94Fit score
Tongyi DeepResearch is an agentic large language model developed by Tongyi Lab, with 30 billion total parameters activating only 3 billion per token. It's optimized for long-horizon, deep information-seeking tasks and de…
Model details →Best AI models for function calling
Tool-use models can call external functions, retrieve data, and chain steps. Most also support structured outputs for reliable JSON.
94Fit score
Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and...
Model details →94Fit score
Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, code, and tools to produce verifiable results,...
Model details →Top 25 models for tool use
| # | Model | Provider | Context | Input price / 1M | Tier |
|---|---|---|---|---|---|
| 1 | Tongyi DeepResearch 30B A3B | Alibaba | 131K Long context (128K+) | $0.09 | Budget |
| 2 | Anthropic: Claude Haiku 5.5 (batch) | Anthropic | 1M Ultra context (1M+) | $0.05 | Budget |
| 3 | Apodex: Apodex 1.1 Mini (free) | Apodex | 262K Long context (128K+) | $0.00 | Budget |
| 4 | Arcee AI: Trinity Mini | Arcee Ai | 131K Long context (128K+) | $0.04 | Budget |
| 5 | Arcee AI: Trinity Mini (free) | Arcee Ai | 131K Long context (128K+) | $0.00 | Budget |
| 6 | ByteDance Seed: Seed 1.6 Flash | Bytedance Seed | 262K Long context (128K+) | $0.07 | Budget |
| 7 | DeepSeek: DeepSeek V4 Flash 0423 | DeepSeek | 1.0M Ultra context (1M+) | $0.09 | Budget |
| 8 | DeepSeek: DeepSeek V4 Flash 0731 | DeepSeek | 1.0M Ultra context (1M+) | $0.02 | Budget |
| 9 | DeepSeek: DeepSeek V4 Flash 0731 (free) | DeepSeek | 1.0M Ultra context (1M+) | $0.00 | Budget |
| 10 | DeepSeek: DeepSeek V4.1 Flash | DeepSeek | 1.0M Ultra context (1M+) | $0.04 | Budget |
| 11 | Dots Studio: Dots3-Note Preview (free) | Dots Studio | 512K Long context (128K+) | $0.00 | Budget |
| 12 | Google: Gemini 2.0 Flash Lite | 1.0M Ultra context (1M+) | $0.07 | Budget | |
| 13 | Google: Gemini 2.5 Flash Lite (batch) | 1.0M Ultra context (1M+) | $0.05 | Budget | |
| 14 | Google: Gemma 3 12B | 131K Long context (128K+) | $0.05 | Budget | |
| 15 | Google: Gemma 3 27B | 131K Long context (128K+) | $0.08 | Budget | |
| 16 | Google: Gemma 4 26B A4B | 262K Long context (128K+) | $0.08 | Budget | |
| 17 | Google: Gemma 4 26B A4B (free) | 262K Long context (128K+) | $0.00 | Budget | |
| 18 | Google: Gemma 4 31B | 262K Long context (128K+) | $0.09 | Budget | |
| 19 | Google: Gemma 4 31B (free) | 262K Long context (128K+) | $0.00 | Budget | |
| 20 | meta-llama/Llama-3.1-8B-Instruct | Meta | 131K Long context (128K+) | $0.05 | Budget |
| 21 | OpenAI: gpt-oss-20b | OpenAI | 131K Long context (128K+) | $0.02 | Budget |
| 22 | Qwen: Qwen3 32B | Qwen | 131K Long context (128K+) | $0.08 | Budget |
| 23 | IBM: Granite 4.1 8B | Ibm Granite | 131K Long context (128K+) | $0.05 | Budget |
| 24 | IBM: Granite 4.2 8B | Ibm Granite | 131K Long context (128K+) | $0.06 | Budget |
| 25 | Inception: Mercury 2.5 | Inception | 260K Long context (128K+) | $0.04 | Budget |
Frequently asked questions
What is function calling?
The ability for the model to emit a structured tool-call (e.g. 'search_web("query")') that your app executes and feeds back. Foundation for agents and most RAG pipelines.
Are tool-use and function calling the same?
Yes — different vendors use different names for the same capability. OpenAI calls them 'tools', Anthropic calls them 'tools', Google calls them 'function calling'.
Related use cases
AI models for codingAI reasoning modelsAI vision modelslong-context AI models (128K+)AI models for structured / JSON outputsAI models for agentsfree AI modelsCheapest AI models per tokenmultilingual AI modelsembedding modelssmall / on-device AI modelsAI image generation modelsAI voice / audio modelsAI models for mathAI models for writingopen-source AI modelsAI models for RAGAI models for summarizationAI models for translationAI models for enterprise