Compare a long document pass on Claude Fable 5.1
Sample
Input tokens: 45,000 Output tokens: 2,000
What you get
Useful for PDF or codebase summaries where input dominates the bill — switch Fable vs Sonnet to compare.
Claude API Cost Estimator
Plan your Anthropic budget with precision. This estimator loads Claude Fable 5.1, Opus, Sonnet, Haiku, and other Anthropic tiers from OpenRouter’s live model catalog, then projects spend from your token and volume assumptions. Live model lists and $/1M rates load from OpenRouter’s public models API (https://openrouter.ai/api/v1/models), with TensorFeed and a local snapshot as fallbacks. New releases (for example Gemini 3.8 Flash or Claude Fable 5.1) appear automatically when OpenRouter lists them.
Claude API Cost Estimator
Anthropic · Local registry · as of 2026-09-02 · 6 models · refreshing…
Pricing data: OpenRouter models
Model Pricing (per 1M tokens)
| Model | Input | Output | Thinking |
|---|---|---|---|
| Claude Fable 5.1 | $10.00 | $50.00 | $50.00 |
| Claude Fable 5 | $10.00 | $50.00 | $50.00 |
| Claude Opus 5 | $5.00 | $25.00 | — |
| Claude Opus 4.8 | $5.00 | $25.00 | — |
| Claude Sonnet 5 | $2.00 | $10.00 | — |
| Claude Haiku 4.5 | $1.00 | $5.00 | — |
Per Request
$0.0350
Daily
$3.50
Monthly
$105.00
Annual
$1260.00
How to Use This Tool
- Choose the Claude model tier you need (Fable, Opus, Sonnet, Haiku, …).
- Enter your expected input tokens per request.
- Enter your expected output tokens per request.
- Set your request volume (requests per day).
- Review cost projections and compare tiers in the pricing table.
Features
- Live Anthropic models via OpenRouter (incl. Claude Fable 5.1)
- Input/output token cost separation
- Monthly and annual spend projections
- Tier comparison table
- Adapts when Anthropic ships new Claude versions
Example
Frequently Asked Questions
What is Claude Fable 5.1?
Fable is Anthropic’s frontier line listed on OpenRouter with higher $/1M rates than Sonnet/Haiku. Use it when you need maximum reasoning quality; pick Sonnet or Haiku for everyday cost efficiency.
How do Opus and Sonnet prices compare?
Opus is usually the premium reasoning tier; Sonnet targets balanced quality and cost; Haiku is the budget/low-latency option. Exact $/1M rates come from the live pricing table.
Will Claude updates appear automatically?
Yes. When OpenRouter adds or updates Anthropic models, this estimator’s dropdown refreshes with them.
Related Tools
GPT Token & API Cost Calculator
Calculate API costs for current OpenAI GPT models with live OpenRouter pricing.
Gemini Token & API Cost Calculator
Calculate costs for Gemini 3.8 Flash and other current Google models with live pricing.
RAG vs Fine-Tuning Cost Comparison Calculator
Compare RAG and fine-tuning costs to find the optimal approach for your project.
Llama Self-Hosting Cost Estimator
Estimate GPU and cloud costs for self-hosting Llama models.
AI Token Counter & API Cost Calculator
Count tokens and estimate API costs across major LLMs — models update from OpenRouter live pricing.