Skip to main content
ZICQ

Tool Calling (Function Call)

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

Last updated: 45 min ago (2026-11-20 05:59)
Clear
Sources and methodology

Models declaring tools / tool_choice support, ranked by Agentic index plus a tool bonus.

📊 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 479
Free & tunable 16
Vision 335
Tool calling 416
Reasoning 362
Max context xAI: Grok 4.20 2M tokens
Average known input price $1.56 / 1M USD / 1M tokens
Cheapest model inclusionAI: Ling 3.0 Tiny $0.015 / 1M
TOP by Tool bonus Google: Gemini 4 Neon $-36.840
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
Metric Google: Gemini 4 Neon Google DeepMind Google: Gemini 4 Neon (batch) Google DeepMind OpenAI: GPT-6.2 Astra Pro OpenAI
Intelligence / Coding / Agentic 61.4 / 0.0 / 0.0 61.4 / 0.0 / 0.0 —
Context Window 1.0M tokens 1.0M tokens 1.1M tokens
Input / Output Price (1M) $3.00 / $15.00 $1.50 / $7.50 $8.00 / $40.00
Est. Monthly Cost (30d) Adjust inputs to calculate Adjust inputs to calculate Adjust inputs to calculate
  1. #41
    DeepSeek: DeepSeek V4.1 Flash 1017 DeepSeek 视觉多模态 Benchmarked

    DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

    Tools Vision Reasoning Structured
    Context 1.0M Output ≤ 393K
    $0.15/1M $0.60/1M out cache $0.00/1M
    Stable Function Calling
  2. #42
    DeepSeek: DeepSeek V4.1 Flash 1017 (batch) DeepSeek 视觉多模态 Benchmarked

    DeepSeek V4.1 Flash 1017 is the October 17, 2026 snapshot of DeepSeek V4.1 Flash, served by DeepSeek under the `deepseek-flash` API model name. V4.1 Flash is a sparse mixture-of-experts model...

    Tools Vision Reasoning Structured
    Context 1.0M Output ≤ 943K
    $0.04/1M $0.15/1M out cache $0.00/1M
    Stable Function Calling
  3. #43
    Elorian: Glimpse Elorian 视觉多模态

    Glimpse is a multimodal visual reasoning model from Elorian, built for visual understanding and complex visual reasoning in the physical world. It reasons directly over images and video rather than...

    Tools Vision Video Reasoning Structured
    Context 262K Output ≤ 256K
    $0.60/1M $3.00/1M out cache $0.06/1M
    Stable Function Calling
  4. #44
    Reflection: Beam 1.0 501B A23B Reflection General LLM Benchmarked

    Beam 1.0 is Reflection's open-weight reasoning model for coding and long-horizon agentic workflows. It uses a sparse mixture-of-experts architecture with 501B total and 23B active parameters per token, and a...

    Tools Reasoning Structured
    Context 1.0M Output ≤ 131K
    $0.25/1M $1.00/1M out cache $0.05/1M
    Stable Function Calling
  5. #45
    PrismML: Ternary Bonsai 2 9B Prism-Ml 视觉多模态

    Ternary Bonsai 2 9B is PrismML’s compact, open-weight language model for conversational AI, reasoning, and tool use. Built on Qwen3.5, it uses ternary weights packed into 2 bits for efficient...

    Tools Vision Reasoning Structured
    Context 262K Output ≤ 65K
    $0.08/1M $0.13/1M out cache $0.04/1M
    Stable Function Calling
  6. #46
    Meta: Muse Spark Open Meta Audio-Video Multimodal Benchmarked

    Muse Spark Open is a coding-optimized open-weight model. Trained specifically for agentic coding workflows, it delivers higher first-attempt accuracy, reliable tool calling, and deep codebase understanding across the repos developers...

    Tools Vision Audio Video Docs Reasoning Structured
    Context 1.0M Output ≤ 943K
    $1.25/1M $4.25/1M out cache $0.15/1M
    Stable Function Calling
  7. #47
    NVIDIA: Nemotron 3.5 Super VL NVIDIA 视觉多模态 Benchmarked

    NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    Tools Vision Video Reasoning Structured
    Context 1.0M Output ≤ 235K
    $0.15/1M $0.50/1M out cache $0.02/1M
    Stable Function Calling
  8. #48
    NVIDIA: Nemotron 3.5 Super VL (free) NVIDIA 视觉多模态 Free Benchmarked

    NVIDIA Nemotron 3.5 Super VL is an open multimodal mixture-of-experts model from NVIDIA, with 12B active parameters out of 120B total. It takes text, images, documents, GUI screenshots, and video...

