U

Unknown

18 个模型

当前繁忙

这些模型的所有供应商都已达到请求上限。限制解除后会自动恢复。

UUnknown
繁忙免费
solar-mini4:free

Efficient model for low-latency assistance, extraction, and routine automation

推理工具缓存
52.4万
UUnknown
繁忙免费
hy-3d-component:free

Decomposes a 3D mesh into functional parts, the P3-SAM and X-Part stage of Tencent Hunyuan3D Studio.

UUnknown
繁忙免费
hy-3d-format:free

Exports a generated 3D asset for a target game engine, the packaging stage of Tencent Hunyuan3D Studio.

UUnknown
繁忙免费
hy-3d-retopology:free

Retopologizes a high fidelity mesh into game ready polygons, the PolyGen stage of Tencent Hunyuan3D Studio.

UUnknown
繁忙免费
hy-3d-rigging:free

Infers joints and bone hierarchy to auto rig a mesh for animation, part of Tencent Hunyuan3D Studio.

UUnknown
繁忙免费
hy-3d-uv:free

Unwraps a mesh UV layout with material grouped seam placement, the SeamGPT stage of Tencent Hunyuan3D Studio.

UUnknown
繁忙免费
hy-3d-texture:free

Generates physically based texture maps for a 3D mesh, Tencent Hunyuan3D-Paint-v2-1 from the Hunyuan3D-2.1 release.

UUnknown
繁忙免费
clef-flash:free

Clef-flash is the fast 9B member of Cloudflare's open-source Clef decision model family, a fine-tune of Qwen3.5-9B served on Workers AI. It turns a state (text or structured JSON) plus a schema of...

视觉
6.6万
UUnknown
繁忙免费
compassjudger-1-32b-instruct:free
UUnknown
繁忙免费
deep-research-max-preview-04-2026:free

Maximum-comprehensiveness agentic researcher for multi-step investigation, synthesis, and cited reports

推理工具视觉
13.1万
UUnknown
繁忙免费
deep-research-preview-04-2026:free

Agentic model for autonomous multi-step research, synthesis, and cited reports

推理工具视觉
13.1万
UUnknown
繁忙免费
deep-research-pro-preview-12-2025:free
视觉缓存
6.6万
UUnknown
繁忙免费
embed-v5.0-fast:free
12.8万
UUnknown
繁忙免费
embed-v5.0-pro:free
12.8万
UUnknown
繁忙免费
flint-v1.0:free

Flint is an open-weight mixture-of-experts model from Recursive, with about 2.5B active parameters out of 40B total, built by Recursive's autoresearch system Eureka Machine for coding agents. It is...

UUnknown
繁忙免费
mammoth-1:free

Mammoth 1 is a 27B decision model from Base Labs, Baseten's research team, built on Qwen3.5-27B. Given a state (text or JSON) and typed questions (yes/no, multiple choice, or ordinal score), it...

UUnknown
繁忙免费
morph-dsv41flash:free

DeepSeek V4.1 Flash model for reasoning and agentic coding

推理工具视觉缓存
100万
UUnknown
繁忙免费
phonellm-mini-alpha-2:free