Skip to main content
ZICQ

Agents & Tool Calling

ZICQ LLM rankings update daily across intelligence, coding, price, and context for selection and comparison.

Last updated: 34 min ago (2026-11-18 10:41)
Clear
Sources and methodology

Ranked by OpenRouter benchmarks.agentic_index (agent / tool-calling index) plus the supported_parameters.tools flag — a reference for agent framework builders.

📊 Evaluation Benchmarks & Methodology
1. Source:Model metadata and pricing are synced hourly from OpenRouter (openrouter.ai), covering commercial, open-weight, and preview/experimental versions.
2. Benchmarks:Intelligence, coding, and agentic indices are sourced directly from Artificial Analysis (artificialanalysis.ai) official benchmark indices.
3. Overall Score Weights:Overall Score = 60% × Intelligence Index + 25% × Coding Index + 15% × Agentic Index. Models without benchmark data are ranked at the end.
4. Referral links:"Try it" buttons marked "Referral" are referral links; ZICQ may earn a commission. Referral relationships never affect rankings or scores.
Statistics for this selection
Models tracked 478
Free & tunable 17
Vision 334
Tool calling 415
Reasoning 361
Max context xAI: Grok 4.20 Multi-Agent 2M tokens
Average known input price $1.55 / 1M USD / 1M tokens
Cheapest model Z.ai: GLM 5.2 $0.007 / 1M
TOP by Agentic Anthropic: Claude Fable 5.1 57.2
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
Metric Anthropic: Claude Fable 5.1 Anthropic Anthropic: Claude Fable 5.1 (batch) Anthropic Anthropic: Claude Opus 5 Anthropic
Intelligence / Coding / Agentic 50.0 / 80.7 / 57.2 50.0 / 80.7 / 57.2 44.2 / 78.0 / 56.5
Context Window 1M tokens 1M tokens 1M tokens
Input / Output Price (1M) $10.00 / $50.00 $5.00 / $25.00 $5.00 / $25.00
Est. Monthly Cost (30d) Adjust inputs to calculate Adjust inputs to calculate Adjust inputs to calculate
  1. #421
    Perplexity: Sonar Reasoning Pro Perplexity 视觉多模态

    Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) Sonar Reasoning Pro is a premier reasoning model powered by DeepSeek R1 with Chain of Thought (CoT). Designed for...

    Vision Reasoning Web search
    Context 128K Output ≤ 115K
    $2.00/1M $8.00/1M out
    Solid Tool Calling
  2. #422
    Perplexity: Sonar Pro Perplexity 视觉多模态

    Note: Sonar Pro pricing includes Perplexity search pricing. See [details here](https://docs.perplexity.ai/guides/pricing#detailed-pricing-breakdown-for-sonar-reasoning-pro-and-sonar-pro) For enterprises seeking more advanced capabilities, the Sonar Pro API can handle in-depth, multi-step queries with added extensibility, like...

    Vision Web search
    Context 200K Output ≤ 8K
    $3.00/1M $15.00/1M out
    Solid Tool Calling
  3. #423
    Perplexity: Sonar Deep Research Perplexity General LLM

    Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...

    Reasoning Web search
    Context 128K Output ≤ 115K
    $2.00/1M $8.00/1M out
    Solid Tool Calling
  4. #424
    Mistral: Saba Mistral AI General LLM

    Mistral Saba is a 24B-parameter language model specifically designed for the Middle East and South Asia, delivering accurate and contextually relevant responses while maintaining efficient performance. Trained on curated regional...

    Tools Docs Structured
    Context 32K Output ≤ 26K
    $0.20/1M $0.60/1M out cache $0.02/1M
    Solid Tool Calling
  5. #425
    AionLabs: Aion-RP 1.0 (8B) Aion-Labs General LLM

    Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model...

    Context 32K Output ≤ 29K
    $0.80/1M $1.60/1M out
    Solid Tool Calling
  6. #426
    Qwen: Qwen2.5 VL 72B Instruct Alibaba 通义 视觉多模态

    Qwen2.5-VL is proficient in recognizing common objects such as flowers, birds, fish, and insects. It is also highly capable of analyzing texts, charts, icons, graphics, and layouts within images.

    Vision Structured
    Context 128K Output ≤ 115K
    $0.80/1M $1.00/1M out cache $0.40/1M
    Solid Tool Calling
  7. #427
    Qwen: Qwen-Plus Alibaba 通义 General LLM

    Qwen-Plus, based on the Qwen2.5 foundation model, is a 131K context model with a balanced performance, speed, and cost combination.

