1. Paste a typical prompt
Enter a representative prompt, document, or chat message. Its input tokens drive the input cost for every model.
LLM API Cost Calculator
Estimate and compare API cost across models in your browser. Paste a prompt, set expected output and monthly call volume, and see per-call and monthly cost for every model — with the cheapest priced option highlighted. Token counts are Exact for OpenAI and clearly labeled Estimated elsewhere.
Private by default · No signup · Local token counting where supported · Exact and estimated results clearly labeled
Your text is processed in your browser for supported local tokenizers. We do not store pasted prompts.
Model comparison
Compare the current prompt, expected output, and monthly call volume across every supported model.
| Model | Accuracy | Prompt tokens | Per-call cost | Monthly cost | Context fit |
|---|---|---|---|---|---|
| OpenAI · GPT-5.5gpt-5.5 | Exact | — | — | — | — |
| OpenAI · GPT-5.4gpt-5.4 | Exact | — | — | — | — |
| OpenAI · GPT-5.4 minigpt-5.4-mini | Exact | — | — | — | — |
| OpenAI · GPT-5.4 nanogpt-5.4-nano | Exact | — | — | — | — |
| Anthropic · Claude Fable 5claude-fable-5 | Estimated | — | — | — | — |
| Anthropic · Claude Opus 4.8claude-opus-4-8 | Estimated | — | — | — | — |
| Anthropic · Claude Sonnet 5claude-sonnet-5 | Estimated | — | — | — | — |
| Anthropic · Claude Sonnet 4.6claude-sonnet-4-6 | Estimated | — | — | — | — |
| Anthropic · Claude Opus 4.6claude-opus-4-6 | Estimated | — | — | — | — |
| Anthropic · Claude Haiku 4.5claude-haiku-4-5-20251001 | Estimated | — | — | — | — |
| Google · Gemini 3.5 Flashgemini-3.5-flash | Estimated | — | — | — | — |
| Google · Gemini 3.1 Pro Previewgemini-3.1-pro-preview | Estimated | — | — | — | — |
| Google · Gemini 3.1 Flash-Litegemini-3.1-flash-lite | Estimated | — | — | — | — |
| Google · Gemini 3 Flash Previewgemini-3-flash-preview | Estimated | — | — | — | — |
| Google · Gemini 2.5 Progemini-2.5-pro | Estimated | — | — | — | — |
| Google · Gemini 2.5 Flashgemini-2.5-flash | Estimated | — | — | — | — |
| Google · Gemini 2.5 Flash-Litegemini-2.5-flash-lite | Estimated | — | — | — | — |
| Mistral · Mistral Largemistral-large-latest | Estimated | — | — | — | — |
| Mistral · Mistral Mediummistral-medium-latest | Estimated | — | — | — | — |
| Mistral · Mistral Smallmistral-small-latest | Estimated | — | — | — | — |
| Mistral · Ministral 14Bministral-14b-latest | Estimated | — | — | — | — |
| DeepSeek · DeepSeek V4 Flashdeepseek-v4-flash | Estimated | — | — | — | — |
| DeepSeek · DeepSeek V4 Prodeepseek-v4-pro | Estimated | — | — | — | — |
| xAI · Grok 4.3grok-4.3 | Estimated | — | — | — | — |
| xAI · Grok Build 0.1grok-build-0.1 | Estimated | — | — | — | — |
| Meta · Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct | Estimated | — | — | — | — |
| Meta · Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct | Estimated | — | — | — | — |
Estimated rows use one local OpenAI-compatible proxy token count, so real provider counts can differ. Pricing estimate based on public model pricing. Check provider pricing before production use.
Model pricing table
Published API list prices per 1M tokens for every supported model, from the local model list. This is a static reference — use the calculator above to price your own prompt.
