TokenCost
Live pricing · 398 models · 58 providers

Know what every LLM really costs

Compare 400+ AI models across 50+ providers, estimate token costs in seconds, and find the cheapest model for your workload. Free, open-source, no signup required.

398

Models

58

Providers

100%

Free & open source

Cost Calculator

Pick a model, enter token usage, see the exact cost.

openai/gpt-4o

OpenAI: GPT-4o

Cost per request$0.007500
Monthly (1,000 req)$7.5000
In 1,000 tok · $0.002500Out 500 tok · $0.005000

Price Comparison

398 models from 58 providers · per 1M tokens · USD

+48 more

cohere/north-mini-code:free

cohereFree256K

google/gemma-4-26b-a4b-it:free

googleFree262K

google/gemma-4-31b-it:free

googleFree262K

google/lyria-3-clip-preview

googleFree1.0M

google/lyria-3-pro-preview

googleFree1.0M

inclusionai/ling-3.0-tiny:free

inclusionaiFree262K

nvidia/nemotron-3-nano-30b-a3b:free

nvidiaFree256K

nvidia/nemotron-3-nano-omni-30b-a3b-reasoning:free

nvidiaFree256K

nvidia/nemotron-3-super-120b-a12b:free

nvidiaFree262K

nvidia/nemotron-3-ultra-550b-a55b:free

nvidiaFree1.0M

nvidia/nemotron-3.5-content-safety:free

nvidiaFree128K

nvidia/nemotron-3.5-lightning:free

nvidiaFree1.0M

nvidia/nemotron-nano-12b-v2-vl:free

nvidiaFree128K

nvidia/nemotron-nano-9b-v2:free

nvidiaFree128K

openai/gpt-oss-20b:free

openaiFree131K

openrouter/free

openrouterFree200K

poolside/laguna-s-2.1:free

poolsideFree262K

poolside/laguna-xs-2.1:free

poolsideFree262K

inclusionai/ling-2.6-flash

inclusionai$0.0100$0.0300262K

ibm-granite/granite-4.0-h-micro

ibm-granite$0.0170$0.1120131K

mistralai/mistral-nemo

mistralai$0.0190$0.0300131K

inclusionai/ling-3.0-flash

inclusionai$0.0210$0.0630262K

nex-agi/nex-n2-mini

nex-agi$0.0250$0.1000262K

openai/gpt-5-nano:batch

openai$0.0250$0.2000400K

meta-llama/llama-3.2-1b-instruct

meta-llama$0.0270$0.201060K

openai/gpt-oss-20b

openai$0.0300$0.1300131K

qwen/qwen3.7-flash

qwen$0.0300$0.13001.0M

upstage/solar-pro4

upstage$0.0300$0.1200524K

amazon/nova-micro-v1

amazon$0.0350$0.1400128K

openai/gpt-oss-120b

openai$0.0370$0.1700131K

cohere/command-r7b-12-2024

cohere$0.0375$0.1500128K

sao10k/l3-lunaris-8b

sao10k$0.0400$0.05008K

qwen/qwen3-30b-a3b-instruct-2507

qwen$0.0481$0.1930262K

google/gemini-2.5-flash-lite:batch

google$0.0500$0.20001.0M

google/gemma-3-12b-it

google$0.0500$0.1500131K

google/gemma-3-4b-it

google$0.0500$0.1000131K

ibm-granite/granite-4.1-8b

ibm-granite$0.0500$0.1000131K

meta-llama/llama-3.1-8b-instruct

meta-llama$0.0500$0.0800131K

meta-llama/llama-3.2-3b-instruct

meta-llama$0.0500$0.3300131K

mistralai/mistral-small-24b-instruct-2501

mistralai$0.0500$0.080033K

nvidia/nemotron-3-nano-30b-a3b

nvidia$0.0500$0.2000262K

openai/gpt-4.1-nano:batch

openai$0.0500$0.20001.0M

openai/gpt-5-nano

openai$0.0500$0.4000400K

amazon/nova-lite-v1

amazon$0.0600$0.2400300K

google/gemma-3n-e4b-it

google$0.0600$0.120033K

gryphe/mythomax-l2-13b

gryphe$0.0600$0.06008K

poolside/laguna-xs-2.1

poolside$0.0600$0.1200262K

z-ai/glm-4.7-flash

z-ai$0.0600$0.4000203K

tencent/hy3-preview

tencent$0.0630$0.2100262K

qwen/qwen3.5-flash-02-23

qwen$0.0650$0.26001.0M

microsoft/phi-4

microsoft$0.0700$0.140016K

qwen/qwen3-coder-30b-a3b-instruct

qwen$0.0700$0.2800262K

bytedance-seed/seed-1.6-flash

bytedance-seed$0.0750$0.3000262K

inclusionai/ling-2.6-1t

inclusionai$0.0750$0.6250262K

inclusionai/ring-2.6-1t

inclusionai$0.0750$0.6250262K

openai/gpt-4o-mini:batch

openai$0.0750$0.3000128K

openai/gpt-oss-safeguard-20b

openai$0.0750$0.3000131K

~deepseek/deepseek-v4-flash-latest

~deepseek$0.0798$0.15961.0M

deepseek/deepseek-v4-flash-0731

deepseek$0.0800$0.18001.0M

google/gemma-3-27b-it

google$0.0800$0.4500262K
Showing 60 of 398 models · click column headers to sort

Token Estimator

Paste text — count tokens & estimate cost locally in your browser.

Counted with the GPT-4o tokenizer (cl100k_base) — approximation for most modern models.

Tokens51

Estimated input cost

$0.000128

Output at same size

$0

Within typical context limits.

Public API

Free JSON endpoints — use pricing data in your own tools.

GET /api/prices
{
  "count": 403,
  "currency": "USD",
  "generatedAt": "2026-08-11T21:50:00+07:00",
  "models": [
    {
      "id": "openai/gpt-4o",
      "name": "OpenAI: GPT-4o",
      "provider": "openai",
      "inputPricePer1M": 2.5,
      "outputPricePer1M": 10,
      "contextLength": 128000,
      "currency": "USD"
    }
  ]
}

curl https://tokencost.pages.dev/api/prices?provider=anthropic

POST /api/estimate
{
  "modelId": "openai/gpt-4o",
  "inputTokens": 1000,
  "outputTokens": 500,
  "inputCost": 0.0025,
  "outputCost": 0.005,
  "totalCost": 0.0075,
  "currency": "USD"
}

curl -X POST https://tokencost.pages.dev/api/estimate \ -H "Content-Type: application/json" \ -d '{"modelId":"openai/gpt-4o","inputTokens":1000,"outputTokens":500}'