OneProvider
OneProvider

Claude & GPT API Pricing per 1M Tokens

See what Claude, GPT, Gemini and DeepSeek really cost per 1M tokens. One prepaid balance, no subscription, pay only for the requests you make.

Pay for usage, not seats

Top up the balance you need and use it across supported Claude and Codex models. The balance does not reset each month.

Check rates before a large run

Use the live per-token rate reference and your measured input and output tokens to estimate cost.

Model catalog

Models, IDs and live rates

Choose a specific model, keep a familiar API protocol, and pay for measured usage.

  • Frontier · Anthropic Messages API

    Claude Fable 5

    claude-fable-5 · 1M-token context

    input $10.00 / MTok; output $50.00 / MTok

  • Speed · Anthropic Messages API

    Claude Haiku 4.5

    claude-haiku-4-5 · 200K-token context

    input $1.00 / MTok; output $5.00 / MTok

  • Speed · Anthropic Messages API

    Claude Haiku 4.5 20251001

    claude-haiku-4-5-20251001 · 200K-token context

    input $1.00 / MTok; output $5.00 / MTok

  • Speed · Anthropic Messages API

    Claude Haiku 4.5 20251001 Thinking

    claude-haiku-4-5-20251001-thinking · Context window varies by model

    input $1.00 / MTok; output $5.00 / MTok

  • Speed · Anthropic Messages API

    Claude Haiku 4.5 Thinking

    claude-haiku-4-5-thinking · Context window varies by model

    input $1.00 / MTok; output $5.00 / MTok

  • Frontier · Anthropic Messages API

    Claude Opus 4.7

    claude-opus-4-7 · 1M-token context

    input $5.00 / MTok; output $25.00 / MTok

  • Flagship · Anthropic Messages API

    Claude Opus 4.8

    claude-opus-4-8 · 1M-token context

    input $5.00 / MTok; output $25.00 / MTok

  • Flagship · Anthropic Messages API

    Claude Opus 5

    claude-opus-5 · 1M-token context

    input $5.00 / MTok; output $25.00 / MTok

  • Flagship · Anthropic Messages API

    Claude Opus 5.5

    claude-opus-5-5 · 1M-token context

    input $4.00 / MTok; output $20.00 / MTok

  • Balanced · Anthropic Messages API

    Claude Sonnet 5.5

    claude-sonnet-5-5 · 1M-token context

    input $2.00 / MTok; output $10.00 / MTok

  • Speed · Anthropic Messages API

    Claude Haiku 5.5

    claude-haiku-5-5 · 1M-token context

    input $0.10 / MTok; output $0.50 / MTok

  • Frontier · Anthropic Messages API

    Claude Opus 5 Thinking

    claude-opus-5-thinking · Context window varies by model

    input $5.00 / MTok; output $25.00 / MTok

  • Balanced · Anthropic Messages API

    Claude Sonnet 4.6

    claude-sonnet-4-6 · 1M-token context

    input $3.00 / MTok; output $15.00 / MTok

  • Balanced · Anthropic Messages API

    Claude Sonnet 5

    claude-sonnet-5 · 1M-token context

    input $2.00 / MTok; output $10.00 / MTok

  • Frontier · Anthropic Messages API

    Claude Sonnet 5 Thinking

    claude-sonnet-5-thinking · 1M-token context

