Data
LLM API cost calculator
Enter your monthly token volume once, compare every current model's bill side by side. The link updates as you type, so you can send someone the exact scenario instead of describing it.
Qwen3.7-Flash is the cheapest at $0.06/month - 491.1x cheaper than GPT-5.6 Cyber at $27.50/month.
| Model | Provider | Input cost | Output cost | Total/month |
|---|---|---|---|---|
| Qwen3.7-Flash | Alibaba (Qwen) | $0.03 | $0.03 | $0.06 |
| Command R7B | Cohere | $0.04 | $0.03 | $0.07 |
| Ministral 3 3B | Mistral | $0.10 | $0.02 | $0.12 |
| Ministral 3 8B | Mistral | $0.15 | $0.03 | $0.18 |
| Gemini 2.5 Flash-Lite | $0.10 | $0.08 | $0.18 | |
| GPT-6 Luna | OpenAI | $0.10 | $0.10 | $0.20 |
| Ministral 3 14B | Mistral | $0.20 | $0.04 | $0.24 |
| Qwen3.8-Flash | Alibaba (Qwen) | $0.15 | $0.09 | $0.24 |
| Qwen3.8-Omni-Flash | Alibaba (Qwen) | $0.15 | $0.09 | $0.24 |
| Mistral Small 4 | Mistral | $0.15 | $0.12 | $0.27 |
| Command R (08-2024) | Cohere | $0.15 | $0.12 | $0.27 |
| GPT-5.6 Luna | OpenAI | $0.20 | $0.24 | $0.44 |
| Codestral | Mistral | $0.30 | $0.18 | $0.48 |
| DeepSeek V4.1 Flash | DeepSeek | $0.30 | $0.24 | $0.54 |
| Qwen3.7-Plus | Alibaba (Qwen) | $0.40 | $0.32 | $0.72 |
| Gemini 3.5 Flash-Lite | $0.30 | $0.50 | $0.80 | |
| Gemini 2.5 Flash | $0.30 | $0.50 | $0.80 | |
| Mistral Large 3 | Mistral | $0.50 | $0.30 | $0.80 |
| Grok Build 0.1 | xAI | $1.00 | $0.40 | $1.40 |
| Gemini 3.8 Flash promo | $0.75 | $0.75 | $1.50 | |
| Gemini 3.7 Flash promo | $0.75 | $0.75 | $1.50 | |
| Gemini 3.6 Flash promo | $0.75 | $0.75 | $1.50 | |
| Grok 4.3 | xAI | $1.25 | $0.50 | $1.75 |
| Grok 4.20 (reasoning) | xAI | $1.25 | $0.50 | $1.75 |
| Grok 4.20 (non-reasoning) | xAI | $1.25 | $0.50 | $1.75 |
| Grok 4.20 Multi-agent | xAI | $1.25 | $0.50 | $1.75 |
| Claude Haiku 4.5 | Anthropic | $1.00 | $1.00 | $2.00 |
| Gemini Robotics ER 2 Preview promo | $1.00 | $1.00 | $2.00 | |
| Gemini Robotics ER 2 Streaming Preview promo | $1.00 | $1.00 | $2.00 | |
| Muse Spark 1.3 | Meta | $1.25 | $0.85 | $2.10 |
| Muse Spark 1.2 | Meta | $1.25 | $0.85 | $2.10 |
| DeepSeek V4 Pro | DeepSeek | $1.32 | $0.79 | $2.11 |
| GLM 5.2 | Mistral | $1.40 | $0.88 | $2.28 |
| GLM 5.3 | Mistral | $1.40 | $0.88 | $2.28 |
| Mistral Medium 3.5 | Mistral | $1.50 | $1.50 | $3.00 |
| Grok 4.6 | xAI | $2.00 | $1.20 | $3.20 |
| Grok 4.7 | xAI | $2.00 | $1.20 | $3.20 |
| Grok 4.5 | xAI | $2.00 | $1.20 | $3.20 |
| Qwen3.8-Max | Alibaba (Qwen) | $2.00 | $1.20 | $3.20 |
| Gemini 2.5 Pro | $1.25 | $2.00 | $3.25 | |
| Gemini 3.5 Flash | $1.50 | $1.80 | $3.30 | |
| GPT-6.1 Sol | OpenAI | $2.00 | $2.00 | $4.00 |
| GPT-6 Sol | OpenAI | $2.00 | $2.00 | $4.00 |
| Claude Sonnet 5.5 | Anthropic | $2.00 | $2.00 | $4.00 |
| Claude Sonnet 5 | Anthropic | $2.00 | $2.00 | $4.00 |
| Qwen3.7-Max | Alibaba (Qwen) | $2.50 | $1.50 | $4.00 |
| GPT-5.6 Terra | OpenAI | $2.00 | $2.40 | $4.40 |
| Gemini 3.1 Pro Preview | $2.00 | $2.40 | $4.40 | |
| Command A | Cohere | $2.50 | $2.00 | $4.50 |
| Command R+ (08-2024) | Cohere | $2.50 | $2.00 | $4.50 |
| GPT-5.3 Codex | OpenAI | $1.75 | $2.80 | $4.55 |
| Claude Sonnet 4.6 | Anthropic | $3.00 | $3.00 | $6.00 |
