# Calcis

Pre-flight LLM API cost estimator.

Calcis estimates what an LLM API call will cost before you send it.
Paste a prompt, pick a model, and see token counts, cost breakdowns,
and at-scale projections.

## Supported providers

- OpenAI (GPT-5.4, GPT-5, GPT-4o, o3, o4-mini, and more)
- Anthropic (Claude Opus 4.7, Sonnet 4.6, Haiku 4.5)
- Google (Gemini 2.5 Pro, 2.5 Flash, 3.1 Pro)

## Features

- Web estimator with output prediction and confidence intervals
- GitHub Action for cost breakdowns as PR comments
- Public REST API (Pro tier and above)
- VS Code extension with status bar cost display
- Chrome extension overlay for ChatGPT, Claude, and Gemini
- Session cost simulator for multi-turn conversations
- Model recommendation engine
- 25+ model pricing comparison

## Pricing

- Free: token estimates, basic forecasting, no account needed
- Pro ($15/mo): LLM-assisted predictions, API access, model recommendations
- Max ($29/mo): prompt compression, higher volume
- Team ($40/seat/mo): pooled usage, team dashboards

## Links

- Website: https://www.calcis.dev
- Estimator: https://www.calcis.dev/estimator
- API docs: https://www.calcis.dev/api-docs
- Models: https://www.calcis.dev/models
- GitHub Action: https://github.com/marketplace/actions/calcis-llm-cost-estimate

## Full model pricing table

Prices are USD per 1,000,000 tokens. Context / max-output are token counts.
All rows verified against provider documentation; see calcis.dev/models/<id>
for the citation and last-verified date per model.

### Anthropic

| Model              | Input / 1M | Output / 1M | Context    | Max output |
|--------------------|-----------:|------------:|-----------:|-----------:|
| Claude Opus 4.7    |     $5.00  |     $25.00  | 1,000,000  |    128,000 |
| Claude Opus 4.6    |     $5.00  |     $25.00  | 1,000,000  |    128,000 |
| Claude Sonnet 4.6  |     $3.00  |     $15.00  | 1,000,000  |     64,000 |
| Claude Haiku 4.5   |     $1.00  |      $5.00  |   200,000  |     64,000 |
| Claude Opus 4.5    |     $5.00  |     $25.00  |   200,000  |     64,000 |
| Claude Sonnet 4.5  |     $3.00  |     $15.00  |   200,000  |     64,000 |
| Claude Opus 4.1    |    $15.00  |     $75.00  |   200,000  |     32,000 |

Note: Opus 4.7 applies a 1.15x tokenizer multiplier so cost forecasts
reflect the retrained tokenizer emitting 1.0-1.35x more tokens than
Opus 4.6 for the same text.

### Google Gemini

| Model                         | Input / 1M | Output / 1M | Context    | Long-ctx (>200K) in/out |
|-------------------------------|-----------:|------------:|-----------:|------------------------:|
| Gemini 3.1 Pro (preview)      |     $2.00  |     $12.00  | 1,000,000  | $4.00 / $18.00          |
| Gemini 3 Flash (preview)      |     $0.50  |      $3.00  | 1,000,000  | -                       |
| Gemini 3.1 Flash-Lite (prev.) |     $0.25  |      $1.50  | 1,000,000  | -                       |
| Gemini 2.5 Pro                |     $1.25  |     $10.00  | 2,000,000  | $2.50 / $15.00          |
| Gemini 2.5 Flash              |     $0.30  |      $2.50  | 1,000,000  | -                       |
| Gemini 2.5 Flash-Lite         |     $0.10  |      $0.40  | 1,000,000  | -                       |

Cached-input pricing is available on every Gemini row (10% of list).

### OpenAI

| Model         | Input / 1M | Cached in | Output / 1M | Context    | Max output |
|---------------|-----------:|----------:|------------:|-----------:|-----------:|
| GPT-5.4       |     $2.50  |   $0.25   |     $15.00  | 1,050,000  |    128,000 |
| GPT-5.4 mini  |     $0.75  |   $0.075  |      $4.50  |   400,000  |    128,000 |
| GPT-5.4 nano  |     $0.20  |   $0.02   |      $1.25  |   400,000  |    128,000 |
| GPT-5         |     $1.25  |   $0.125  |     $10.00  |   400,000  |    128,000 |
| GPT-5 mini    |     $0.25  |   $0.025  |      $2.00  |   400,000  |    128,000 |
| GPT-5 nano    |     $0.05  |   $0.005  |      $0.40  |   400,000  |    128,000 |
| GPT-4.1       |     $2.00  |   $0.50   |      $8.00  | 1,047,576  |     32,768 |
| GPT-4.1 mini  |     $0.40  |   $0.10   |      $1.60  | 1,047,576  |     32,768 |
| GPT-4o        |     $2.50  |   $1.25   |     $10.00  |   128,000  |     16,384 |
| GPT-4o mini   |     $0.15  |   $0.075  |      $0.60  |   128,000  |     16,384 |
| o3            |     $2.00  |   $0.50   |      $8.00  |   200,000  |    100,000 |
| o4-mini       |     $1.10  |   $0.275  |      $4.40  |   200,000  |    100,000 |

## API

Public REST endpoint: POST https://www.calcis.dev/api/v1/estimate
Auth: Bearer token (API key, Pro tier or above).

Request body:
{
  "prompt": "<text>",
  "model": "<modelId>",
  "expectedOutputTokens": 500
}

Response: { inputTokens, outputTokens, inputCost, outputCost, total }.

Full schema and examples at https://www.calcis.dev/api-docs.

## Data freshness

Calcis pricing rows are re-verified on a rolling schedule against the
provider's own rate card. Each row exposes a verified_at ISO date.
The same source URL is cited in the model page footer.