    input $2.00 / MTok; output $10.00 / MTok

  • Frontier · Anthropic Messages API

    Claude Fable 5.1

    claude-fable-5-1 · 1M-token context

    input $10.00 / MTok; output $50.00 / MTok

  • Speed · OpenAI-compatible API

    DeepSeek V4.1 Flash

    deepseek-v4.1-flash · 1M-token context

    input $0.30 / MTok; output $1.20 / MTok

  • Speed · OpenAI-compatible API

    DeepSeek V4 Flash

    deepseek-v4-flash · 1M-token context

    input $0.30 / MTok; output $1.20 / MTok

  • Speed · OpenAI-compatible API

    DeepSeek V4 Flash 0731

    deepseek-v4-flash-0731 · 1M-token context

    input $0.30 / MTok; output $1.20 / MTok

  • Speed · OpenAI-compatible API

    DeepSeek V4 Flash Vision Exp

    deepseek-v4-flash-vision-exp · 1M-token context

    input $0.30 / MTok; output $1.20 / MTok

  • Frontier · OpenAI-compatible API

    DeepSeek V4 Pro

    deepseek-v4-pro · 1M-token context

    input $1.32 / MTok; output $3.96 / MTok

  • Frontier · OpenAI-compatible API

    DeepSeek V4 Pro 0813

    deepseek-v4-pro-0813 · 1M-token context

    input $1.32 / MTok; output $3.96 / MTok

  • Image · OpenAI-compatible API

    Gemini 3.1 Flash Image

    gemini-3.1-flash-image · 131,072-token context

    Rate details are shown in the live pricing table

  • Efficient · OpenAI-compatible API

    Gemini 3.1 Flash Lite

    gemini-3.1-flash-lite · 1,048,576-token context

    input $0.25 / MTok; output $1.50 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.1 Flash Lite Preview

    gemini-3.1-flash-lite-preview · 1,048,576-token context

    input $0.25 / MTok; output $1.50 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.1 Pro

    gemini-3.1-pro · 1,048,576-token context

    input $2.00 / MTok; output $12.00 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.1 Pro High

    gemini-3.1-pro-high · 1,048,576-token context

    input $2.00 / MTok; output $12.00 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.1 Pro Low

    gemini-3.1-pro-low · 1,048,576-token context

    input $2.00 / MTok; output $12.00 / MTok

  • Frontier · OpenAI-compatible API

    Gemini 3.1 Pro Preview

    gemini-3.1-pro-preview · 1,048,576-token context

    input $2.00 / MTok; output $12.00 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.1 Pro Preview Low

    gemini-3.1-pro-preview-low · 1,048,576-token context

    input $2.00 / MTok; output $12.00 / MTok

  • Balanced · OpenAI-compatible API

    Gemini 3.5 Flash

    gemini-3.5-flash · 1,048,576-token context

    input $1.50 / MTok; output $9.00 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.6 Flash

    gemini-3.6-flash · 1,048,576-token context

    input $0.75 / MTok; output $3.75 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.6 Flash Tiered

    gemini-3.6-flash-tiered · 1,048,576-token context

    input $0.75 / MTok; output $3.75 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.7 Flash

