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: 25 min ago (2026-11-20 05:59)
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 479
Free & tunable 16
Vision 335
Tool calling 416
Reasoning 362
Max context xAI: Grok 4.20 Multi-Agent 2M tokens
Average known input price $1.56 / 1M USD / 1M tokens
Cheapest model inclusionAI: Ling 3.0 Tiny $0.015 / 1M
TOP by Agentic Anthropic: Claude Fable 5.2 0.0
⚡ 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 5.2 Anthropic Anthropic: Claude Fable 5.2 (batch) Anthropic OpenAI: GPT-6.2 Astra OpenAI
Intelligence / Coding / Agentic 64.6 / 0.0 / 0.0 64.6 / 0.0 / 0.0 62.1 / 0.0 / 0.0
Context Window 1M tokens 1M tokens 1.1M tokens
Input / Output Price (1M) $8.00 / $40.00 $4.00 / $20.00 $8.00 / $40.00
Est. Monthly Cost (30d) Adjust inputs to calculate Adjust inputs to calculate Adjust inputs to calculate
  1. #101
    Google: Gemma 4 31B Google DeepMind 视觉多模态 Benchmarked

    Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

    Tools Vision Video Reasoning Structured
    Intelligence 4.4
    Agentic 0.0
    Context 262K Output ≤ 16K
    $0.20/1M $0.40/1M out
    Solid Tool Calling
  2. #102
    Google: Gemma 4 31B (free) Google DeepMind 视觉多模态 Free Benchmarked

    Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...

    Tools Vision Video Reasoning Structured
    Intelligence 4.4
    Agentic 0.0
    Context 262K Output ≤ 32K
    Free
    Free & Tunable
  3. #103
    Mistral: Mistral Small 4 Mistral AI 视觉多模态 Benchmarked

    Mistral Small 4 is the next major release in the Mistral Small family, unifying the capabilities of several flagship Mistral models into a single system. It combines strong reasoning from...

    Tools Vision Reasoning Structured
    Intelligence 4.3
    Agentic 0.0
    Context 262K Output ≤ 209K
    $0.15/1M $0.60/1M out cache $0.01/1M
    Solid Tool Calling
  4. #104
    OpenAI: gpt-oss-120b OpenAI General LLM Benchmarked

    gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

    Tools Reasoning Structured
    Intelligence 3.8
    Agentic 0.0
    Context 131K Output ≤ 65K
    $0.15/1M $0.60/1M out cache $0.07/1M
    Solid Tool Calling
  5. #105
    OpenAI: gpt-oss-120b (batch) OpenAI General LLM Benchmarked

    gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

    Tools Reasoning Structured
    Intelligence 3.8
    Agentic 0.0
    Context 131K Output ≤ 117K
    $0.03/1M $0.14/1M out
    Solid Tool Calling
  6. #106
    Cohere: North Mini Code (free) Cohere Coding & Programming Free Benchmarked

    North Mini Code is Cohere's first agentic coding model and the debut of its North family. A sparse mixture-of-experts model with 30B total parameters and 3B active, it is optimized...

    Tools Reasoning
    Intelligence 3.4
    Agentic 0.0
    Context 256K Output ≤ 64K
    Free
    Free & Tunable
  7. #107
    OpenAI: GPT-6.2 Astra Pro OpenAI Doc & Vision

    GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

    Tools Vision Docs Reasoning Structured
    Context 1.1M Output ≤ 128K
    $8.00/1M $40.00/1M out cache $0.40/1M
    Solid Tool Calling
  8. #108
    OpenAI: GPT-6.2 Astra Pro (batch) OpenAI Doc & Vision

    GPT-6.2 Astra Pro is the same underlying model as [GPT-6.2 Astra](https://openrouter.ai/openai/gpt-6.2-astra), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

    Tools Vision Docs Reasoning Structured
    Context 1.1M Output ≤ 128K
    $4.00/1M $20.00/1M out cache $0.20/1M
    Solid Tool Calling
  9. #109
    OpenAI: GPT-6.2 Sol Pro OpenAI Doc & Vision

    GPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

    Tools Vision Docs Reasoning Structured
    Context 1.1M Output ≤ 128K
    $2.00/1M $10.00/1M out cache $0.10/1M
    Solid Tool Calling
  10. #110
    OpenAI: GPT-6.2 Sol Pro (batch) OpenAI Doc & Vision

    GPT-6.2 Sol Pro is the same underlying model as [GPT-6.2 Sol](https://openrouter.ai/openai/gpt-6.2-sol), served with `reasoning.mode` set to `pro` for higher-quality responses on complex tasks. **Cost note:** pro mode spends far more...

