Use Functionary Medium v2.2 for Free

Functionary Medium v2.2 is an AI model released 2024 by meetkai, a leading organization in large language model research. MeetKai Functionary — chat model fine-tuned to reliably emit function-call JSON. Great for tool-using agents and structured output. With 7B and a 8K tokens context window, Functionary Medium v2.2 is designed to excel across a range of demanding tasks — from software engineering and mathematical problem-solving to multilingual content generation and long-document analysis.

Functionary Medium v2.2 uses a dense transformer architecture with 7B of parameters, all of which are active for every input token. Dense architectures provide predictable, consistent behavior across diverse task types — there are no "cold" experts to warm up, and quality is uniform across prompts. meetkai's training pipeline combined large-scale pretraining on a large-scale multilingual pretraining dataset with supervised fine-tuning and alignment techniques (RLHF or DPO), producing Functionary Medium v2.2's characteristic balance of capability, helpfulness, and safety.

As of 2026-10-16, Functionary Medium v2.2 by meetkai demonstrates measurable performance on standard AI evaluation benchmarks. On BFCL Overall — which measures model performance on specialized evaluation tasks — it achieves 83.2%. These scores place Functionary Medium v2.2 — at 7B of parameters — in a competitive position within its model class. Note that benchmark scores reflect controlled evaluation conditions; real-world performance varies by task, prompt design, and domain specificity.

The primary strengths of Functionary Medium v2.2 are: Production-grade function calling — deployed in commercial products; Parallel tool calling: multiple API calls simultaneously; MIT license. These make it particularly well-suited for Production AI agent frameworks, Multi-tool orchestration, Structured workflow automation. Users working on complex, multi-step problems benefit most from Functionary Medium v2.2's ability to maintain coherence across long inputs and produce structured, verifiable outputs.

Like all current AI systems, Functionary Medium v2.2 has limitations: Specialized — less balanced for general conversation. For production deployments, validating outputs against authoritative sources — especially for domain-specific or time-sensitive information — remains best practice. meetkai continues to improve Functionary Medium v2.2 through ongoing research.

Functionary Medium v2.2 is available on LITHOVEX AI with a free account. Unlike direct API access — which requires billing setup, API key management, and per-token charges — LITHOVEX AI provides a seamless browser interface with no setup required, making Functionary Medium v2.2 accessible to students, researchers, developers, and early-stage teams globally.

As of 2026-10-16, Functionary Medium v2.2 by meetkai demonstrates measurable performance on standard AI evaluation benchmarks. On BFCL Overall — which measures model performance on specialized evaluation tasks — it achieves 83.2%. These scores place Functionary Medium v2.2 — at 7B of parameters — in a competitive position within its model class. Note that benchmark scores reflect controlled evaluation conditions; real-world performance varies by task, prompt design, and domain specificity.

Dense transformer, 7B, fine-tuned for function calling with parallel tool support

The training pipeline for Functionary Medium v2.2 involves multiple stages: large-scale pretraining on diverse multilingual text and code corpora to develop broad world knowledge, followed by supervised fine-tuning on instruction-response pairs, and alignment techniques such as RLHF or DPO. Each stage refines the model's helpfulness, accuracy, and safety. meetkai's research team — based in United States — has optimized Functionary Medium v2.2 for the specific capability profile described above.

Inference efficiency: Functionary Medium v2.2 at 7B is designed to deliver quality outputs at practical serving speeds. Its 8K tokens context window enables processing entire documents, multi-file codebases, and extended conversation histories — particularly valuable for contract review, technical documentation analysis, and codebase-level AI assistance.

Getting started with Functionary Medium v2.2 on LITHOVEX AI takes under two minutes. Follow these steps:

For best results with Functionary Medium v2.2: provide specific, context-rich prompts; include examples when generating code; specify output format when structure matters; break complex tasks into focused sub-questions.

meetkai is a leading organization in AI research and large language model development. Their team has built expertise across natural language processing, model architecture design, and alignment research. meetkai's models are used by researchers, developers, and enterprises worldwide. Their commitment to advancing AI capability while maintaining responsible deployment practices has made them a respected contributor to the global AI ecosystem. The organization continues to publish research and release models that push the boundaries of what AI systems can achieve.

Founded: 2021, headquartered in United States.

Visit the official meetkai website →

Functionary Medium v2.2 by meetkai competes in a field with several strong alternatives. Below is a detailed side-by-side comparison against commonly listed alternatives, using benchmark data and capability profiles in the catalog.

Both Functionary Medium v2.2 and the models above are available free on LITHOVEX AI — test them side by side on your real tasks before committing to a subscription with any provider.

Functionary Medium v2.2 is released under MIT, which means you can download and run it on your own hardware. Below are the quickest ways to get started.

Functionary is widely used globally in production agentic AI systems where reliable, parallelizable function calling is critical. Teams building AI copilots, workflow automation, and multi-tool AI agents across North America, Europe, and Asia rely on its consistent structured output.

Functionary Medium v2.2 by meetkai has the following version history and notable updates:

For the complete changelog and latest release notes, visit the official meetkai model page.