Support

AI-powered help

Welcome!

Please introduce yourself before we start.

    Long Context Models

    Models with context windows of 200K tokens or more — up to 2M — for whole-codebase and multi-document workloads

    Compare
    Use Case
    Capabilities
    Provider
    Status
    Input Price ($/M tokens)
    Output Price ($/M tokens)
    Context Size (tokens)
    157/283
    Models
    42/55
    Providers
    114
    Vision Models (filtered)
    147
    Tool-enabled (filtered)
    1
    Free Models (filtered)
    Features
    Alibaba Cloud(eu-frankfurt)
    kimi-k2.5
    $0.57$3.01—
    EmberCloud
    kimi-k2.5
    $0.40$1.98$0.22
    Moonshot AI
    kimi-k2.5
    $0.60$3.00$0.10
    Alibaba Cloud
    kimi-k2.5
    $0.57$3.01—
    Azure
    gpt-5.2-codex
    $1.75$14.00$0.17
    NovitaAI
    minimax-m2.1
    $0.30$1.20$0.03
    EmberCloud
    glm-4.7-flash
    $0.06$0.40$0.01
    Vertex AI (OpenAI-compatible)
    glm-4.7
    $0.60$2.20—
    EmberCloud
    glm-4.7
    $0.38$1.98$0.19
    Cerebras
    glm-4.7
    $2.25$2.75—
    Z AI
    glm-4.7
    $0.60$2.20$0.11
    ByteDance
    glm-4.7
    $0.60$2.20$0.11
    NovitaAI
    glm-4.7
    $0.60$2.20$0.11
    Together AI
    glm-4.7
    $0.45$2.00—
    Z AI
    glm-4.7-flashx
    $0.07$0.40$0.01
    ByteDance
    seed-1-8-251228
    $0.25$2.00$0.05
    Google AI Studio
    gemini-3-flash-preview
    $0.50$3.00$0.05
    Google Vertex AI
    gemini-3-flash-preview
    $0.50$3.00$0.05
    OpenAI
    gpt-5.2-pro
    $21.00$18.90
    -10% off
    $168.00$151.20
    -10% off
    —
    Azure
    gpt-5.2-pro
    $21.00$168.00—
    OpenAI
    gpt-5.2
    $1.75$1.57
    -10% off
    $14.00$12.60
    -10% off
    $0.17$0.16
    -10% off
    Azure
    gpt-5.2
    $1.75$14.00$0.17
    Mistral AI
    devstral-2512
    $0.40$0.38
    -5% off
    $2.00$1.90
    -5% off
    —
    Mistral AI
    ministral-14b-2512
    $0.20$0.19
    -5% off
    $0.20$0.19
    -5% off
    —
    Mistral AI
    ministral-8b-2512
    $0.15$0.14
    -5% off
    $0.15$0.14
    -5% off
    —
    Mistral AI
    mistral-large-2512
    $0.50$0.47
    -5% off
    $1.50$1.42
    -5% off
    —
    AWS Bedrock(eu)
    claude-opus-4-5-20251101
    $5.50$27.50$0.55
    AWS Bedrock(us)
    claude-opus-4-5-20251101
    $5.50$27.50$0.55
    AWS Bedrock(global)
    claude-opus-4-5-20251101
    $5.00$25.00$0.50
    Anthropic
    claude-opus-4-5-20251101
    $5.00$4.75
    -5% off
    $25.00$23.75
    -5% off
    $0.50$0.47
    -5% off
    Vertex AI (Anthropic)
    claude-opus-4-5-20251101
    $5.00$25.00$0.50
    AWS Bedrock
    claude-opus-4-5-20251101
    $5.00$25.00$0.50
    Azure AI Foundry
    grok-4-1-fast-non-reasoning
    $0.20$0.50—
    Azure AI Foundry
    grok-4-1-fast-reasoning
    $0.20$0.50—
    Azure
    gpt-5.1-codex
    $1.25$10.00—
    Azure
    gpt-5.1-codex-mini
    $0.25$2.00$0.02
    Vertex AI (OpenAI-compatible)
    kimi-k2-thinking
    $0.60$2.50$0.06
    Azure
    gpt-5.1
    $1.25$10.00$0.13
    OpenAI
    gpt-5.1
    $1.25$1.13
    -10% off
    $10.00$9.00
    -10% off
    $0.13$0.11
    -10% off
    AWS Bedrock(jp)
    claude-haiku-4-5-20251001
    $1.10$5.50$0.11
    AWS Bedrock(au)
    claude-haiku-4-5-20251001
    $1.10$5.50$0.11
    AWS Bedrock(eu)
    claude-haiku-4-5-20251001
    $1.10$5.50$0.11
    AWS Bedrock(us)
    claude-haiku-4-5-20251001
    $1.10$5.50$0.11
    AWS Bedrock(global)
    claude-haiku-4-5-20251001
    $1.00$5.00$0.10
    AWS Bedrock
    claude-haiku-4-5-20251001
    $1.00$5.00$0.10
    Anthropic
    claude-haiku-4-5-20251001
    $1.00$0.95
    -5% off
    $5.00$4.75
    -5% off
    $0.10$0.09
    -5% off
    Alibaba Cloud(cn-beijing)
    qwen3-vl-flash
    $0.02$0.21$0.00
    Alibaba Cloud(us-virginia)
    qwen3-vl-flash
    $0.02$0.21$0.00
    Alibaba Cloud(singapore)
    qwen3-vl-flash
    $0.05$0.40$0.01
    Alibaba Cloud
    qwen3-vl-flash
    $0.05$0.40$0.01
    Page 8 of 10

