adapted for this model's API mode: Chat completions. The model field is set to meta-models/Muse-Glimmer-30B. If your deployment uses an alias, mirror that value when you paste into your app. For general concepts, see the main documentation hub.
Keys and base URL
YOUR_API_KEY with the key from Models after you sign in. This page's snippets use https://app.ai-grid.io when you are signed in (see DOCS_AUTHENTICATED_API_BASE_URL). Otherwise they keep the placeholder host for sovereign-safe documentation.Send a chat completion
Chat completions
/v1/chat/completionscurl https://app.ai-grid.io/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer YOUR_API_KEY" \
-d '{
"model": "meta-models/Muse-Glimmer-30B",
"messages": [
{ "role": "user", "content": "Hello from AIGrid!" }
]
}'Other models
Qwen · Text LLM
Qwen/Qwen3.8-27B
General assistants
Qwen/Qwen3.8-27B
Efficient 27B text generation for assistants, analysis, and code.
Throughput
No throughput info
Input
73 DA / 1M tokens
Output
148 DA / 1M tokens
- Balanced default for assistants and code
- OpenAI-compatible `/v1/chat/completions`
- Use the exact case-sensitive model id
Qwen · Text LLM
Qwen3-30B-A3B-Thinking
Reasoning
Qwen3-30B-A3B-Thinking
Reasoning-forward 30B tier for planning and analysis.
Throughput
660 tokens/sec
Input
73 DA / 1M tokens
Output
148 DA / 1M tokens
- Extended thinking style outputs
- Ideal for LangGraph flows
- Tune system prompts for chain-of-thought depth
Google · Text LLM
google/gemma-4-31B
High-volume chat
google/gemma-4-31B
Fast 31B text generation for assistants and RAG answers.
Throughput
580 tokens/sec
Input
73 DA / 1M tokens
Output
148 DA / 1M tokens
- Great for high-volume chat
- Pairs with LangChain ChatOpenAI
- Stable for LlamaIndex completion nodes
Alibaba · Embedding
Alibaba-NLP/gte-Qwen2-7B-instruct
Embeddings
Alibaba-NLP/gte-Qwen2-7B-instruct
Dense text encoder for semantic search and clustering.
Throughput
No throughput info
Input
Free
Output
Free
- Vector / similarity workflows
- LlamaIndex Settings helper
- Keep API id in sync with the model catalog
Zhipu / Z.ai · OCR
zai-org/GLM-OCR
PDF OCR
zai-org/GLM-OCR
Document and image OCR with multimodal chat messages.
Throughput
1.96 pages PDF/sec
Input
8 DA / 1M tokens
Output
8 DA / 1M tokens
- Vision + OCR style prompts
- Great for ingestion pipelines
- Resize images for latency
DeepSeek · OCR
DeepSeek-OCR
Image OCR
deepseek-ocr
OCR-focused multimodal stack for documents.
Throughput
860 tokens/sec
Input
8 DA / 1M tokens
Output
8 DA / 1M tokens
- Multimodal messages for scans
- Works with guarded BFF patterns
- Batch pages for throughput