TOKENS

Paste text, drop a file, and compare token costs across every major model.

Paste your text or prompt

You are an AI agent that helps developers build applications. Your task is to:

1. Analyze the user's codebase structure
2. Identify areas where AI can add value
3. Suggest concrete implementations using TypeScript
4. Generate working code with proper error handling

When building an AI agent, consider these key principles:
- Keep the agent loop simple and predictable
- Use structured tool definitions with clear schemas
- Implement proper retry logic and timeout handling
- Log every step for debugging and observability
- Test with deterministic inputs before going live

Here is an example tool definition:

const tools = [
  {
    name: "search_codebase",
    description: "Search for files and code patterns in the repository",
    parameters: {
      type: "object",
      properties: {
        query: { type: "string", description: "The search query" },
        fileType: { type: "string", description: "Filter by file extension" }
      },
      required: ["query"]
    }
  }
];

Please analyze the attached codebase and provide recommendations.

302

est. tokens (code - ~3.5 c/t)

153

words

1,056

characters

Cost comparison - sorted by cheapest input

Model	Tokens	Input Cost	Output Cost	Context Used
Llama 3.3 70B $0.2 / $0.2 per 1M	302	< $0.0001	< $0.0001	0.24%
Gemini 2.5 Pro $1.25 / $5 per 1M	302	$0.0004	$0.0015	0.03%
GPT-4o $2.5 / $10 per 1M	302	$0.0008	$0.0030	0.24%
Claude Sonnet 4.6 $3 / $15 per 1M	302	$0.0009	$0.0045	0.15%
GPT-5.3 $4.81 / $4.81 per 1M	302	$0.0015	$0.0015	0.15%
Claude Opus 4.6 $15 / $75 per 1M	302	$0.0045	$0.0226	0.15%

Context window usage

Llama 3.3 70B

128K context

302 / 128,000

Gemini 2.5 Pro

1M context

302 / 1,000,000

GPT-4o

128K context

302 / 128,000

Claude Sonnet 4.6

200K context

302 / 200,000

GPT-5.3

200K context

302 / 200,000

Claude Opus 4.6

200K context

302 / 200,000