Author's Description
Caller Large is Arcee's specialist "function‑calling" SLM built to orchestrate external tools and APIs. Instead of maximizing next‑token accuracy, training focuses on structured JSON outputs, parameter extraction and multi‑step tool chains, making Caller a natural choice for retrieval‑augmented generation, robotic process automation or data‑pull chatbots. It incorporates a routing head that decides when (and how) to invoke a tool versus answering directly, reducing hallucinated calls. The model is already the backbone of Arcee Conductor's auto‑tool mode, where it parses user intent, emits clean function signatures and hands control back once the tool response is ready. Developers thus gain an OpenAI‑style function‑calling UX without handing requests to a frontier‑scale model.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
Arcee AI's Caller Large, created on May 5, 2025, is an SLM specifically designed for function-calling and tool orchestration, prioritizing structured JSON outputs and multi-step tool chains over next-token accuracy. This model performs among the fastest models, typically ranking in the top tier for speed (76th percentile), and offers competitive pricing (51st percentile). Its reliability is exceptional, demonstrating minimal technical failures and ranking in the 96th percentile. While its core strength lies in tool invocation, its general benchmark performance reveals a mixed profile. Caller Large exhibits strong performance in Ethics (97.0% accuracy) and General Knowledge (90.5% accuracy), though its percentile rankings in these areas are moderate (36th and 35th respectively), suggesting a broad but not top-tier general understanding. Its Instruction Following (53.1% accuracy, 59th percentile) and Reasoning (68.0% accuracy, 63rd percentile) capabilities are solid. However, it shows notable weaknesses in Coding (60.0% accuracy, 29th percentile) and particularly in Email Classification (87.0% accuracy, but only 12th percentile), indicating that while it can achieve high accuracy in some classification tasks, its relative performance against other models in this domain is low. Its speed is particularly impressive in Email Classification, completing tasks very quickly (98th percentile for duration).
Model Pricing
Current Pricing
Feature | Price (per 1M tokens) |
---|---|
Prompt | $0.55 |
Completion | $0.85 |
Price History
Available Endpoints
Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
---|---|---|---|---|
Together
|
Together | arcee-ai/caller-large | 32K | $0.55 / 1M tokens | $0.85 / 1M tokens |
Benchmark Results
Benchmark | Category | Reasoning | Free | Executions | Accuracy | Cost | Duration |
---|
Other Models by arcee-ai
|
Released | Params | Context |
|
Speed | Ability | Cost |
---|---|---|---|---|---|---|---|
Arcee AI: Spotlight | May 05, 2025 | ~7B | 131K |
Text input
Image input
Text output
|
★★★★★ | ★★★ | $$$ |
Arcee AI: Maestro Reasoning | May 05, 2025 | ~32B | 131K |
Text input
Text output
|
★★ | ★★★★ | $$$$$ |
Arcee AI: Virtuoso Large | May 05, 2025 | ~72B | 131K |
Text input
Text output
|
★★★★★ | ★★★★ | $$$$ |
Arcee AI: Coder Large | May 05, 2025 | ~32B | 32K |
Text input
Text output
|
★★★★★ | ★★★★ | $$$ |
Arcee AI: Virtuoso Medium V2 Unavailable | May 05, 2025 | ~32B | 131K |
Text input
Text output
|
★★★★★ | ★★★★ | $$$ |
Arcee AI: Arcee Blitz Unavailable | May 05, 2025 | ~24B | 32K |
Text input
Text output
|
★★★★ | ★★★★ | $$$ |