CostForge
AI API Cost Calculator
Compare Claude vs GPT vs Gemini API costs side-by-side. Estimate daily and monthly spend with browser-side calculations and no account requirement.
CostForge is a free interactive LLM API token cost calculator and FinOps estimator. Compare per-request, daily, and monthly API spend across 30 frontier models from 7 providers (Anthropic Claude Sonnet 5.5 & Opus 5.5, OpenAI Sol 6.1 & GPT-6 Astra, Google Gemini 3.8 Flash & 3.5 Pro, DeepSeek V4 Pro, Moonshot Kimi K3, xAI Grok 4.7, and Mistral Medium 3.5), including 90% prompt caching and 50% batch API discounts.
📝 Token Estimator
💰 Prompt Caching Savings
💡 Cost Optimization Tips
Why CostForge?
30 Models Compared
Side-by-side pricing for Claude 5.5, Sol 6.1 & GPT-6 Astra, Gemini 3.8, DeepSeek V4, Kimi K3, Grok 4.7, and Mistral — 7 providers in one view.
Live Calculations
Drag sliders or type exact numbers. Per-request, daily, and monthly costs recalculate as inputs change.
7 Use Case Presets
Pre-configured token counts for Chatbot, Code Assistant, Data Processing, RAG Pipeline, Content Generation, Summarization, and Agentic Workflows.
Batch vs Standard
Toggle between standard and batch pricing. See exactly how much you save with async/batch processing for each provider.
Visual Cost Bars
Horizontal bars make it easy to compare relative costs at a glance. The lowest-cost result is highlighted.
Optimization Tips
Expert advice on reducing API costs: prompt caching, model routing, token compression, and budget monitoring strategies.
Pricing Snapshot
Pricing data reflects published rates from Anthropic, OpenAI, Google, DeepSeek, Moonshot AI, xAI, and Mistral as of October 2026. Verify against official pricing pages before commitment.
Browser-Side Math
Calculations run in your browser session. Avoid entering sensitive credentials or proprietary payloads.
Frequently Asked Questions
Which AI models does the calculator support?
CostForge supports the latest 2026 API pricing across 30 frontier models from 7 providers: Google Gemini (Gemini 3.8 Flash, Gemini 3.6 Flash, 3.5 Pro), Anthropic Claude (Claude Sonnet 5.5, Claude Opus 5.5, Sonnet 5 permanent $2/$10 pricing, Fable 5, Opus 4.8, Haiku 4.5), OpenAI (Sol 6.1, GPT-6 Astra, OpenAI Agents API, GPT-5.6 series, GPT-4.1, o3), DeepSeek (DeepSeek V4 Pro GA, V4 Flash), Moonshot Kimi K3, xAI (Grok 4.7, Grok 4.5), and Mistral.
How is the monthly API cost calculated?
The monthly cost is calculated by multiplying your estimated daily input and output tokens by 30 days, using the exact per-million token pricing from the respective AI providers.
Are prompt caching and batch discounts included?
Yes, we factor in Anthropic 90% prompt caching discounts ($0.20/M read rate on Sonnet 5.5), Google Gemini 75% context cache savings, DeepSeek 93% MLA KV-cache savings, and 50% batch API discounts across OpenAI and Anthropic.
How much do Claude Sonnet 5.5, GPT-6 Astra / Sol 6.1, and Gemini 3.8 Flash cost per 1M tokens?
In October 2026, Claude Sonnet 5.5 costs $2.00/M input tokens ($0.20/M cached) and $10.00/M output tokens. OpenAI Sol 6.1 costs $3.50/M input ($0.35/M cached) and $14.00/M output, while GPT-6 Astra costs $10.00/M input ($2.50/M cached) and $50.00/M output. Gemini 3.8 Flash costs $0.75/M input ($0.075/M cached) and $3.75/M output. CostForge allows real-time interactive cost simulations across all 30 models.