Patch Update - 14.23

🚀 Platform Update: Major Model Expansion & Service Enhancements

We are excited to announce a significant update, featuring a massive expansion of our model library and key improvements to platform stability and performance.

🧠 New Model Integrations: Provider 1

The following state-of-the-art models have been successfully integrated and are now available for use. They have been grouped by developer for your convenience.

DeepSeek-AI:

• deepseek-ai/DeepSeek-V3.1-turbo
• deepseek-ai/DeepSeek-V3-0324-turbo
• deepseek-ai/DeepSeek-V3.1-Terminus
• deepseek-ai/DeepSeek-R1-Distill-Qwen-14B
• deepseek-ai/DeepSeek-R1-Distill-Qwen-7B
• deepseek-ai/DeepSeek-R1-Distill-Qwen-1.5B
• deepseek-ai/DeepSeek-R1-Distill-Llama-8B
• deepseek-ai/DeepSeek-R1-Distill-Qwen-32B

Meta-Llama:

• meta-llama/Llama-3.1-8B-Instruct
• meta-llama/llama-3.1-8b-instruct/fp-16
• meta-llama/llama-3.2-1b-instruct/fp-16
• meta-llama/llama-3.2-3b-instruct/fp-16
• meta-llama/llama-3.2-11b-instruct/fp-16

Qwen / Alibaba:

• qwen/qwen2.5-7b-instruct/bf-16
• Qwen/Qwen2.5-72B-Instruct
• Alibaba-NLP/Tongyi-DeepResearch-30B-A3B
• Qwen/Qwen2.5-Coder-32B-Instruct
• Qwen/Qwen2.5-Coder-3B-Instruct
• Qwen/Qwen2.5-Coder-7B-Instruct
• Qwen/Qwen2.5-VL-72B-Instruct
• Qwen/Qwen3-8B
• Qwen/Qwen3-32B
• Qwen/Qwen3-4B-Thinking-2507
• Qwen/Qwen3-Next-80B-A3B-Thinking
• Qwen/Qwen3-235B-A22B-Instruct-2507
• Qwen/Qwen3-235B-A22B-Thinking-2507
• Qwen/Qwen3-235B-A22B-Thinking-2507-FP8

MistralAI & Associates:

• chutesai/Mistral-Small-3.2-24B-Instruct-2506
• mistralai/mistral-nemo-12b-instruct/fp-8
• mistralai/mixtral-8x22b-instruct-v0.1
• mistralai/Devstral-Small-2505
• cognitivecomputations/Dolphin3.0-Mistral-24B

NousResearch:

• NousResearch/Hermes-4-14B
• NousResearch/DeepHermes-3-Mistral-24B-Preview
• NousResearch/DeepHermes-3-Llama-3-8B-Preview
• NousResearch/Hermes-4-70B
• NousResearch/Hermes-4-405B-FP8

Unsloth:

• unsloth/gemma-3-4b-it
• unsloth/gemma-3-12b-it
• unsloth/gemma-3-27b-it
• unsloth/gemma-2-9b-it
• unsloth/Mistral-Small-24B-Instruct-2501
• unsloth/Llama-3.2-3B-Instruct
• unsloth/Mistral-Nemo-Instruct-2407

Google Gemma:

• google/gemma-3-27b-instruct/bf-16

Zhipu AI (GLM):

• zai-org/GLM-4-32B-0414
• zai-org/GLM-4.5-turbo
• zai-org/GLM-4.5V
• zai-org/GLM-4.5-Air
• zai-org/GLM-Z1-32B-0414

Other Notable Additions:

• agentica-org/DeepCoder-14B-Preview
• meituan-longcat/LongCat-Flash-Chat-FP8
• meituan-longcat/LongCat-Flash-Thinking-FP8
• ByteDance-Seed/Seed-OSS-36B-Instruct
• moonshotai/Kimi-K2-Instruct
• moonshotai/Kimi-VL-A3B-Thinking
• OpenGVLab/InternVL3-78B
• microsoft/MAI-DS-R1-FP8
• TheDrummer/Tunguska-39B-v1
• TheDrummer/Skyfall-36B-v2
• TheDrummer/Gemmasutra-Pro-27B-v1.1
• tngtech/DeepSeek-R1T-Chimera
• tngtech/DeepSeek-TNG-R1T2-Chimera
• shisa-ai/shisa-v2-llama3.3-70b
• tencent/Hunyuan-A13B-Instruct
• ArliAI/QwQ-32B-ArliAI-RpR-v1
• openai/gpt-oss-20b

✅ Platform Enhancements & Stability Updates

Alongside new models, we have deployed several key improvements to the service:

• Provider Efficiency: Performance and resource management have been optimized for Provider 2 and Provider 7.
• Enhanced Streaming Performance: We've deployed improvements to ensure faster and more reliable streaming output from models.
• Increased VPS Limits: The resource limits for our virtual private servers have been raised, leading to greater stability and reliability, especially for model editing tasks.