AI models

Jev is TypeSafe AI's hosted System One model for making typed decisions inside software. Give it text or structured text state and narrow Choice, Score or Noul questions; it returns probabilities for routing, classification and scoring. It does not generate prose or code and cannot replace a chat or coding-agent LLM. The documented Jev 1.13 version is available through TypeSafe's API in early access. Start with a decision in your own workflow and keep the final action in your application code.

Cloud · Paid

Ornith-1.5-35B-A3B is an open-weight reasoning model for coding, repository work and agents that call tools. Its Qwen3.5-family mixture-of-experts architecture contains about 35 billion parameters but activates roughly 3 billion per token. Ornith describes training that jointly improves task generation, agent scaffolds and solutions through reinforcement learning. The published context window is 262,144 tokens. It is a candidate for developers who want to run a coding assistant on their own infrastructure: the official card documents vLLM and SGLang servers with OpenAI-compatible APIs, plus GGUF use through Ollama or llama.cpp. Start with a small repository task and check the result against your tests before expanding its role.

Self-hosted · Free

Qwen3.6 (35B-A3B)

Run an open mixture-of-experts model with coding and multilingual capabilities.

Self-hosted · Free

Phi-4-mini

Run a compact local model for summaries, drafts, classification, and simple code.

Self-hosted · Free

gpt-oss-20b

Run an open-weight model locally for private tool-use tasks.

Self-hosted · Free

Gemini 3.1 Pro

Analyze large documents, media files, and whole code repositories.

Cloud · Paid

Gemini 3.1 Flash-Lite

Process text, images, video, audio, and PDFs in bulk.

Cloud · Paid