LLM token counter & API cost calculator
Paste a prompt, set your volume, and see what it costs on every major AI model — side by side, with prompt caching and batch discounts.
0 characters0 words0 tokens (GPT o200k)
| Model | Per month |
|---|---|
| Claude Fable 5.1 | |
| Claude Opus 5.5 | |
| Claude Opus 5 | |
| Claude Sonnet 5.5 | |
| Claude Sonnet 5 | |
| Claude Haiku 5.5 | |
| Claude Sonnet 4.6 | |
| Claude Haiku 4.5 | |
| GPT-6 Astra | |
| GPT-6.1 Sol | |
| GPT-6.1 Terra | |
| GPT-6 Sol | |
| GPT-6 Luna | |
| GPT-5.6 Sol | |
| GPT-5.6 Terra | |
| GPT-5.6 Luna | |
| GPT-5.5 | |
| GPT-5.4 | |
| GPT-5.4 mini | |
| GPT-5.4 nano | |
| GPT-5 mini | |
| GPT-4.1 | |
| GPT-4o mini | |
| o3 | |
| o4-mini | |
| Gemini 4 Argon | |
| Gemini 3.8 Flash | |
| Gemini 3.6 Flash | |
| Gemini 3.5 Flash-Lite | |
| Gemini 3.1 Pro (preview) | |
| Gemini 3.1 Flash-Lite | |
| Gemini 2.5 Pro | |
| Gemini 2.5 Flash | |
| Gemini 2.5 Flash-Lite | |
| Grok 4.7 | |
| Grok 4.6 | |
| Grok 4.5 | |
| Grok 4.3 | |
| Grok 4.20 | |
| Grok Build 0.1 | |
| DeepSeek V4 Pro | |
| DeepSeek Flash | |
| Mistral Large 3 |
≈ = estimated token count: only OpenAI publishes its tokenizer. Claude counts use Anthropic’s published ratios; use the count_tokens API for an exact number.
Price per million tokens
Prices checked on October 28, 2026. USD, standard tier.
Anthropic (Claude)
| Model | Input | Cached input | Output | Batch |
|---|---|---|---|---|
Claude Fable 5.1 claude-fable-5-1 | $10 | $0.25 | $50 | −50% |
Claude Opus 5.5 claude-opus-5-5 | $4 | $0.2 | $20 | −50% |
Claude Opus 5 claude-opus-5 | $5 | $0.5 | $25 | −50% |
Claude Sonnet 5.5 claude-sonnet-5-5 | $2 | $0.1 | $10 | −50% |
Claude Sonnet 5 claude-sonnet-5 | $2 | $0.2 | $10 | −50% |
Claude Haiku 5.5 claude-haiku-5-5Above 100K tokens: $0.5 / $2.5 | $0.1 | $0.01 | $0.5 | −50% |
Claude Sonnet 4.6 claude-sonnet-4-6 | $3 | $0.3 | $15 | −50% |
Claude Haiku 4.5 claude-haiku-4-5 | $1 | $0.1 | $5 | −50% |
Sources: platform.claude.com
OpenAI (GPT)
| Model | Input | Cached input | Output | Batch |
|---|---|---|---|---|
GPT-6 Astra gpt-6-astraAbove 272K tokens: $20 / $75 | $10 | $1 | $50 | −50% |
GPT-6.1 Sol gpt-6.1-solAbove 272K tokens: $4 / $15 | $2 | $0.1 | $10 | −50% |
GPT-6.1 Terra gpt-6.1-terraAbove 272K tokens: $2 / $7.5 | $1 | $0.05 | $5 | −50% |
GPT-6 Sol gpt-6-solAbove 272K tokens: $4 / $15 | $2 | $0.2 | $10 | −50% |
GPT-6 Luna gpt-6-lunaAbove 272K tokens: $0.2 / $0.75 | $0.1 | $0.01 | $0.5 | −50% |
GPT-5.6 Sol gpt-5.6-solAbove 272K tokens: $8 / $30 Promotional price, available at least through November 21, 2026. | $4 | $0.4 | $20 | −50% |
GPT-5.6 Terra gpt-5.6-terra | $2 | $0.2 | $12 | −50% |
GPT-5.6 Luna gpt-5.6-luna | $0.2 | $0.02 | $1.2 | −50% |
GPT-5.5 gpt-5.5Price for prompts up to 272K tokens; longer prompts cost more. | $5 | $0.5 | $30 | −50% |
GPT-5.4 gpt-5.4Price for prompts up to 272K tokens; longer prompts cost more. | $2.5 | $0.25 | $15 | −50% |
GPT-5.4 mini gpt-5.4-mini | $0.75 | $0.075 | $4.5 | −50% |
GPT-5.4 nano gpt-5.4-nano | $0.2 | $0.02 | $1.25 | −50% |
GPT-5 mini gpt-5-mini | $0.25 | $0.025 | $2 | −50% |
GPT-4.1 gpt-4.1 | $2 | $0.5 | $8 | −50% |
GPT-4o mini gpt-4o-mini | $0.15 | $0.075 | $0.6 | −50% |
o3 o3 | $2 | $0.5 | $8 | −50% |
o4-mini o4-mini | $1.1 | $0.275 | $4.4 | −50% |
Sources: developers.openai.com
