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)
    166/323
    Models
    42/51
    Providers
    115
    Vision Models (filtered)
    152
    Tool-enabled (filtered)
    2
    Free Models (filtered)
    Features
    ByteDance
    deepseek-v4-pro
    		$1.32$3.96$0.04
    DeepInfra
    deepseek-v4-pro
    		$1.30$2.60$0.10
    Together AI
    deepseek-v4-pro
    		$1.32$3.96$0.13
    Nebius AI
    deepseek-v4-pro
    		$1.75$3.50—
    Baidu
    deepseek-v4-pro
    		$1.69$3.38$0.14
    CanopyWave
    deepseek-v4-pro
    		$1.74$3.48$0.01
    Alibaba Cloud
    deepseek-v4-pro
    		$2.40$4.80$0.20
    DeepInfra
    deepseek-v4-pro
    		$1.30$2.60$0.10
    Nebius AI
    deepseek-v4-pro
    		$1.75$3.50—
    Baidu
    deepseek-v4-pro
    		$1.69$3.38$0.14
    Alibaba Cloud(singapore)
    deepseek-v4-pro
    		$2.40$4.80$0.20
    Alibaba Cloud(us-virginia)
    deepseek-v4-pro
    		$2.40$4.80$0.20
    Fireworks AI
    deepseek-v4-pro
    		$1.32$3.96$0.04
    ByteDance
    deepseek-v4-pro
    		$1.32$3.96$0.04
    Alibaba Cloud
    deepseek-v4-pro
    		$2.40$4.80$0.20
    NovitaAI
    llama-4-maverick-17b-instruct
    		$0.27$0.85—
    NovitaAI
    llama-4-maverick-17b-instruct
    		$0.27$0.85—
    Meta
    muse-spark-1.1
    		$1.25$4.25$0.15
    Meta
    muse-spark-1.1
    		$1.25$4.25$0.15
    Meta
    muse-spark-1.2
    		$1.25$4.25$0.15
    Meta
    muse-spark-1.2
    		$1.25$4.25$0.15
    Xiaomi
    mimo-v2-flash
    		$0.10$0.30$0.02
    Xiaomi
    mimo-v2-omni
    		$0.40$2.00$0.08
    Xiaomi
    mimo-v2.5
    		$0.14$0.28$0.00
    Xiaomi
    mimo-v2.5
    		$0.14$0.28$0.00
    Xiaomi
    mimo-v2-pro
    		$1.00$3.00$0.20
    Xiaomi
    mimo-v2.5-pro
    		$0.43$0.87$0.00
    Xiaomi
    mimo-v2.5-pro
    		$0.43$0.87$0.00
    xAI
    grok-build-0-1
    		$1.00$2.00$0.20
    xAI
    grok-build-0-1
    		$1.00$2.00$0.20
    AWS Bedrock
    grok-4-6
    		$2.00$6.00$0.50
    xAI
    grok-4-6
    		$2.00$6.00$0.50
    AWS Bedrock
    grok-4-6
    		$2.00$6.00$0.50
    AWS Bedrock(us-west-2)
    grok-4-6
    		$2.20$6.60$0.55
    xAI
    grok-4-6
    		$2.00$6.00$0.50
    xAI
    grok-4-5
    		$2.00$6.00$0.30
    xAI
    grok-4-5
    		$2.00$6.00$0.30
    AWS Bedrock(global)
    grok-4-3
    		$1.25$2.50$0.20
    AWS Bedrock
    grok-4-3
    		$1.25$2.50$0.20
    xAI
    grok-4-3
    		$1.25$2.50$0.20
    AWS Bedrock(us-west-2)
    grok-4-3
    		$1.38$2.75$0.22
    AWS Bedrock(us)
    grok-4-3
    		$1.38$2.75$0.22
    AWS Bedrock
    grok-4-3
    		$1.25$2.50$0.20
    xAI
    grok-4-3
    		$1.25$2.50$0.20
    Vertex AI (OpenAI-compatible)
    grok-4-20-non-reasoning
    		$1.25$2.50$0.20
    Vertex AI (OpenAI-compatible)
    grok-4-20-non-reasoning
    		$1.25$2.50$0.20
    Vertex AI (OpenAI-compatible)
    grok-4-20-reasoning
    		$1.25$2.50$0.20
    Vertex AI (OpenAI-compatible)
    grok-4-20-reasoning
    		$1.25$2.50$0.20
    xAI
    grok-4-20-beta-0309-non-reasoning
    		$2.00$6.00$0.20
    xAI
    grok-4-20-beta-0309-non-reasoning
    		$2.00$6.00$0.20
    Page 8 of 15

    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 Provider
    • Partners
    • Lounge
    • Changelog
    • Compare Models
    • Enterprise

    Resources

    • Legal Overview
    • Apps
    • MCP Server
    • Use Cases
    • Blog
    • Documentation
    • Integrations
    • Guides
    • Brand Assets
    • Token Cost Calculator
    • Copilot Cost Calculator
    • Referral Program
    • GitHub
    • Discord
    • Twitter
    • 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
    • Azure AI 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
    • NovitaAI
    • AtlasCloud
    • AWS Bedrock
    • AWS Mantle
    • Azure
    • Azure AI Foundry
    • Z AI
    • Moonshot AI
    • Baidu
    • Perplexity
    • Nebius AI
    • Mistral AI
    • CanopyWave
    • Inference.net
    • Together AI
    • SCX.ai (Turbo)
    • SCX.ai
    • ByteDance
    • MiniMax
    • EmberCloud
    • Meta
    • Sakana AI
    • Xiaomi
    • DeepInfra
    • ElevenLabs
    • Runware
    • Gonka24
    • Fireworks AI

    © 2026 OffRail. All rights reserved.

    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.

    OffRail
    • Lounge
    • Models
    • Docs
    • Pricing
    • Lounge
    • Pricing
    • Docs
    • Models
      • AI Gateway
      • Lounge
      • Observability
      • Enterprise
      • Blog
      • Changelog
      • Integrations
      • Reliability
      • Guardrails
      • Providers
      • Partners
      • Rankings
      • Apps
      • Models
      • Model Timeline
      • Compare
      • Token Cost Calculator
      • Referral Program
      • MCP Server
      • AI SDK Provider
      • Guides
    Log InGet Started
    ★