| Model | Input / 1M | Cached input / 1M | Output / 1M | Context window | Pricing last checked |
|---|---|---|---|---|---|
| OpenAI · GPT-5.5gpt-5.5 | $5.00 | $0.50 | $30.00 | 1,000,000 | 2026-07-08 |
| OpenAI · GPT-5.4gpt-5.4 | $2.50 | $0.25 | $15.00 | 1,000,000 | 2026-07-08 |
| OpenAI · GPT-5.4 minigpt-5.4-mini | $0.75 | $0.075 | $4.50 | 400,000 | 2026-07-08 |
| OpenAI · GPT-5.4 nanogpt-5.4-nano | $0.20 | $0.02 | $1.25 | 400,000 | 2026-07-08 |
| Anthropic · Claude Fable 5claude-fable-5 | $10.00 | $1.00 | $50.00 | 1,000,000 | 2026-07-08 |
| Anthropic · Claude Opus 4.8claude-opus-4-8 | $5.00 | $0.50 | $25.00 | 1,000,000 | 2026-07-08 |
| Anthropic · Claude Sonnet 5claude-sonnet-5 | $2.00 | $0.20 | $10.00 | 1,000,000 | 2026-07-08 |
| Anthropic · Claude Sonnet 4.6claude-sonnet-4-6 | $3.00 | $0.30 | $15.00 | 1,000,000 | 2026-07-08 |
| Anthropic · Claude Opus 4.6claude-opus-4-6 | $5.00 | $0.50 | $25.00 | 1,000,000 | 2026-07-08 |
| Anthropic · Claude Haiku 4.5claude-haiku-4-5-20251001 | $1.00 | $0.10 | $5.00 | 200,000 | 2026-07-08 |
| Google · Gemini 3.5 Flashgemini-3.5-flash | $1.50 | $0.15 | $9.00 | 1,048,576 | 2026-07-08 |
| Google · Gemini 3.1 Pro Previewgemini-3.1-pro-preview | $2.00 | $0.20 | $12.00 | 1,048,576 | 2026-07-08 |
| Google · Gemini 3.1 Flash-Litegemini-3.1-flash-lite | $0.25 | $0.025 | $1.50 | 1,048,576 | 2026-07-08 |
| Google · Gemini 3 Flash Previewgemini-3-flash-preview | $0.50 | $0.05 | $3.00 | 1,048,576 | 2026-07-08 |
| Google · Gemini 2.5 Progemini-2.5-pro | $1.25 | $0.125 | $10.00 | 1,048,576 | 2026-07-08 |
| Google · Gemini 2.5 Flashgemini-2.5-flash | $0.30 | $0.03 | $2.50 | 1,048,576 | 2026-07-08 |
| Google · Gemini 2.5 Flash-Litegemini-2.5-flash-lite | $0.10 | $0.01 | $0.40 | 1,048,576 | 2026-07-08 |
| Mistral · Mistral Largemistral-large-latest | $0.50 | $0.05 | $1.50 | 256,000 | 2026-07-08 |
| Mistral · Mistral Mediummistral-medium-latest | $1.50 | $0.15 | $7.50 | 256,000 | 2026-07-08 |
| Mistral · Mistral Smallmistral-small-latest | $0.15 | $0.015 | $0.60 | 256,000 | 2026-07-08 |
| Mistral · Ministral 14Bministral-14b-latest | $0.20 | $0.02 | $0.20 | 256,000 | 2026-07-08 |
| DeepSeek · DeepSeek V4 Flashdeepseek-v4-flash | $0.14 | $0.0028 | $0.28 | 1,000,000 | 2026-07-08 |
| DeepSeek · DeepSeek V4 Prodeepseek-v4-pro | $0.435 | $0.003625 | $0.87 | 1,000,000 | 2026-07-08 |
| xAI · Grok 4.3grok-4.3 | $1.25 | $0.20 | $2.50 | 1,000,000 | 2026-07-08 |
| xAI · Grok Build 0.1grok-build-0.1 | $1.00 | $0.20 | $2.00 | 256,000 | 2026-07-08 |
| Meta · Llama 4 Scoutmeta-llama/Llama-4-Scout-17B-16E-Instruct | Pricing varies by host | 10,000,000 | — | ||
| Meta · Llama 4 Maverickmeta-llama/Llama-4-Maverick-17B-128E-Instruct | Pricing varies by host | 1,000,000 | — | ||
List prices are each provider's standard, non-batch tier. Some models publish long-context, cached, or promotional rates — check the provider before production use.
Pricing estimate based on public model pricing. Check provider pricing before production use.
Plan your monthly API budget
Four steps to turn a prompt into a monthly cost estimate you can compare across providers.
2. Set expected output tokens
Estimate how many tokens the model will generate. Output tokens are usually priced higher than input, so this matters.
3. Set calls per month
Enter how many times you expect to call the API each month to turn a per-call cost into a monthly estimate.
4. Compare and sort by cost
The comparison table prices the same prompt across every model. Sort by per-call or monthly cost, and the cheapest priced model is highlighted.
Read the estimate honestly
Costs are estimates from public list prices, and token counts for non-OpenAI models are Estimated. List prices use each provider's standard tier — some models have long-context, cached, or promotional rates — so confirm with the provider before committing a budget.
LLM API cost FAQ
Answers about estimating monthly cost, finding the cheapest model, and how pricing works.
Can I estimate monthly API cost?
Yes. Enter expected output tokens and calls per month. The calculator combines those values with the selected model's public pricing to estimate per-call and monthly cost.
Which model is cheapest?
The cheapest model depends on your prompt size, expected output length, and monthly volume. Use the comparison table to price the same text across all supported models; models without first-party pricing show Pricing varies by host.
What are input vs output tokens, and why is output usually more expensive?
Input tokens are the prompt and context you send to the model. Output tokens are the model's response. Providers often price output tokens higher because generating text costs more compute than reading input.
What is cached input pricing?
Some providers discount repeated input that can be reused from cache. When a model publishes cached-input pricing, the calculator shows it separately. If a model does not publish it, the row stays empty or unavailable.
How do I reduce LLM API cost?
Remove repeated instructions, shorten examples, reduce expected output length, use smaller models for simple tasks, use cached input when available, and avoid sending full documents when a retrieved excerpt is enough.
Is this calculator exact?
It is Exact only for supported OpenAI encodings counted locally with gpt-tokenizer. Other providers are labeled Estimated and use an OpenAI-compatible tokenizer as a proxy, so real provider counts can vary.
Is my prompt uploaded to your server?
No. Pasted text is processed in your browser. This site has no accounts, saved prompt history, analytics scripts, ad scripts, or server-side text processing.
More token tools
Focus on one provider with the OpenAI, Claude, or Gemini token calculators, or start from the main LLM token calculator.