Appndo
All models

Gradient Ai API pricing

Hosted10 language models

As of Oct 14, 2026, Gradient Ai lists 10 language models through its API. Its cheapest language model is Llama3 8B Instruct at $0.20 input / $0.20 output per million tokens.

Language models (10)

Prices per million tokens.

  • DeepSeek R1 Distill Llama 70B

    gradient_ai/deepseek-r1-distill-llama-70b

    Input
    $0.99
    Output
    $0.99
    Context
    33K

  • Llama 3.3 70B Instruct

    gradient_ai/llama3.3-70b-instruct

    Input
    $0.65
    Output
    $0.65
    Context
    128K

  • Llama3 8B Instruct

    gradient_ai/llama3-8b-instruct

    Input
    $0.20
    Output
    $0.20
    Context
    8K

  • Mistral Nemo Instruct 2407

    gradient_ai/mistral-nemo-instruct-2407

    Input
    $0.30
    Output
    $0.30
    Context
    128K

  • Anthropic Claude 3 Opus

    gradient_ai/anthropic-claude-3-opus

    Input
    $15.00
    Output
    $75.00
    Context
    200K

  • Anthropic Claude 3.5 Haiku

    gradient_ai/anthropic-claude-3.5-haiku

    Input
    $0.80
    Output
    $4.00
    Context
    200K

  • Anthropic Claude 3.5 Sonnet

    gradient_ai/anthropic-claude-3.5-sonnet

    Input
    $3.00
    Output
    $15.00
    Context
    200K

  • Anthropic Claude 3.7 Sonnet

    gradient_ai/anthropic-claude-3.7-sonnet

    Input
    $3.00
    Output
    $15.00
    Context
    200K

  • OpenAI O3

    gradient_ai/openai-o3

    Input
    $2.00
    Output
    $8.00
    Context
    200K

  • OpenAI O3 Mini

    gradient_ai/openai-o3-mini

    Input
    $1.10
    Output
    $4.40
    Context
    200K

Prices in USD from LiteLLM and models.dev, checked daily; confirm on Gradient Ai's pricing page before you rely on a number.