Ollama

deepseek-v4.1-flash

DeepSeek-V4.1-Flash is an advanced tool designed to enhance search capabilities, providing users with faster and more accurate results.

$$$$ 1M contextvisiontoolsthinking cloud

glm-5.3

Z.ai's flagship model and the most capable open-weights model for coding, with major gains on long-horizon agentic tasks.

$$$$ 1M contexttoolsthinking cloud

glm-5.3-flash

Z.ai's first natively multimodal model, approaching Claude Opus 4.8 on coding and agentic benchmarks with just 18B active parameters.

$$$$ 1M contextvisiontoolsthinking cloud

d1

d1 is a 3B decision model from Liquid AI, built on LFM2.5-VL-3B

vision 3b

11.5K

nimble-v3

A 9B decision model from Bespoke Labs for fast classification, routing, and scoring.

toolsdecisionthinking 9b

10.3K

kev

Kev scores answers to structured questions about a supplied text state in a single forward pass.

decision

2,258

pplx-decider

pplx-decider is a 27B decision model from Perplexity, fine-tuned from Qwen3.8-27B

vision 27b

756

muse-spark-open

Muse Spark Open is a natively multimodal model with 816B total parameters (42B active) and a 1M-token context window. Built for coding and agentic work, it excels at long-horizon tasks, complex software engineering, and multi-step reasoning.

$$$$ 1M contextvisiontoolsthinking cloud

tev1

A 4B decision model from Together AI for fast classification.

toolsdecisionthinking 0.8b 4b

94.7K

embeddinggemma-2

EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture.

visionembeddingaudio 270m 440m 570m 740m

48.3K

nimble

A 9B decision model from Bespoke Labs for fast, typed classification.

toolsdecisionthinking 9b

45.5K

clef-flash

Clef-Flash is a 9B multimodal model that turns a state and a schema of typed questions into decisions.

visiondecision 9b

23.8K

clef

Clef is a 27B multimodal model created by Cloudflare that turns a state and a schema of typed questions into decisions.

$$$$ 64K contextvisiondecision cloud 27b

16.6K

mistral-large-4

Mistral Large 4 is Mistral's open-weight, general-purpose multimodal model. Its granular Mixture-of-Experts design activates 52B of 1.05T total parameters, with a 1.6B vision encoder handling images.

$$$$ 1M contextvisiontoolsthinking cloud