Skip to main content
ZICQ

Best Value

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

Last updated: 56 min ago (2026-11-18 12:41)
Clear
Sources and methodology

Ascending price, free models first; for budget-sensitive / high-concurrency workloads.

📊 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 Auto Router 2M tokens
Average known input price $1.55 / 1M USD / 1M tokens
Cheapest model Z.ai: GLM 5.2 $0.007 / 1M
TOP by Price (USD / 1M) inclusionAI: Ling 3.2 Flash (free) $0.000
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
Metric inclusionAI: Ling 3.2 Flash (free) Inclusionai Baidu: ERNIE-5.5-Flash-Preview (free) Baidu Thinking Machines: Inkling 2 Small (free) Thinkingmachines
Intelligence / Coding / Agentic — — 30.6 / 0.0 / 0.0
Context Window 1.0M tokens 1.0M tokens 1.0M tokens
Input / Output Price (1M) Free Free Free
Est. Monthly Cost (30d) $0.00 / mo $0.00 / mo $0.00 / mo
  1. #21
    NVIDIA: Switchyard NVIDIA General LLM

    Switchyard is an open-source model routing system that switches between multiple models to optimize the cost of requests. By default it will use OpenRouter market data to select the most...

    Context 1M
    $-1000000.00/1M $-1000000.00/1M out
    Extreme Value
  2. #22
    Auto Router (Beta) Openrouter Image Generation

    The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta...

    Tools Vision Audio Video Docs Reasoning Structured Image gen
    Context 2M Output ≤ 64K
    $-1000000.00/1M $-1000000.00/1M out
    Extreme Value
  3. #23
    OpenRouter: Fusion Openrouter General LLM

    Fusion turns your prompt into a small multi-model deliberation. A panel of expert models (see below) analyzes your prompt in parallel with web search and web fetch enabled, then a...

    Context 1M
    $-1000000.00/1M $-1000000.00/1M out
    Extreme Value
  4. #24
    Pareto Code Router Openrouter Coding & Programming

    The Pareto Router maintains a tiered shortlist of strong coding models, ranked by [Artificial Analysis](https://artificialanalysis.ai/) coding percentiles. Set min_coding_score between 0 and 1 on the [pareto-router plugin](https://openrouter.ai/docs/guides/routing/routers/pareto-router#the-min_coding_score-parameter) to control how...

    Tools Reasoning Structured
    Context 2M
    $-1000000.00/1M $-1000000.00/1M out
    Extreme Value
  5. #25
    Body Builder (beta) Openrouter General LLM

    Transform your natural language requests into structured OpenRouter API request objects. Describe what you want to accomplish with AI models, and Body Builder will construct the appropriate API calls. Example:...

    Context 128K
    $-1000000.00/1M $-1000000.00/1M out
    Extreme Value
  6. #26
    Z.ai: GLM 5.2 Zhipu 智谱 General LLM Benchmarked

    GLM 5.2 is a large-scale reasoning model from Z.ai. It supports text input and output with a 1M-token context window, and is suited for long-horizon agent workflows, project-level software engineering,...

    Tools Reasoning Structured
    Context 1.0M Output ≤ 943K
    $0.01/1M $6.80/1M out cache $0.01/1M
    Extreme Value
  7. #27
    inclusionAI: Ling 3.0 Tiny Inclusionai General LLM Benchmarked

    Ling 3.0 Tiny is a mixture-of-experts model from InclusionAI, with 1.3B active parameters out of 7.9B total. It is designed for responsive agents, instruction following, and multi-turn conversations, with switchable...

