Ernie 5.0 Thinking Preview

ERNIE 5.1

ERNIE 5.1 is the latest Wenxin model, with broad upgrades to agentic workflows, knowledge, reasoning, and deep search. ⚠️ Note: privacy and logging guarantees may be limited.

ERNIE 5.1 Thinking

ERNIE 5.1 Thinking is the latest Wenxin model with explicit reasoning enabled for harder planning, coding, math, and agentic tasks. ⚠️ Note: privacy and logging guarantees may be limited.

ERNIE X1.1

The Wenxin large model X1.1 has made significant improvements in question answering, tool invocation, intelligent agents, instruction following, logical reasoning, mathematics, and coding tasks, with notable enhancements in factual accuracy. The context length has been extended to 64K tokens, supporting longer inputs and dialogue history, which improves the coherence of long-chain reasoning while maintaining response speed. ⚠️ Note: This model routes through Baidu (China) — privacy and logging guarantees may be limited.

Clef

Cloudflare's open decision model evaluates application state and answers typed Choice, Score and Noul questions. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It supports 16K tokens of text context and generates no text tokens; only input tokens are billed.

Sakana Namazu

Sakana AI's Japanese-specialized model, based on Kimi K2.6 and tuned for Japanese language, culture, and business contexts. Supports reasoning, image understanding, function calling, and structured output.

Liquid D1

Liquid AI's D1 evaluates application state and returns typed Choice, Score and yes/no answers with calibrated probabilities. Use /v1/decisions or /v1/systemone, or a questions response format through Chat Completions, Messages or Responses. It supports a 65,536-token context and generates no text tokens; only input tokens are billed.