Models

17 of 245 models

• 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.

  Runs on Ollama’s cloudCloud Medium usage $0.30 in · $1.20 out per 1M tokens$$$$

  1M contextToolsThinkingVision

• 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.

  Runs on Ollama’s cloudCloud High usage $1.40 in · $4.40 out per 1M tokens$$$$

  1M contextToolsThinking

• 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.

  Runs on Ollama’s cloudCloud Medium usage $0.15 in · $0.50 out per 1M tokens$$$$

  1M contextToolsThinkingVision

• 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.

  Runs on Ollama’s cloudCloud High usage $0.68 in · $2.09 out per 1M tokens$$$$

  1M contextToolsThinkingVision

• minimax-m3

  MiniMax M3: Coding & Agentic Frontier. 1M context window. Native Multimodality.

  Runs on Ollama’s cloudCloud High usage $0.60 in · $2.40 out per 1M tokens$$$$

  500K contextToolsThinkingVision

• glm-5.2

  GLM-5.2 is Z.ai’s flagship model for the era of long-horizon tasks.

  Runs on Ollama’s cloudCloud High usage $1.40 in · $4.40 out per 1M tokens$$$$

  1M contextToolsThinking

• deepseek-v4-pro

  DeepSeek-V4-Pro is a frontier Mixture-of-Experts model with a large context window and three reasoning modes.

  Runs on Ollama’s cloudCloud Extra High usage $1.32 in · $3.96 out per 1M tokens$$$$

  1M contextToolsThinking

• kimi-k2.7-code

  Kimi K2.7 Code is Moonshot AI's coding-focused agentic model built upon Kimi K2.6, with substantial improvements on real-world long-horizon coding tasks and roughly 30% lower thinking-token usage.

  Runs on Ollama’s cloudCloud High usage $0.95 in · $4.00 out per 1M tokens$$$$

  256K contextToolsThinkingVision

• kimi-k3

  Kimi K3 is an open-weight, native multimodal agentic model and our most capable model to date.

  Runs on Ollama’s cloudCloud Extra High usage $3.00 in · $15.00 out per 1M tokens$$$$

  1M contextToolsThinkingVision

• nemotron-3-ultra

  NVIDIA Nemotron 3 Ultra is built for high-throughput reasoning and long-running agent workflows.

  Runs on Ollama’s cloudCloud High usage $0.10 in · $3.00 out per 1M tokens$$$$

  256K contextToolsThinking

• gemma4

  Gemma 4 models are designed to deliver frontier-level performance at each size. They are well-suited for reasoning, agentic workflows, coding, and multimodal understanding.

  Runs on your computere2b·e4b·12b·26b·31b Runs on Ollama’s cloudCloud Low usage $0.14 in · $0.40 out per 1M tokens$$$$

  256K contextToolsThinkingVisionAudio
  26.5M

• nemotron-3-super

  NVIDIA Nemotron 3 Super is a 120B open MoE model activating just 12B parameters to deliver maximum compute efficiency and accuracy for complex multi-agent applications.

  Runs on your computer120b Runs on Ollama’s cloudCloud Medium usage $0.015 in · $0.60 out per 1M tokens$$$$

  256K contextToolsThinking
  3M

• minimax-m2.7

  MiniMax's M2-series model for coding, agentic workflows, and professional productivity.

  Runs on Ollama’s cloudCloud Medium usage $0.30 in · $1.20 out per 1M tokens$$$$

  192K contextToolsThinking

• nemotron-3-nano

  Nemotron-3-Nano is a new Standard for Efficient, Open, and Intelligent Agentic Models, now updated with a 4B parameter count model.

  Runs on your computer4b·30b Runs on Ollama’s cloudCloud Low usage $0.06 in · $0.24 out per 1M tokens$$$$

  256K contextToolsThinking
  887.2K

• kimi-k2.6

  Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.

  Runs on Ollama’s cloudCloud High usage $0.95 in · $4.00 out per 1M tokens$$$$

  256K contextToolsThinkingVision

• mistral-large-3

  A general-purpose multimodal mixture-of-experts model for production-grade tasks and enterprise workloads.

  Runs on Ollama’s cloudCloud Medium usage $0.50 in · $1.50 out per 1M tokens$$$$

  256K contextToolsVision

• gpt-oss

  OpenAI’s open-weight models designed for powerful reasoning, agentic tasks, and versatile developer use cases.

  Runs on your computer20b·120b Runs on Ollama’s cloudCloud Low usage From $0.07 in · $0.30 out per 1M tokens$$$$

  128K contextToolsThinking
  13.6M