Models

0G.AI in-house model optimized for agentic coding and tool use; thinking enabled by default.

0gm-1.0-35b-a3b

by 0G Foundation

Lightweight MoE (284B total / 13B active) with native 1M context; low-latency, low-cost.

deepseek-v4-flash

by 0G Foundation

DeepSeek flagship for agentic coding, multi-step workflows, and complex reasoning; 1M context, up to 384K output.

deepseek-v4-pro

by 0G Foundation

671B mixture-of-experts model with hybrid thinking; strong at coding, math, and multi-step reasoning.

deepseek-v3

by 0G Foundation

Next-generation model purpose-built for coding and agent workflows; 744B foundation.

glm-5

by 0G Foundation

Zhipu AI flagship purpose-built for long-horizon tasks; 744B foundation, 200K context.

glm-5.1

by 0G Foundation

Multilingual automatic speech recognition (ASR); transcription and translation.

whisper-large-v3

by 0G Foundation

Alibaba multimodal vision-language model; strong at visual reasoning, OCR, and document understanding.

qwen3-vl-30b

by 0G Foundation

Alibaba flagship with hybrid linear attention and sparse MoE; 1M context, 119 languages.

qwen3.6-plus

by 0G Foundation

Alibaba flagship with native function calling and web search; 1M context.

qwen3.7-max

by 0G Foundation

Asynchronous text-to-image model with Base64 output.

z-image

by 0G Foundation