AI Models

    Browse available models and their pricing

    DeepSeek V3.1

    DEEPSEEK

    Large hybrid reasoning model with thinking modes

    Estimated context length:212,940 words
    Input:$0.55
    Output:$2.20
    per roughly 769,000 words

    Gemini 2.5 Pro

    GEMINI

    State-of-the-art AI for advanced reasoning, coding, and science with thinking

    Estimated context length:1,363,148 words
    Input:$1.25
    Output:$10.00
    per roughly 769,000 words

    Gemini 2.5 Flash

    GEMINI

    State-of-the-art workhorse with advanced reasoning and built-in thinking

    Estimated context length:1,363,148 words
    Input:$0.30
    Output:$2.50
    per roughly 769,000 words

    Gemini 2.5 Flash Lite

    GEMINI

    Lightweight reasoning model optimized for ultra-low latency

    Estimated context length:1,363,148 words
    Input:$0.10
    Output:$0.40
    per roughly 769,000 words

    Gemini 2.0 Flash

    GEMINI

    Significantly faster TTFT compared to Gemini Flash 1.5

    Estimated context length:1,363,148 words
    Input:$0.10
    Output:$0.40
    per roughly 769,000 words

    GPT-4.1 Mini

    GPT

    Mid-sized model with GPT-4o performance at lower latency and cost

    Estimated context length:1,361,848 words
    Input:$0.40
    Output:$1.60
    per roughly 769,000 words

    Claude Sonnet 4.5

    CLAUDE

    Most advanced Sonnet for real-world agents and coding workflows

    Estimated context length:1,300,000 words
    Input:$3.00
    Output:$15.00
    per roughly 769,000 words

    Claude Sonnet 4

    CLAUDE

    High-performance model with exceptional reasoning and efficiency

    Estimated context length:1,300,000 words
    Input:$3.00
    Output:$15.00
    per roughly 769,000 words

    Grok 4 Fast

    GROK

    xAI's latest multimodal model with SOTA cost-efficiency and 2M context

    Estimated context length:2,599,999 words
    Input:$0.20
    Output:$0.50
    per roughly 769,000 words

    GPT-5

    GPT

    Most advanced reasoning, code quality, and complex tasks

    Estimated context length:520,000 words
    Input:$1.25
    Output:$10.00
    per roughly 769,000 words

    GPT-5 Mini

    GPT

    Compact GPT-5 for lighter reasoning tasks with reduced latency

    Estimated context length:520,000 words
    Input:$0.25
    Output:$2.00
    per roughly 769,000 words

    GPT-5 Nano

    GPT

    Fastest GPT-5 variant for ultra-low latency and cost-sensitive apps

    Estimated context length:520,000 words
    Input:$0.05
    Output:$0.40
    per roughly 769,000 words

    Qwen3 Max

    QWEN

    Major improvements in reasoning, multilingual support, and RAG optimization

    Estimated context length:332,800 words
    Input:$1.20
    Output:$6.00
    per roughly 769,000 words

    Claude Opus 4.1

    CLAUDE

    World's best coding model with sustained performance on complex tasks

    Estimated context length:260,000 words
    Input:$15.00
    Output:$75.00
    per roughly 769,000 words

    Gemma 3 12B

    GEMINI

    Multimodal model with vision, 128k context, and 140+ languages

    Estimated context length:170,394 words
    Input:$0.04
    Output:$0.13
    per roughly 769,000 words

    GPT-4o

    GPT

    Multimodal model with vision capabilities

    Estimated context length:166,400 words
    Input:$5.00
    Output:$15.00
    per roughly 769,000 words

    Mistral Small 3.2 24B

    OTHER

    Latest Mistral Small with vision capabilities

    Estimated context length:170,394 words
    Input:$0.20
    Output:$0.60
    per roughly 769,000 words

    Mistral Small 3.1 24B

    OTHER

    Mistral Small with vision and reasoning capabilities

    Estimated context length:170,394 words
    Input:$0.20
    Output:$0.60
    per roughly 769,000 words

    Mixtral 8x22B

    OTHER

    Mistral's mixture of experts model

    Estimated context length:85,197 words
    Input:$0.65
    Output:$0.65
    per roughly 769,000 words

    WizardLM 2 8x22B

    OTHER

    Microsoft's advanced reasoning model

    Estimated context length:85,197 words
    Input:$0.65
    Output:$0.65
    per roughly 769,000 words

    Llama 3.1 405B

    LLAMA

    Meta's largest open-source model

    Estimated context length:42,598 words
    Input:$2.70
    Output:$2.70
    per roughly 769,000 words

    Llama 3.1 70B

    LLAMA

    Meta's high-performance open model

    Estimated context length:42,598 words
    Input:$0.52
    Output:$0.52
    per roughly 769,000 words

    Llama 3.3 70B Instruct (free)

    LLAMA

    Meta's powerful 70B parameter model - free tier

    Estimated context length:170,394 words
    FREE

    Gemma 3n 2B (free)

    GEMINI

    Free lightweight model for basic tasks

    Estimated context length:10,650 words
    FREE