Google (Gemini)
| Model | Input | Cached input | Output | Batch |
|---|---|---|---|---|
Gemini 4 Argon gemini-4-argonLaunch price through November 30, 2026; $4 / $20 from December 1, 2026. | $2 | $0.1 | $10 | −50% |
Gemini 3.8 Flash gemini-3.8-flashPrice doubles in January 2027 ($1.50 / $7.50). | $0.75 | $0.075 | $3.75 | −50% |
Gemini 3.6 Flash gemini-3.6-flashPrice doubles in January 2027 ($1.50 / $7.50). | $0.75 | $0.075 | $3.75 | −50% |
Gemini 3.5 Flash-Lite gemini-3.5-flash-lite | $0.3 | $0.03 | $2.5 | −50% |
Gemini 3.1 Pro (preview) gemini-3.1-pro-previewAbove 200K tokens: $4 / $18 | $2 | $0.2 | $12 | −50% |
Gemini 3.1 Flash-Lite gemini-3.1-flash-lite | $0.25 | $0.025 | $1.5 | −50% |
Gemini 2.5 Pro gemini-2.5-proAbove 200K tokens: $2.5 / $15 | $1.25 | $0.125 | $10 | −50% |
Gemini 2.5 Flash gemini-2.5-flash | $0.3 | $0.03 | $2.5 | −50% |
Gemini 2.5 Flash-Lite gemini-2.5-flash-lite | $0.1 | $0.01 | $0.4 | −50% |
Sources: ai.google.dev
xAI (Grok)
| Model | Input | Cached input | Output | Batch |
|---|---|---|---|---|
Grok 4.7 grok-4.7Above 200K tokens: $4 / $12 | $2 | $0.5 | $6 | −20% |
Grok 4.6 grok-4.6Above 200K tokens: $4 / $12 | $2 | $0.5 | $6 | −20% |
Grok 4.5 grok-4.5Above 200K tokens: $4 / $12 | $2 | $0.3 | $6 | −20% |
Grok 4.3 grok-4.3Above 200K tokens: $2.5 / $5 | $1.25 | $0.2 | $2.5 | −20% |
Grok 4.20 grok-4.20Above 200K tokens: $2.5 / $5 | $1.25 | $0.2 | $2.5 | −20% |
Grok Build 0.1 grok-build-0.1Above 200K tokens: $2 / $4 | $1 | $0.2 | $2 | — |
Sources: docs.x.ai
DeepSeek
| Model | Input | Cached input | Output | Batch |
|---|---|---|---|---|
DeepSeek V4 Pro deepseek-v4-proPeak price. Off-peak is half: outside 01–04 and 06–10 UTC on weekdays, plus weekends and Chinese public holidays. | $1.32 | $0.044 | $3.96 | — |
DeepSeek Flash deepseek-flashPeak price. Off-peak is half: outside 01–04 and 06–10 UTC on weekdays, plus weekends and Chinese public holidays. | $0.3 | $0.006 | $1.2 | — |
Sources: api-docs.deepseek.com
Mistral
| Model | Input | Cached input | Output | Batch |
|---|---|---|---|---|
Mistral Large 3 mistral-large-3 | $0.5 | — | $1.5 | −50% |
Sources: mistral.ai
Frequently asked questions
What is a token?
A token is a piece of text a language model reads or writes — often part of a word. In English, 1,000 tokens is roughly 750 words. APIs bill per million tokens, with separate prices for input (your prompt) and output (the answer).
Why do Claude and GPT count different tokens for the same text?
Each company uses its own tokenizer. Anthropic says Claude Opus 4.7 and later produce about 30% more tokens than earlier Claude models for the same text, so comparing price per token alone is misleading — compare the cost of the same prompt, as this calculator does.
Are the token counts exact?
For GPT-4o, GPT-4.1, the o-series and GPT-5, yes: we use OpenAI’s public o200k tokenizer in your browser. Other providers don’t publish their tokenizers, so their counts are estimates (marked ≈). For an exact Claude count, use Anthropic’s count_tokens API.
How do prompt caching and the Batch API lower the cost?
Cached input is billed at a fraction of the normal price (10% on most Claude models, less on some). The Batch API halves prices for requests that can wait up to 24 hours. Use the slider and checkbox to see the effect.