Skip to main content
ZICQ

Long Context

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

Last updated: 25 min ago (2026-11-19 05:12)
Clear
Sources and methodology

Sorted by context_length descending — for long-document reading, whole-repo analysis, and million-token tasks.

📊 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 17
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 Context length xAI: Grok 4.20 Multi-Agent 2M
⚡ Side-by-Side Model PK & Token Cost Calculator Click "+ Compare" on any model below to swap · Live monthly cost calculator · Shareable comparison URL
Metric xAI: Grok 4.20 Multi-Agent xAI xAI: Grok 4.20 xAI Auto Router Openrouter
Intelligence / Coding / Agentic — — —
Context Window 2M tokens 2M tokens 2M tokens
Input / Output Price (1M) $1.25 / $2.50 $1.25 / $2.50 $-1000000.00 / $-1000000.00
Est. Monthly Cost (30d) Adjust inputs to calculate Adjust inputs to calculate Adjust inputs to calculate
  1. #181
    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
  2. #182
    NVIDIA: Nemotron 3 Ultra (free) NVIDIA General LLM Free Benchmarked

    NVIDIA Nemotron 3 Ultra is an open frontier-reasoning and orchestration model from NVIDIA, with 55B active parameters out of 550B total (MoE). Built on a hybrid Transformer-Mamba mixture-of-experts architecture, it...

    Tools Reasoning
    Context 1M Output ≤ 65K
    Free
    Free & Tunable
  3. #183
    NVIDIA: Nemotron 3.5 Lightning (free) NVIDIA General LLM Free Benchmarked

    NVIDIA Nemotron 3.5 Lightning is an open mixture-of-experts model from NVIDIA, with 3B active parameters out of 30B total. It is suited for high-throughput agentic workloads and specialized tasks that...

    Tools Reasoning
    Context 1M Output ≤ 65K
    Free
    Free & Tunable
  4. #184
    ScaleDown: Summarize Scaledown Doc & Vision

    Summarize is an abstractive summarization model from ScaleDown. It condenses long text and documents into a fluent, faithful rewrite rather than lifting sentences from the source, and is suited for...

    Vision Docs
    Context 1M Output ≤ 4K
    $0.04/1M $0.00/1M out
    1M+ Long Context
  5. #185
    ScaleDown: Extract Scaledown Doc & Vision

    Extract is a description-driven entity extraction model from ScaleDown. Instead of a fixed set of entity types, callers describe the fields they want in plain English through `provider.options.scaledown.entities`, and the...

    Vision Docs
    Context 1M Output ≤ 900K
    $0.04/1M $0.00/1M out
    1M+ Long Context
  6. #186
    Z.ai: GLM 5.3 Prime Zhipu 智谱 General LLM

    GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...

    Tools Reasoning Structured
    Context 1M Output ≤ 131K
    $1.68/1M $5.28/1M out cache $0.34/1M
    1M+ Long Context
  7. #187
    Qwen: Qwen3.8 Max Prime Alibaba 通义 视觉多模态

    Qwen3.8 Max Prime is a higher-throughput variant of Qwen3.8 Max from Alibaba's Qwen team, served as a separate SKU at a higher price point. It accepts text, image, and video...

    Tools Vision Video Reasoning Structured
    Context 1M Output ≤ 131K
    $4.00/1M $12.00/1M out cache $0.50/1M
    1M+ Long Context
  8. #188
    Qwen: Qwen3.8 Omni Flash Alibaba 通义 Audio-Video Multimodal

    Qwen3.8 Omni Flash is an omni-modal reasoning model from Alibaba, the first Qwen model built around agentic capabilities with native audio-video understanding. It is suited for audio-video analysis and summarization,...

    Tools Vision Audio Video Reasoning Structured
    Context 1M Output ≤ 131K
    $0.15/1M $0.47/1M out cache $0.02/1M
    1M+ Long Context
  9. #189
    Sakana: Fugu Ultra v2 Sakana Doc & Vision

    Fugu Ultra v2 is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to...

    Tools Vision Docs Reasoning Structured Web search
    Context 1M Output ≤ 128K
    $5.00/1M $30.00/1M out cache $0.50/1M
    1M+ Long Context
  10. #190
    Sakana: Fugu Max Sakana Doc & Vision

    Fugu Max is the cost-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

    Tools Vision Docs Reasoning Structured Web search
    Context 1M Output ≤ 128K
    $2.00/1M $6.00/1M out cache $0.25/1M
    1M+ Long Context
  11. #191
    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
    1M+ Long Context
  12. #192
    Anthropic: Claude Sonnet 5 Anthropic Doc & Vision

    Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $2.00/1M $10.00/1M out cache $0.20/1M
    1M+ Long Context
  13. #193
    Anthropic: Claude Sonnet 5 (batch) Anthropic Doc & Vision

    Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $1.00/1M $5.00/1M out cache $0.10/1M
    1M+ Long Context
  14. #194
    Sakana: Fugu Ultra Sakana 视觉多模态

    Fugu Ultra is the higher-performance model in Sakana AI's Fugu family. Rather than a single monolithic model, Fugu is a learned multi-agent orchestration system: a language model trained to route...

    Tools Vision Reasoning Structured Web search
    Context 1M Output ≤ 128K
    $5.00/1M $30.00/1M out cache $0.50/1M
    1M+ Long Context
  15. #195
    Anthropic: Claude Fable Latest ~Anthropic Doc & Vision

    This model always redirects to the latest model in the Claude Fable family.

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $8.00/1M $40.00/1M out cache $0.20/1M
    1M+ Long Context
  16. #196
    Anthropic: Claude Fable 5 Anthropic Doc & Vision

    Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $10.00/1M $50.00/1M out cache $1.00/1M
    1M+ Long Context
  17. #197
    Anthropic: Claude Fable 5 (batch) Anthropic Doc & Vision

    Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $5.00/1M $25.00/1M out cache $0.50/1M
    1M+ Long Context
  18. #198
    Qwen: Qwen3.7 Plus Alibaba 通义 视觉多模态

    Qwen3.7-Plus is a cost-effective model in Alibaba's Qwen3.7 series. It supports text and image input with text output, building on the series' text capabilities with a comprehensive upgrade to its...

    Tools Vision Reasoning Structured
    Context 1M Output ≤ 131K
    $0.32/1M $1.28/1M out cache $0.06/1M
    1M+ Long Context
  19. #199
    Anthropic: Claude Opus 4.8 Anthropic Doc & Vision

    Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $5.00/1M $25.00/1M out cache $0.50/1M
    1M+ Long Context
  20. #200
    Anthropic: Claude Opus 4.8 (batch) Anthropic Doc & Vision

    Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token...

    Tools Vision Docs Reasoning Structured
    Context 1M Output ≤ 128K
    $2.50/1M $12.50/1M out cache $0.25/1M
    1M+ Long Context