| GPT-5.6 Sol promo | OpenAI | $4.00 | $4.00 | $8.00 |
| Claude Opus 5.5 | Anthropic | $4.00 | $4.00 | $8.00 |
| GPT-Rosalind restricted | OpenAI | $5.00 | $5.00 | $10.00 |
| Claude Opus 5 | Anthropic | $5.00 | $5.00 | $10.00 |
| Claude Opus 4.8 | Anthropic | $5.00 | $5.00 | $10.00 |
| Claude Opus 4.7 | Anthropic | $5.00 | $5.00 | $10.00 |
| Claude Opus 4.6 | Anthropic | $5.00 | $5.00 | $10.00 |
| Claude Opus 4.5 | Anthropic | $5.00 | $5.00 | $10.00 |
| ChatGPT (chat-latest) | OpenAI | $5.00 | $6.00 | $11.00 |
| GPT-6 Astra | OpenAI | $10.00 | $10.00 | $20.00 |
| Claude Fable 5.1 | Anthropic | $10.00 | $10.00 | $20.00 |
| Claude Mythos 5.1 invite-only | Anthropic | $10.00 | $10.00 | $20.00 |
| Claude Fable 5 | Anthropic | $10.00 | $10.00 | $20.00 |
| Claude Mythos 5 | Anthropic | $10.00 | $10.00 | $20.00 |
| GPT-5.6 Cyber restricted | OpenAI | $12.50 | $15.00 | $27.50 |
6 of these estimates use a promotional price: GPT-5.6 Sol, Gemini 3.8 Flash, Gemini 3.7 Flash, Gemini 3.6 Flash, Gemini Robotics ER 2 Preview and Gemini Robotics ER 2 Streaming Preview. Each model page shows the date and, where the provider publishes it, the list price; the calculator never fills in a list price the provider has not printed.
Prices are the same verified numbers as /api-pricing/ - see that page's methodology. Cache hit rate applies only to input tokens, at each model's own cached-input rate; where a model publishes no cache price, the cached share is charged at its input price. Models with no published USD price aren't included - there's nothing to multiply.
Analysis
What the dataset shows when it is read across providers.
- How LLM API pricing worksThe guide: tokens, cache reads and writes, long-prompt tiers, Batch and Fast mode, region, peak hours, promotions and hosts, each on a real row of the dataset.
- Same List Price, Different Bill: Five Pairs of LLM APIs Where the Workload Decides What You PayClaude Sonnet 5.5 and GPT-6.1 Sol both list at $2 / $10, yet a long-document workload costs $250 on one and $475 on the other. Five pairs, every assumption shown.
- Prompt Caching Is Not 10% Everywhere: What a Cache Hit Costs Across Eight Providers49 of the 64 current priced models publish a cache-hit price; four providers charge 10% of input. Anthropic, DeepSeek, xAI, Alibaba and Meta differ, with dates.
- The Second Price List: What Batch, Flex, Priority and Data-Sharing Discounts Cost Across Seven ProvidersHalf price to wait, double to skip the queue, 12.5× less input to share data: the second price lists of seven LLM providers, read by hand on September 16, 2026.
- Five Things Decide What You Pay for a Model, and Only One of Them Is the ModelHost, time of day, promotions, region and request size move the price of the same model by anything from 1.2× to 10×. Five verified cases, with dates and sources.
- OpenAI's Pricing Page Has Four Tabs That Look the Same in Plain Text. We Published the Wrong One for Seven Days.From September 3 to 11, 2026 this site listed GPT-5.6 Sol, Terra and Luna at half their price, read from the Batch tab. What went wrong, what caught it, and what is still not caught.