AI Token Counter
Token counts and cost estimates for GPT, Claude, etc.
Cost Comparison
Estimated cost for 0 tokens as input. Pricing as of Feb 2026.
| Model | Input $/1M | Output $/1M | Context | Est. Input Cost |
|---|---|---|---|---|
| Anthropic | ||||
| Claude Opus 4.6 | $5.00 | $25.00 | 200K | — |
| Claude Sonnet 4.5 | $3.00 | $15.00 | 200K | — |
| Claude Haiku 4.5 | $1.00 | $5.00 | 200K | — |
| OpenAI | ||||
| GPT-5 | $1.25 | $10.00 | 400K | — |
| GPT-4.1 | $2.00 | $8.00 | 1M | — |
| GPT-4o | $2.50 | $10.00 | 128K | — |
| o3 | $2.00 | $8.00 | 200K | — |
| o4-mini | $1.10 | $4.40 | 200K | — |
| Gemini 3 Pro | $2.00 | $12.00 | 1M | — |
| Gemini 2.5 Pro | $1.25 | $10.00 | 1M | — |
| Gemini 2.5 Flash | $0.30 | $2.50 | 1M | — |
| xAI | ||||
| Grok 4 | $3.00 | $15.00 | 131K | — |
| Grok 4 Fast | $0.20 | $0.50 | 2M | — |
| DeepSeek | ||||
| DeepSeek R1 | $0.55 | $2.19 | 64K | — |
| DeepSeek V3 | $0.27 | $1.10 | 64K | — |
| Meta (via API) | ||||
| Llama 4 Maverick | $0.22 | $0.85 | 1M | — |
How Estimation Works
Token counts are estimated using a character-based heuristic (~4 characters per token for English text). This is approximately 80% accurate for typical English prose and code. Actual token counts vary by model since each provider uses a different tokenizer (BPE vocabulary).
For billing-critical accuracy, use each provider's official token counting API.
What are LLM Tokens?
LLMs break text into tokens, which are roughly word fragments. A typical English word is 1-2 tokens. API pricing is per-token, so knowing your token count lets you estimate costs before sending a request.