Paste any prompt to count its tokens, then see exactly what one call costs across GPT-5.5, Claude, Gemini, GLM, DeepSeek, Qwen and more — sorted cheapest first. Every model here is callable through one apimodels.app API and a single key.
Estimate of the model's reply length.
Token counts use the GPT o200k tokenizer; Claude / Gemini differ slightly (close estimate).
| Model | In $/1M | Out $/1M | Per call | Total |
|---|---|---|---|---|
deepseek-v4-flashcheapest OpenAI / Other · DeepSeek V4 Flash | $0.119 | $0.238 | $0.00012 | $0.00012 |
gemini-3-flash-preview Gemini · Gemini 3 Flash Preview | $0.111 | $0.662 | $0.00033 | $0.00033 |
deepseek-v4-pro OpenAI / Other · DeepSeek V4 Pro | $0.36975 | $0.7395 | $0.00037 | $0.00037 |
qwen3.7-plus OpenAI / Other · Qwen3.7 Plus | $0.8824 | $1.1765 | $0.00059 | $0.00059 |
MiniMax-M2.5 OpenAI / Other · MiniMax M2.5 | $0.442 | $1.765 | $0.00088 | $0.00088 |
claude-haiku-4-5-20251001 Claude · Claude Haiku 4.5 | $0.353 | $1.765 | $0.00088 | $0.00088 |
gemini-3.1-flash-lite Gemini · Gemini 3.1 Flash Lite | $0.375 | $2.25 | $0.00113 | $0.00113 |
gemini-3.1-pro-preview Gemini · Gemini 3.1 Pro Preview | $0.442 | $2.648 | $0.00132 | $0.00132 |
gemini-3-pro-preview Gemini · Gemini 3 Pro Preview | $0.442 | $2.648 | $0.00132 | $0.00132 |
grok-4.2 OpenAI / Other · Grok-4.2 | $0.618 | $3.089 | $0.00154 | $0.00154 |
gemini-3.5-flash Gemini · Gemini 3.5 Flash | $0.662 | $3.971 | $0.00199 | $0.00199 |
glm-5.2 OpenAI / Other · GLM-5.2 | $1.4 | $4 | $0.00200 | $0.00200 |
qwen3.7-max OpenAI / Other · Qwen3.7 Max | $1.7647 | $5.2941 | $0.00265 | $0.00265 |
claude-sonnet-4-6 Claude · Claude Sonnet 4.6 | $1.059 | $5.295 | $0.00265 | $0.00265 |
claude-sonnet-4-5-20250929 Claude · Claude Sonnet 4.5 | $1.059 | $5.295 | $0.00265 | $0.00265 |
claude-sonnet-4-20250514 Claude · Claude Sonnet 4 | $1.059 | $5.295 | $0.00265 | $0.00265 |
claude-opus-4-6 Claude · Claude Opus 4.6 | $1.765 | $8.824 | $0.00441 | $0.00441 |
claude-opus-4-5-20251101 Claude · Claude Opus 4.5 | $1.765 | $8.824 | $0.00441 | $0.00441 |
gpt-5-4 OpenAI / Other · GPT-5.4 | $1.5 | $9 | $0.00450 | $0.00450 |
claude-opus-4-8 Claude · Claude Opus 4.8 | $3 | $13 | $0.00650 | $0.00650 |
gpt-5-5 OpenAI / Other · GPT-5.5 | $3 | $18 | $0.00900 | $0.00900 |
claude-opus-4-7 Claude · Claude Opus 4.7 | $3.676 | $18.382 | $0.00919 | $0.00919 |
claude-opus-4-20250514 Claude · Claude Opus 4 | $5.295 | $26.471 | $0.0132 | $0.0132 |
Prices are apimodels.app rates (USD per 1M tokens) and may change; thinking variants share their base model's price.
Call any of these with one key — create an API key and start in minutes.
Get an API keyWe tokenize your text in the browser with the GPT o200k_base tokenizer (used by GPT-4o / GPT-5). Claude and Gemini tokenize slightly differently, so for those models treat the count as a close estimate — usually within ~10-20%.
cost = input_tokens × input price + output_tokens × output price. Prices are apimodels.app per-1M-token rates in USD, pulled from our live model registry. You are only charged for successful requests.
GPT-5.5 / GPT-5.4, Claude (Opus/Sonnet/Haiku), Gemini (Pro/Flash), plus GLM, DeepSeek, Qwen, MiniMax and Grok — all callable through one API and one key.