    Tools Structured
    Context 1M Output ≤ 32K
    $0.26/1M $0.78/1M out cache $0.05/1M
    Solid Tool Calling
  8. #428
    OpenAI: o3 Mini (batch) OpenAI General LLM

    OpenAI o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and coding. This model supports the `reasoning_effort` parameter, which can be set to...

    Tools Docs Reasoning Structured
    Context 200K Output ≤ 100K
    $0.55/1M $2.20/1M out cache $0.28/1M
    Solid Tool Calling
  9. #429
    Mistral: Mistral Small 3 Mistral AI General LLM

    Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks. Released under the Apache 2.0 license, it features both pre-trained and instruction-tuned versions designed...

    Structured
    Context 32K Output ≤ 16K
    $0.05/1M $0.08/1M out
    Solid Tool Calling
  10. #430
    Perplexity: Sonar Perplexity 视觉多模态

    Sonar is lightweight, affordable, fast, and simple to use — now featuring citations and the ability to customize sources. It is designed for companies seeking to integrate lightweight question-and-answer features...

    Vision Web search
    Context 127K Output ≤ 114K
    $1.00/1M $1.00/1M out
    Solid Tool Calling
  11. #431
    Microsoft: Phi 4 Microsoft General LLM

    [Microsoft Research](/microsoft) Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed. At 14 billion...

    Structured
    Context 16K Output ≤ 14K
    $0.07/1M $0.14/1M out
    Solid Tool Calling
  12. #432
    DeepSeek: DeepSeek V3 DeepSeek General LLM

    DeepSeek-V3 is the latest model from the DeepSeek team, building upon the instruction following and coding abilities of the previous versions. Pre-trained on nearly 15 trillion tokens, the reported evaluations...

    Tools Structured
    Context 163K Output ≤ 16K
    $0.26/1M $1.03/1M out
    Solid Tool Calling
  13. #433
    Cohere: Command R7B (12-2024) Cohere General LLM

    Command R7B (12-2024) is a small, fast update of the Command R+ model, delivered in December 2024. It excels at RAG, tool use, agents, and similar tasks requiring complex reasoning...

    Tools Structured
    Context 128K Output ≤ 4K
    $0.04/1M $0.15/1M out
    Solid Tool Calling
  14. #434
    Meta: Llama 3.3 70B Instruct Meta General LLM Benchmarked

    The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

    Tools Structured
    Intelligence 0.0
    Agentic 0.0
    Context 131K Output ≤ 115K
    $0.71/1M $0.71/1M out cache $0.71/1M
    Solid Tool Calling
  15. #435
    Amazon: Nova Lite 1.0 Amazon 视觉多模态

    Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite...

    Tools Vision
    Context 300K Output ≤ 5K
    $0.06/1M $0.24/1M out
    Solid Tool Calling
  16. #436
    Amazon: Nova Micro 1.0 Amazon General LLM

    Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length...

    Tools
    Context 128K Output ≤ 5K
    $0.04/1M $0.14/1M out
    Solid Tool Calling
  17. #437
    Amazon: Nova Pro 1.0 Amazon 视觉多模态

    Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December...

    Tools Vision
    Context 300K Output ≤ 5K
    $0.80/1M $3.20/1M out
    Solid Tool Calling
  18. #438
    OpenAI: GPT-4o (2024-11-20) OpenAI Doc & Vision

    The 2024-11-20 version of GPT-4o offers a leveled-up creative writing ability with more natural, engaging, and tailored writing to improve relevance & readability. It’s also better at working with uploaded...

    Tools Vision Docs Structured Web search
    Context 128K Output ≤ 16K
    $2.50/1M $10.00/1M out cache $1.25/1M
    Solid Tool Calling
  19. #439
    Mistral Large 2407 Mistral AI General LLM

    This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407). It's a proprietary weights-available model and excels at reasoning, code, JSON, chat, and more. Read the launch announcement [here](https://mistral.ai/news/mistral-large-2407/)....

    Tools Docs Structured
    Context 131K Output ≤ 104K
    $2.00/1M $6.00/1M out cache $0.20/1M
    Solid Tool Calling
  20. #440
    Qwen2.5 Coder 32B Instruct Alibaba 通义 Coding & Programming

    Qwen2.5-Coder is the latest series of Code-Specific Qwen large language models (formerly known as CodeQwen). Qwen2.5-Coder brings the following improvements upon CodeQwen1.5: - Significantly improvements in **code generation**, **code reasoning**...

    Structured
    Context 32K Output ≤ 29K
    $0.66/1M $1.00/1M out
    Solid Tool Calling