Count tokens in prompts, code, JSON, and documents; estimate input/output spend; and compare verified pricing across GPT, Claude, Gemini, DeepSeek, and 100+ models. Free, browser-based, and no signup.
01 — Model Matchups
Compare pricing deltas, token rates, and context sizes side-by-side.
Pick any two frontier or budget models to calculate live price deltas, input/output cost divergence, and context capacity.
Ultimate frontier battle: OpenAI GPT-5.6 Sol ($5/$30) vs Anthropic Claude Opus 5 ($5/$25) for deep multi-hour reasoning.
Long-context giants: OpenAI Sol ($5/$30) with 1M tokens vs Google Gemini 3.1 Pro ($2/$12) with 2M tokens.
Creative & reasoning pinnacle: Sol's high throughput ($5/$30) vs Claude Fable 5 ($10/$50).
2.4T parameter MoE challenger: Alibaba Qwen 3.8 Max ($2/$6) vs OpenAI GPT-5.6 Sol ($5/$30).
400B open MoE vs OpenAI balanced flagship: Llama 4 Maverick ($0.45/$1.25) vs GPT-5.6 Terra ($2/$12).
Extreme context window showdown: Llama 4 Scout (10 Million tokens) vs Gemini 3.1 Pro (2 Million tokens).
02 — Workload Simulator
Simulate chat turns, agent loops, RAG queries, and refactors across all models with prompt caching.
Simulate request costs with prompt cache discounts across 167 models.
03 — Model Matrix
Official first-party pricing, context window limits, and token rate tiers.
The balanced 5.6 tier: near-Sol quality at $2/$12 with the full 1.05M context window — the recommended default choice for production.
The cheap 5.6 tier at $0.20/$1.20 — high-volume classification, routing, data extraction, and low-latency interactive agents.
Claude 5 flagship: $5/$25 pricing for deepest multi-hour autonomous reasoning, code orchestration, and 1M context.
Claude 5 balanced anchor: permanent $2/$10 pricing with 1M context window and 90% prompt caching discount.
Google high-throughput volume workhorse at $1.50/$7.50 with 1M context and ultra-fast TTFT.
Next-gen MoE frontier model with 1M context, 384k max output, and dynamic off-peak discounts ($0.66/$1.98 off-peak, $1.32/$3.96 peak).
European open-weight flagship: general-purpose, multimodal, and multilingual engine at $0.50/$1.50 per 1M tokens with 90% prompt caching.
Moonshot AI Beijing 1M-context flagship with deep document analysis and citation indexing at $3.00/$15.00.
04 — Calculator Suite
Specialized workspaces designed for prompt engineers, architects, and product builders.
05 — Token Cost Lookups
06 — Provider Ecosystem
The GPT-5.6 family (Sol, Terra, Luna), GPT-5.5/5.4 generations, and unified reasoning systems: 1M+ context on frontier tiers, 90% prompt caching discounts, and 50% batch discounts.
Claude 5 generation (Opus 5, Sonnet 5, Fable 5, Haiku 4.5) alongside Claude 3.7 Sonnet hybrid reasoning with industry-leading context windows and 90% prompt caching savings.
Gemini 3.x, 2.5, 2.0, and 1.5 series: 2M token context, ultra-fast Flash tiers, context caching discounts up to 90%, and multimodal native reasoning.
DeepSeek V4 Pro, V4 Flash, R1 Reasoning, and V3 Chat: 1M token context, disruptive low pricing, peak/off-peak tier discounts, and 90% cache-hit savings.
Llama 4 Maverick (400B MoE), Llama 4 Scout (109B MoE with 10M context), Llama 3.3 70B, Llama 3.1 405B/70B/8B, and Llama 3.2 Vision: open-weight foundation models.
European open-weight leader: Mistral Large 3, Medium 3.5, Small 4, Codestral 2501 code engine, Pixtral multimodal, and Ministral edge models.
Export the verified pricing dataset as JSON or CSV, or query our REST API directly in your CI/CD pipelines to monitor cost drifts and regressions before deploying changes.