Model comparison

Context windows, prices and strengths of popular models, side by side.

  • GPT-5
    OpenAI
    Context
    256K tokens
    Input / 1M
    $5
    Output / 1M
    $15

    Strong general reasoning, tool use, broad ecosystem.

  • GPT-5 mini
    OpenAI
    Context
    128K tokens
    Input / 1M
    $0.5
    Output / 1M
    $1.5

    Fast and cheap for everyday tasks and high volume.

  • Claude Opus 4
    Anthropic
    Context
    200K tokens
    Input / 1M
    $15
    Output / 1M
    $75

    Deep reasoning, long-form writing, careful instruction following.

  • Claude Sonnet 4
    Anthropic
    Context
    200K tokens
    Input / 1M
    $3
    Output / 1M
    $15

    Balanced quality and cost, excellent for coding and agents.

  • Gemini 2.5 Pro
    Google
    Context
    1M tokens
    Input / 1M
    $1.25
    Output / 1M
    $10

    Huge context window, strong multimodal understanding.

  • Gemini 2.5 Flash
    Google
    Context
    1M tokens
    Input / 1M
    $0.3
    Output / 1M
    $2.5

    Very fast and inexpensive with a large context window.

  • Grok 4
    xAI
    Context
    256K tokens
    Input / 1M
    $3
    Output / 1M
    $15

    Real-time knowledge via X, conversational and witty.

  • Llama 4 Maverick
    Meta
    Context
    1M tokens
    Input / 1M
    $0.2
    Output / 1M
    $0.6

    Open weights, self-hostable, cost-effective at scale.

Last updated: 2026-09-15

Prices and context windows are approximate, drawn from public provider documentation, and change frequently. Always confirm current pricing with the provider before relying on these numbers. TidyChats is not affiliated with any model provider.