Grok 4.20 (Non-Reasoning) Token Counter & Cost Calculator
Count tokens for Grok 4.20 (Non-Reasoning) and estimate the exact API cost — $1.25
per 1M input tokens, $2.50 per 1M output tokens — using a real
o200k_base BPE tokenizer. Everything runs in your browser; nothing is uploaded.
Grok 4.20 (Non-Reasoning)
Counts are exact for OpenAI models (o200k_base is GPT-4o/4.1/5's tokenizer). For Claude, Gemini and other vendors — whose tokenizers are not public — treat the count as a close estimate (typically within ±15%).
Cost of this text across popular models
| Model | Input $/1M | Output $/1M | This text (input) | +500 output tokens |
|---|---|---|---|---|
| GPT-6.1 Terra | 1.00 | 5.00 | $0 | $0 |
| Kimi K3.1 Pro | 2.00 | 10.00 | $0 | $0 |
| MiniMax-M3.1-Flash | 0.15 | 0.60 | $0 | $0 |
| DeepSeek V4.1 Flash 1017 | 0.15 | 0.60 | $0 | $0 |
| Mercury 3 | 0.10 | 0.35 | $0 | $0 |
| Gemini 4 Argon | 2.00 | 10.00 | $0 | $0 |
| Muse Wonder | 4.00 | 20.00 | $0 | $0 |
| Claude Haiku 5.5 | 0.10 | 0.50 | $0 | $0 |
Close estimate (±15%): xAI does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation.
Cost lookup — Grok 4.20 (Non-Reasoning)
| Tokens | Cost on Grok 4.20 (Non-Reasoning) |
|---|---|
| 1K input tokens | 0.125¢ |
| 10K input tokens | $0.0125 |
| 100K input tokens | $0.1250 |
| 1M input tokens | $1.25 |
| 1K output tokens | 0.25¢ |
| 10K output tokens | $0.0250 |
FAQ
How accurate is the Grok 4.20 (Non-Reasoning) token count?
Close estimate (±15%): xAI does not publish its tokenizer, so this count uses OpenAI's o200k_base as an approximation. Paste your own text above to see the exact number for your prompt.
How is Grok 4.20 (Non-Reasoning) API cost calculated?
Cost = (input tokens ÷ 1,000,000) × $1.25 + (output tokens ÷ 1,000,000) × $2.50 — Grok 4.20 (Non-Reasoning)'s per-1M-token prices (xAI's official list price as recorded by models.dev).
See full Grok 4.20 (Non-Reasoning) pricing & benchmarks, or the main token counter for every model.