    Every model on this page accepts at least 200,000 tokens of context — roughly 150,000 words — and the largest stretch much further: Grok 4.1 Fast at 2 million tokens, with Gemini, Claude Sonnet 5, GPT-5.4, DeepSeek V4, and GLM-5.2 at or above the million-token mark. That's enough to fit an entire codebase, a legal document set, or months of chat history into a single prompt.

    Advertised size isn't everything: retrieval quality can degrade well before the window is full, and long prompts get expensive fast. Cached input pricing — shown in the list — matters more than the headline price when you re-send large contexts on every request.

    Frequently asked questions

    Which LLM has the largest context window?

    Grok 4.1 Fast currently leads with a 2 million token window. Gemini models run just over 1 million, and Claude Sonnet 5, GPT-5.4, DeepSeek V4, GLM-5.2, and Qwen3.7 also offer million-token windows.

    How many words fit in a 200K context window?

    Roughly 150,000 English words — about 600 pages. A million-token window fits around 750,000 words: several full-length books, or a mid-sized codebase.

    Do models actually use the full window well?

    Not uniformly. Most models recall the start and end of a prompt better than the middle, and effective context is often smaller than the advertised maximum. For critical retrieval over huge inputs, test with your own data and consider chunking plus retrieval instead of one giant prompt.

    How do I keep long-context costs down?

    Use cached input pricing: providers charge a fraction of the normal rate for re-sent, unchanged prefixes, which is exactly the shape of chatting over a large document or codebase. Structure prompts so the big static context comes first and only the question changes.

    Newsletter

    Stay ahead of the curve

    Join developers who get weekly insights on LLM routing, new model launches, and cost optimization — straight to their inbox.

    • New models & providers as they drop
    • Tips to cut latency & costs
    • Early access to beta features

    No spam. Unsubscribe anytime.

    All systems operational
    AICPA SOC for Service Organizations badgeSOC 2 Type II compliant

    Product

    • Features
    • AI Gateway
    • Observability
    • Models
    • Providers
    • Rankings
    • Add a provider
    • Partners
    • PassingRight Chat
    • DevPass
    • Compare models
    • Enterprise

    Resources

    • Legal overview
    • Apps
    • Templates
    • Agents
    • MCP server
    • Use cases
    • Documentation
    • Developer resources
    • Integrations
    • Guides
    • Brand assets
    • Token cost calculator
    • Copilot cost calculator
    • Referral program
    • About
    • Contact us

    Compliance

    • Trust center
    • Security portal
    • Terms
    • Privacy policy
    • Provider information
    • Sub-processors
    • SOC 2 Type II
    • Status

    Compare

    • All comparisons
    • GitHub Copilot
    • OpenRouter
    • LiteLLM
    • Portkey
    • AWS Bedrock
    • Microsoft Foundry
    • Vercel AI Gateway
    • Migration guides

    Models

    • Text generation
    • Text to image
    • Image to image
    • Video generation
    • Embeddings
    • Vision
    • Reasoning
    • Tool calling
    • Web search
    • Discounted
    • Best for roleplay
    • Best for coding
    • Best for creative writing
    • Best for translation
    • Best for math
    • Long context
    • Cheapest
    • Open source

    Providers

    • OpenAI
    • Anthropic
    • Google AI Studio
    • Google Vertex AI
    • Vertex AI (OpenAI-compatible)
    • Vertex AI (Anthropic)
    • Groq
    • Cerebras
    • xAI
    • DeepSeek
    • Alibaba Cloud
    • Runpod
    • NovitaAI
    • AtlasCloud
    • AWS Bedrock
    • AWS Mantle
    • Azure
    • Azure AI Foundry
    • Azure Anthropic
    • Z AI

    © 2026 PassingRight. All rights reserved.

    PassingRight
    • Models
    • Pricing
    • Docs
    • PassingRight Chat
    • Models
    • Pricing
    • Docs
    • PassingRight Chat
    Log inGet an API key
    Moonshot AI
  1. Baidu
  2. Perplexity
  3. Mistral AI
  4. CanopyWave
  5. Inference.net
  6. Together AI
  7. SCX.ai (Turbo)
  8. SCX.ai
  9. ByteDance
  10. MiniMax
  11. EmberCloud
  12. Meta
  13. Meta Contributor
  14. Sakana AI
  15. Xiaomi
  16. DeepInfra
  17. ElevenLabs
  18. Runware
  19. Gonka24
  20. Fireworks AI
  21. RanoAI
  22. Consensus Protocol
  23. Tencent Cloud
  24. Atria
  25. TypeSafe AI