    Tools Vision Docs Reasoning Structured
    Context 1.1M Output ≤ 128K
    $1.00/1M $5.00/1M out cache $0.05/1M
    Solid Tool Calling
  11. #111
    Tencent: Hy4 flash Tencent 视觉多模态

    Hy4 flash is a cost-efficient variant of [Hy4](https://openrouter.ai/tencent/hy4) from Tencent, served with roughly a quarter of the flagship's parameter count for lower latency and cost. It targets code assistance, agent...

    Tools Vision Reasoning Structured
    Context 1.0M Output ≤ 65K
    $0.04/1M $0.14/1M out cache $0.00/1M
    Solid Tool Calling
  12. #112
    inclusionAI: Ling 3.2 Flash (free) Inclusionai 视觉多模态 Free

    Ling 3.2 Flash is a hybrid reasoning model from inclusionAI that accepts text and image input, with a 1M-token context window and up to 200 images per request. Thinking can...

    Tools Vision Reasoning Structured
    Context 1.0M Output ≤ 262K
    Free
    Free & Tunable
  13. #113
    Baidu: ERNIE-5.5-Flash-Preview (free) Baidu General LLM Free

    ERNIE 5.5 Flash Preview is the latest foundation model in the ERNIE family, with comprehensive improvements in coding, agentic capabilities, knowledge work, and deep research. It has 280 billion total...

    Tools Reasoning Structured
    Context 1.0M Output ≤ 921K
    Free
    Free & Tunable
  14. #114
    Baidu: ERNIE-Light-DT-1.0 Baidu General LLM

    ERNIE-Light-DT-1.0 is based on open-source GLM models and includes research findings from Baidu Search's Lightning large model. It features Baidu Sparse Attention (BSA), a unique sparse attention mechanism developed by...

    Tools Reasoning Structured
    Context 1.0M Output ≤ 131K
    $1.13/1M $3.94/1M out cache $0.11/1M
    Solid Tool Calling
  15. #115
    Nex AGI: Nex-N2.6 Nex-Agi 视觉多模态

    Nex-N2.6 is an agentic model from Nex AGI, built on [GLM-5.3-Flash](https://huggingface.co/zai-org/GLM-5.3-Flash-BF16) with about 321B parameters. It is suited for computer use, coding, and long-horizon tasks that involve tools. Compared with...

    Tools Vision Reasoning Structured
    Context 262K Output ≤ 235K
    $0.12/1M $0.40/1M out cache $0.02/1M
    Solid Tool Calling
  16. #116
    Google: Gemini Omni 1.2 Flash Google DeepMind 视觉多模态

    Gemini Omni 1.2 Flash is Google's native multimodal video generation and editing model, the successor to Gemini Omni 1.1 Flash. It generates clips up to 15 seconds long with native...

    Vision Video Reasoning
    Context 131K Output ≤ 65K
    $1.50/1M $9.00/1M out
    Solid Tool Calling
  17. #117
    KT: Mi:dm K 3.0 Pro Kt General LLM

    Mi:dm K 3.0 Pro is a Mixture-of-Experts reasoning model from KT, with 120B total and 12B active parameters. It uses a hybrid architecture that mixes Mamba, MoE and attention layers.

    Tools Reasoning Structured
    Context 261K Output ≤ 235K
    $0.20/1M $0.80/1M out cache $0.04/1M
    Solid Tool Calling
  18. #118
    Google: Gemini Omni 1.1 Flash Google DeepMind 视觉多模态

    Gemini Omni 1.1 Flash is Google's native multimodal video generation and editing model, the generally available successor to Gemini Omni Flash Preview. It is suited for text-to-video, image-to-video, first and...

    Vision Video Reasoning
    Context 131K Output ≤ 65K
    $1.50/1M $9.00/1M out
    Solid Tool Calling
  19. #119
    Ricursive: Ripple 65B Preview Ricursiveai General LLM

    Ripple-65B-Preview by ricursiveAI, a 65B model with native tool calling, served in BF16.

    Tools Reasoning Structured
    Context 1.0M Output ≤ 131K
    $0.10/1M $0.30/1M out cache $0.02/1M
    Solid Tool Calling
  20. #120
    Motif Technologies: Motif 3 Motif-Technologies General LLM

    Motif 3 is a Mixture-of-Experts language model from Motif Technologies, with 314B total and 13.2B active parameters. It is a general-purpose multilingual model for English and Korean, particularly strong at...

    Tools Reasoning Structured
    Context 262K Output ≤ 235K
    $0.30/1M $1.20/1M out cache $0.06/1M
    Solid Tool Calling