    Tools Vision Video Reasoning Structured
    Context 1M Output ≤ 131K
    Free
    Free & Tunable
  9. #49
    Pareto 26.10 Unbiased 视觉多模态

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    Tools Vision
    Context 1.0M Output ≤ 131K
    $0.80/1M $3.20/1M out cache $0.03/1M
    Stable Function Calling
  10. #50
    Pareto Latest ~Unbiased 视觉多模态

    This model always redirects to the latest model in the Pareto family.

    Tools Vision
    Context 1.0M Output ≤ 131K
    $0.80/1M $3.20/1M out cache $0.03/1M
    Stable Function Calling
  11. #51
    Pareto 26.9 Unbiased 视觉多模态

    Pareto is a multimodal composite model built for research, coding, and agentic workflows, while delivering frontier-level performance across a broad range of general-purpose tasks.

    Tools Vision Structured
    Context 262K Output ≤ 131K
    $2.50/1M $7.50/1M out cache $0.25/1M
    Stable Function Calling
  12. #52
    LiquidAI: LFM2.5-24B-A2B Liquid General LLM

    LFM2.5-24B-A2B is a mixture-of-experts reasoning model from Liquid AI with 24B total and 2.45B active parameters. It always reasons before answering and is built for agents that call tools. Liquid...

    Tools Reasoning Structured
    Context 128K Output ≤ 8K
    $0.05/1M $0.70/1M out cache $0.02/1M
    Stable Function Calling
  13. #53
    Google: Gemini 4 Argon Google DeepMind Audio-Video Multimodal Benchmarked

    Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

    Tools Vision Audio Video Docs Reasoning Structured
    Context 1.0M Output ≤ 943K
    $2.00/1M $10.00/1M out cache $0.10/1M
    Stable Function Calling
  14. #54
    Google: Gemini 4 Argon (batch) Google DeepMind Audio-Video Multimodal Benchmarked

    Gemini 4 Argon is Google's flagship reasoning model, built for complex software engineering, deep mathematical and scientific problem solving, and autonomous multi-step agents. Google trained it to keep context across...

    Tools Vision Audio Video Docs Reasoning Structured
    Context 1.0M Output ≤ 943K
    $1.00/1M $5.00/1M out cache $0.05/1M
    Stable Function Calling
  15. #55
    Meta: Muse Wonder Meta Audio-Video Multimodal Benchmarked

    Muse Wonder is a frontier reasoning model from Meta, designed for complex personal and professional agentic tasks. It accepts text, images, video, audio, and PDF documents and returns text, with...

    Tools Vision Audio Video Docs Reasoning Structured
    Context 1.0M Output ≤ 943K
    $4.00/1M $20.00/1M out cache $0.20/1M
    Stable Function Calling
  16. #56
    StepFun: Step 5 Preview Stepfun 视觉多模态 Benchmarked

    Step 5 Preview is StepFun's flagship model for agentic work, built on a sparse Mixture-of-Experts architecture (27B active / 600B total parameters). It performs strongly in software engineering and professional...

    Tools Vision Video Reasoning Structured
    Context 1M Output ≤ 64K
    $1.00/1M $2.70/1M out cache $0.10/1M
    Stable Function Calling
  17. #57
    Anthropic: Claude Haiku 5.5 Anthropic Doc & Vision Benchmarked

    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...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $0.10/1M $0.50/1M out cache $0.01/1M
    Stable Function Calling
  18. #58
    Anthropic: Claude Haiku 5.5 (batch) Anthropic Doc & Vision Benchmarked

    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...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $0.05/1M $0.25/1M out cache $0.01/1M
    Stable Function Calling
  19. #59
    Google: Nano Banana 2.1 Google DeepMind Image Generation

    Nano Banana 2.1 (Gemini Nano Banana 2.1) is Google's image generation and editing model on the Flash tier, succeeding Nano Banana 2 and Nano Banana Pro. It improves product recontextualization,...

    Tools Vision Reasoning Structured Image gen
    Context 65K Output ≤ 58K
    $1.50/1M $7.50/1M out
    Stable Function Calling
  20. #60
    Mistral: Mistral Large 4 Mistral AI 视觉多模态 Benchmarked

    Mistral Large 4 is a frontier multimodal (text and image input) model from Mistral AI built for reasoning, coding, and agentic workloads. It offers a 1M-token context window with up...

    Tools Vision Reasoning Structured
    Context 1.0M Output ≤ 262K
    $0.70/1M $2.10/1M out cache $0.07/1M
    Stable Function Calling