    gemini-3.7-flash · 1,048,576-token context

    input $0.75 / MTok; output $3.75 / MTok

  • Speed · OpenAI-compatible API

    Gemini 3.8 Flash

    gemini-3.8-flash · 1,048,576-token context

    input $0.75 / MTok; output $3.75 / MTok

  • Frontier · OpenAI-compatible API

    Gemini 4 Argon

    gemini-4-argon · 1,048,576-token context

    input $2.00 / MTok; output $10.00 / MTok

  • Frontier · OpenAI-compatible API

    GLM 5.3

    glm-5.3 · 1M-token context

    input $1.40 / MTok; output $4.40 / MTok

  • Speed · OpenAI-compatible API

    GLM 5.3 Flash

    glm-5.3-flash · 1,048,576-token context

    input $0.15 / MTok; output $0.50 / MTok

  • Frontier · OpenAI-compatible API

    GPT-6.1 Sol

    gpt-6.1-sol · 1050K-token context

    input $2.00 / MTok; output $10.00 / MTok

  • Frontier · OpenAI-compatible API

    GPT-6 Astra

    gpt-6-astra · 1100K-token context

    input $10.00 / MTok; output $50.00 / MTok

  • Frontier · OpenAI-compatible API

    GPT-6 Sol

    gpt-6-sol · 1050K-token context

    input $2.00 / MTok; output $10.00 / MTok

  • Flagship · OpenAI-compatible API

    GPT-5.5

    gpt-5.5 · 1050K-token context

    input $5.00 / MTok; output $30.00 / MTok

  • Efficient · OpenAI-compatible API

    GPT-5.6 Luna

    gpt-5.6-luna · 1050K-token context

    input $1.00 / MTok; output $6.00 / MTok

  • Balanced · OpenAI-compatible API

    GPT-5.6 Terra

    gpt-5.6-terra · 1050K-token context

    input $2.50 / MTok; output $15.00 / MTok

  • Efficient · OpenAI-compatible API

    GPT-6 Luna

    gpt-6-luna · 1050K-token context

    input $0.10 / MTok; output $0.50 / MTok

  • Image · OpenAI-compatible API

    GPT Image 2

    gpt-image-2 · Context window varies by model

    input $5.00 / MTok; output $10.00 / MTok

  • Image · OpenAI-compatible API

    GPT Image 2.5 Sunburst

    gpt-image-2.5-sunburst · Context window varies by model

    input $5.00 / MTok; output $30.00 / MTok

  • Flagship · OpenAI-compatible API

    Grok 4.5

    grok-4.5 · 500K-token context

    input $2.00 / MTok; output $6.00 / MTok

  • Frontier · OpenAI-compatible API

    Grok 4.6

    grok-4.6 · 500K-token context

    input $2.00 / MTok; output $6.00 / MTok

  • Frontier · OpenAI-compatible API

    Grok 4.7

    grok-4.7 · 500K-token context

    input $2.00 / MTok; output $6.00 / MTok

  • Image · OpenAI-compatible API

    Grok Imagine

    grok-imagine · Context window varies by model

    Rate details are shown in the live pricing table

  • Image · OpenAI-compatible API

    Grok Imagine Image 2.0

    grok-imagine-image-2.0 · Context window varies by model

    Rate details are shown in the live pricing table

  • Balanced · OpenAI-compatible API

    Kimi K2.7 Code

    kimi-k2.7-code · 262,144-token context

    input $0.95 / MTok; output $4.00 / MTok

  • Speed · OpenAI-compatible API

    Kimi K2.7 Code Highspeed

    kimi-k2.7-code-highspeed · 262,144-token context

    input $1.90 / MTok; output $8.00 / MTok

  • Frontier · OpenAI-compatible API

    Kimi K3

    kimi-k3 · 1,048,576-token context

    input $3.00 / MTok; output $15.00 / MTok

  • Image · OpenAI-compatible API

    Gemini 3 Pro Image

    gemini-3-pro-image · Context window varies by model

    input $2.00 / MTok; output $12.00 / MTok

  • Image · OpenAI-compatible API

    Gemini 3 Pro Image Preview

    gemini-3-pro-image-preview · Context window varies by model

    input $2.00 / MTok; output $12.00 / MTok

  • Image · OpenAI-compatible API

    Gemini 3.1 Flash Image Preview

    gemini-3.1-flash-image-preview · 131,072-token context

    input $0.50 / MTok; output $3.00 / MTok

  • Flagship · OpenAI-compatible API

    GLM 5.1

    glm-5.1 · Context window varies by model

    input $1.40 / MTok; output $4.40 / MTok

  • Frontier · OpenAI-compatible API

    Qwen 3.7 Max

    qwen3.7-max · Context window varies by model

    input $1.65 / MTok; output $4.951 / MTok

  • Balanced · OpenAI-compatible API

    Qwen 3.7 Plus

    qwen3.7-plus · Context window varies by model

    input $0.40 / MTok; output $1.60 / MTok

  • Speed · OpenAI-compatible API

    Qwen 3.8 Flash

    qwen3.8-flash · Context window varies by model

    input $0.15 / MTok; output $0.47 / MTok

  • Frontier · OpenAI-compatible API

    Qwen 3.8 Max

    qwen3.8-max · Context window varies by model

    input $1.65 / MTok; output $4.951 / MTok