GLM-5.2
TextChatReasoningCode
- Provider
- Zai-org
- Context
- 1M
- Parameters
- 744B MoE
Mixture-of-Experts model with 744B parameters (40B active).
Input
$1.40 / 1M tokens
Output
$4.40 / 1M tokens
model="glm-5-2"
MODEL CATALOG
Open AI Models, Ready to Run
OpenAI-compatible inference for the latest open models. Swap your base URL and go.
Browse 3 open-source models from 3 providers
Gemma-4-31B-it
MultimodalChatReasoning
- Provider
- Context
- 256K
- Parameters
- 31B
31 billion parameter dense multimodal model for deep reasoning.
Input
$0.12 / 1M tokens
Output
$0.38 / 1M tokens
model="gemma-4-31b-it"
Qwen3.6-27B
MultimodalChatReasoning
- Provider
- Qwen
- Context
- 262K
- Parameters
- 27B
27 billion parameter dense causal language model with a native vision encoder.
Input
$0.32 / 1M tokens
Output
$3.20 / 1M tokens
model="qwen3-6-27b"
Early Access
Be first in line.
Sign up for early API access. Don't see a model you need? Request it and we'll prioritize based on demand.
Frequently Asked Questions
Everything you need to know about the Hoonify AI model catalog and API.