Gorilla OpenFunctions v2 vs Functionary Medium v2.2
Compare the listed model data for Gorilla OpenFunctions v2 by gorilla-llm and Functionary Medium v2.2 by meetkai. Benchmark and pricing records are not a controlled test and may change.
Data last updated: 2026-10-16. Verify current model details with each provider.
What the listed data says
Gorilla OpenFunctions v2: 4K tokens; Functionary Medium v2.2: 8K tokens. Functionary Medium v2.2 has the larger listed context window. Gorilla OpenFunctions v2 is listed for no specific capability flags; Functionary Medium v2.2 is listed for no specific capability flags. Shared catalog benchmark entries: BFCL Overall: Gorilla OpenFunctions v2 88.5%; Functionary Medium v2.2 83.2%. These records are reference data, not a controlled head-to-head test; verify current pricing and specifications with each provider.
Catalog source links
Use these model and provider links to verify current specifications, pricing, and availability.
Computed differences from catalog data
- The listed context windows are 4K tokens and 8K tokens; the larger is 2× the smaller.
- On shared numeric benchmark entries, BFCL Overall: Gorilla OpenFunctions v2 − Functionary Medium v2.2 = +5.3 percentage points (88.5% vs 83.2%).
- The first listed parameter quantities are 7B and 7B; the larger quantity is 1× the smaller. Total and active MoE parameters are not directly equivalent.
- A release-date gap cannot be calculated from the catalog values (Gorilla OpenFunctions v2: 2024; Functionary Medium v2.2: 2024).
Cost example: 1M input and 1M output tokens
A cost example for 1M input plus 1M output tokens cannot be calculated reliably because separate numeric input and output rates are not listed for both models.
Choose Gorilla OpenFunctions v2 if…
Choose Gorilla OpenFunctions v2 when your task aligns with catalog-listed uses or strengths such as Function calling in agentic frameworks, Building agents that interact with documented APIs, State-of-the-art function calling at release — trained on API documentation, Understands real-world APIs: Python, Java, JavaScript, REST.
Choose Functionary Medium v2.2 if…
Choose Functionary Medium v2.2 when your task aligns with catalog-listed uses or strengths such as Production AI agent frameworks, Multi-tool orchestration, Structured workflow automation, Production-grade function calling — deployed in commercial products.
Gorilla OpenFunctions v2
Berkeley Gorilla OpenFunctions v2 — purpose-built for accurate API function calling and tool use, rivaling GPT-4 on the Berkeley Function-Calling leaderboard.
Parameters: 7B
Context: 4K tokens
Catalog pricing: Apache 2.0 — free
Functionary Medium v2.2
MeetKai Functionary — chat model fine-tuned to reliably emit function-call JSON. Great for tool-using agents and structured output.
Parameters: 7B
Context: 8K tokens
Catalog pricing: MIT — free
Feature Comparison — Gorilla OpenFunctions v2 vs Functionary Medium v2.2
| Specification | Gorilla OpenFunctions v2 | Functionary Medium v2.2 |
|---|---|---|
| Provider | gorilla-llm | meetkai |
| Parameters | 7B | 7B |
| Context window | 4K tokens | 8K tokens |
| Maximum output | Not listed | Not listed |
| Catalog pricing | Apache 2.0 — free | MIT — free |
| Listed input/output cost per 1M tokens | Separate numeric input/output rates not listed | Separate numeric input/output rates not listed |
| License | Apache 2.0 | MIT |
| Coding support | Not listed | Not listed |
| Reasoning support | Not listed | Not listed |
| Vision input | Not listed | Not listed |
| Multimodal | Not listed | Not listed |
| Open weights | Yes | Yes |
| Benchmark: BFCL Overall | 88.5% | 83.2% |
Figures are transcribed from LITHOVEX model records. Benchmark versions and evaluation setups may differ; pricing and specifications can change. Check each provider's current documentation before making a decision.
Frequently Asked Questions
What is different between Gorilla OpenFunctions v2 and Functionary Medium v2.2?
What benchmark values are listed for Gorilla OpenFunctions v2 and Functionary Medium v2.2?
Which model has the larger listed context window?
What are the listed costs per million tokens for Gorilla OpenFunctions v2 and Functionary Medium v2.2?
How far apart are the listed release dates for Gorilla OpenFunctions v2 and Functionary Medium v2.2?
When was the comparison data last updated?
How should I choose between Gorilla OpenFunctions v2 and Functionary Medium v2.2?
Explore these models and related comparisons
Read the Gorilla OpenFunctions v2 model profile and Functionary Medium v2.2 model profile, or browse the model directory.