Serverless Inference

Nemotron 3.5 Lightning is an MoE model built for fast, reliable agentic tasks across use cases such as financial service

DeepSeek V4-Flash-0731 is an MoE model great for coding, reasoning, and agentic workloads.

GLM-5.2 is an MoE language model featuring 40 billion activated parameters and a total of 744 billion parameters

MiniMax M3 is a multimodal MoE model with 23B active parameters optimized for coding and agentic workflows.

A 1T-parameter MoE model with 32B active parameters built for long-horizon agentic coding and software engineering

A powerful MoE model designed for long-running agents across coding, deep research, and enterprise automation.

Mellum2-12B-A2.5B-Instruct is a fast MoE model with 131K context built for coding, tool use, and low-latency AI workflow

‍

Granite 4.1 8B is a long-context instruct model capable of enhanced tool calling, instruction following, and chat

‍

DeepSeek V4-Pro is a 1.6T-parameter MoE model with 49B active parameters excelling at advanced reasoning and coding

‍

DeepSeek V4-Flash is an MoE model with 1M context length great for coding, reasoning, and agentic workloads.

Qwen3.6-27B is a 27B dense multimodal model with 262K context built for flagship-level agentic coding.

Kimi K2.6 is a multimodal Mixture-of-Experts language model featuring 32 billion activated parameters

Gemma 4 31B Dense is designed for advanced reasoning, agentic workflows, and longer context and is natively trained on 1

Qwen3.6-35B-A3B is an MoE multimodal model with 262K context optimized for agentic coding workflows.

Qwen3.5-27B is a dense model from the Qwen3.5 family built for high performance across a large range of benchmarks.

Qwen3.5-35B-A3B is an open-weights multimodal MoE model built for efficient, high-throughput inference across chat, reasoning, and agentic tasks.

Multimodal MoE language model featuring 32 billion activated parameters and a total of 1 trillion parameters

A large hybrid model that supports both thinking and non-thinking modes via prompt templates.

Lower latency Mixture-of-Experts model trained on OpenAI’s Harmony response format with reasoning capabilities.

Efficient Mixture-of-Experts model designed for high-reasoning, agentic and general-purpose use cases.

A 30.5B MoE instruction-tuned model with enhanced reasoning, coding, and long-context understanding

Efficient multilingual, Mixture-of-Experts, instruction-tuned model, optimized for logical reasoning.

High-performance Mixture-of-Experts model optimized for structured reasoning, math, and long-form generation.

An efficient multilingual, dense, instruction-tuned model, optimized by OpenPipe for building agents with finetuning.

Multilingual model excelling in conversational tasks, detailed instruction-following, and coding.

Efficient conversational model optimized for responsive multilingual chatbot interactions.

Efficient conversational model optimized for responsive multilingual chatbot interactions.