    Tools Reasoning Structured
    Context 262K Output ≤ 250K
    $0.01/1M $0.04/1M out cache $0.00/1M
    Extreme Value
  8. #28
    OpenAI: gpt-oss-20b OpenAI General LLM Benchmarked

    gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Tools Reasoning Structured
    Context 131K Output ≤ 117K
    $0.02/1M $0.09/1M out cache $0.01/1M
    Extreme Value
  9. #29
    Meta: Llama 3.1 8B Instruct Meta General LLM Benchmarked

    Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

    Tools Structured
    Context 131K Output ≤ 16K
    $0.02/1M $0.04/1M out
    Extreme Value
  10. #30
    inclusionAI: Ling 3.0 Flash Inclusionai General LLM Benchmarked

    *Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

    Tools Reasoning Structured
    Context 262K Output ≤ 32K
    $0.02/1M $0.06/1M out cache $0.00/1M
    Extreme Value
  11. #31
    Z.ai: GLM 5.3 Flash (batch) Zhipu 智谱 视觉多模态 Benchmarked

    GLM-5.3-Flash is a native multimodal model from Z.ai. It is suited for efficient coding and long-horizon agent tasks. Its hybrid sparse and linear attention architecture maintains accurate long-context behavior while...

    Tools Vision Video Reasoning Structured
    Context 1.0M Output ≤ 943K
    $0.02/1M $0.07/1M out cache $0.01/1M
    Extreme Value
  12. #32
    OpenAI: gpt-oss-20b (batch) OpenAI General LLM Benchmarked

    gpt-oss-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...

    Tools Reasoning Structured
    Context 131K Output ≤ 117K
    $0.02/1M $0.11/1M out
    Extreme Value
  13. #33
    Nex AGI: Nex-N2.5-Mini Nex-Agi 视觉多模态

    Nex-N2.5 is an agentic model built to turn goals into working, verified outcomes. Its core strength is agentic coding within a visual feedback loop: it can explore codebases, implement multi-file...

    Vision Reasoning Structured
    Context 262K Output ≤ 235K
    $0.02/1M $0.10/1M out cache $0.00/1M
    Extreme Value
  14. #34
    OpenAI: GPT-5 Nano (batch) OpenAI Doc & Vision

    GPT-5-Nano is the smallest and fastest variant in the GPT-5 system, optimized for developer tools, rapid interactions, and ultra-low latency environments. While limited in reasoning depth compared to its larger...

    Tools Vision Docs Reasoning Structured
    Context 400K Output ≤ 128K
    $0.02/1M $0.20/1M out cache $0.00/1M
    Extreme Value
  15. #35
    Meta: Llama 3.2 1B Instruct Meta General LLM

    Llama 3.2 1B is a 1-billion-parameter language model focused on efficiently performing natural language tasks, such as summarization, dialogue, and multilingual text analysis. Its smaller size allows it to operate...

    Context 60K Output ≤ 54K
    $0.03/1M $0.20/1M out
    Extreme Value
  16. #36
    Mistral: Mistral Nemo Mistral AI General LLM

    A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...

    Tools Structured
    Context 131K Output ≤ 16K
    $0.03/1M $0.03/1M out
    Extreme Value
  17. #37
    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
    Context 131K Output ≤ 117K
    $0.03/1M $0.14/1M out
    Extreme Value
  18. #38
    Inference.net: Schematron V2 Turbo Inference-Net General LLM

    Schematron V2 Turbo is a 3B-parameter HTML-to-JSON extraction model from Inference.net. It prioritizes throughput for high-volume extraction workloads. Extraction instructions must be supplied through a JSON schema in response_format rather...

    Structured
    Context 128K Output ≤ 8K
    $0.03/1M $0.15/1M out cache $0.03/1M
    Extreme Value
  19. #39
    Qwen: Qwen3.7 Flash Alibaba 通义 视觉多模态

    Qwen3.7 Flash is a vision-language reasoning model from Alibaba. It is suited for multimodal agents, visual coding, search, and computer interaction, with strengths in object recognition, spatial understanding, and real-world...

    Tools Vision Video Reasoning Structured
    Context 1M Output ≤ 65K
    $0.03/1M $0.13/1M out cache $0.01/1M
    Extreme Value
  20. #40
    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
    Extreme Value