NeuroGenesysWhat will this model cost to run?
Enter the tokens in and out of a typical call and how many calls you make a day. The calculator prices the workload on every model in the table at its current list price, cheapest first, including prompt-cache discounts and the higher rates some providers charge for long prompts. Prices last checked Nov 09, 2026.
Free · runs in your browser · updated
1 · Your workload
2 · What it costs
| Model | Per call | Per day | Per month (30 days) |
|---|---|---|---|
GPT-5 nano OpenAI | $0.00030 | $0.30 | $9.00 |
Claude Haiku 5.5 Anthropic | $0.00045 | $0.45 | $13.50 |
GPT-6 Luna OpenAI | $0.00045 | $0.45 | $13.50 |
GPT-4o mini OpenAI | $0.00060 | $0.60 | $18.00 |
Gemini 3.1 Flash-Lite Google | $0.0013 | $1.25 | $37.50 |
GPT-5 mini OpenAI | $0.0015 | $1.50 | $45.00 |
Gemini 3.5 Flash-Lite Google | $0.0019 | $1.85 | $55.50 |
Gemini 3.8 Flash Google intro price until 2026-12-31 | $0.0034 | $3.38 | $101 |
Claude Haiku 4.5 Anthropic | $0.0045 | $4.50 | $135 |
GPT-6.1 Terra OpenAI | $0.0045 | $4.50 | $135 |
Claude Sonnet 5.5 Anthropic | $0.0090 | $9.00 | $270 |
GPT-6.1 Sol OpenAI | $0.0090 | $9.00 | $270 |
Gemini 4 Argon Google intro price until 2026-11-30 | $0.0090 | $9.00 | $270 |
Gemini 3.1 Pro (preview) Google | $0.01 | $10.00 | $300 |
Claude Opus 5.5 Anthropic | $0.02 | $18.00 | $540 |
GPT-5.5 OpenAI | $0.03 | $25.00 | $750 |
Claude Fable 5.1 Anthropic | $0.04 | $45.00 | $1,350 |
GPT-6 Astra OpenAI | $0.04 | $45.00 | $1,350 |
Standard-tier list prices as of Nov 09, 2026. Excludes batch discounts, cache-write surcharges, taxes and tool fees. Tokenizers differ between providers, so the same text is a different number of tokens on each.
Questions
How are LLM API calls priced?
Per token, with separate rates for input (everything you send: system prompt, context, the user's message) and output (everything the model writes, including hidden reasoning tokens). Rates are quoted per million tokens. Output usually costs four to eight times as much as input.
What is a token?
A chunk of text the model reads as one unit, often part of a word. English prose averages about four characters, or three quarters of a word, per token. Each provider uses its own tokenizer, so the same text is a slightly different number of tokens on each.
How much does prompt caching save?
Input tokens read from the cache are billed at a fraction of the normal rate, often a tenth. It pays off when many calls share a long, identical prefix, such as a system prompt, tool definitions or a document. Providers may also charge extra to write to the cache, which this calculator leaves out.
Why does the price jump for long prompts?
Some models charge a higher rate for every token once a request's input passes a threshold, for example 200K or 272K tokens. The calculator switches to that rate automatically when your input tokens exceed it.
Are these prices current?
They are standard-tier list prices from each provider's pricing page, last checked Nov 09, 2026. Batch processing, committed-use discounts and regional pricing can be lower; check the provider before you budget.
Related
- Free toolTest-time compute cost estimator
- Free toolToken counter
- Free toolLLM API pricing, model by model
- Free toolAI Eval Sample Size CalculatorHow many eval items you need: the margin of error on one model's accuracy, and the sample size to detect a difference between two models, paired or not.
- Free toolLLM Training Compute CalculatorTraining FLOPs from parameters and tokens (6ND), GPU-hours at a realistic utilization, wall-clock time and cost — or the compute-optimal model for a budget.
- Free toolVRAM Calculator: Can I Run This LLM?GPU memory for an LLM at any quantization and context length — weights, KV cache and overhead — and which GPUs and Apple Silicon Macs can hold it.
- Free toolLLM Inference Speed Estimator (Tokens per Second)Tokens per second and time to first token for a model on a GPU or Mac, from memory bandwidth and compute, and how batching changes throughput.
- Free toolAgent Tool Count CalculatorHow often an agent picks the wrong tool as its library grows, from published benchmarks: every tool in the prompt, embedding or BM25 shortlists, with the measured range marked.
- Free toolLLM Judge Agreement CalculatorCheck an LLM-as-judge against human labels: Cohen's kappa with a 95% interval, the confusion matrix, sensitivity and specificity, and how many human labels the judge is worth.
- Free toolEU AI Act Risk CheckerAnswer a few questions to see your EU AI Act risk tier, the obligations with their articles, and the deadlines after the 2026 Digital Omnibus.
