LLM API Pricing Calculator

Enter your monthly token volume, pick the models you're weighing up, and see the monthly bill for each — side by side, from published rate cards.

How it works: monthly cost = (input tokens ÷ 1M × input rate) + (output tokens ÷ 1M × output rate). List prices only — prompt-caching, batch and cache-hit discounts are not applied.

1 · Your monthly token volume

Prompts, context, documents you send to the model
Tokens the model generates back

2 · Models to compare

3 · Monthly cost, side by side

ModelInput rate /1MOutput rate /1MInput costOutput costMonthly totalvs cheapest

Not sure how many tokens your text is? Use the token counter to measure real prompts first, or check the VRAM calculator if you're weighing self-hosting an open-weight model instead.

Ad slot — AdSense in-article unit

The full rate table (July 2026)

Every rate below links to the model page it was taken from. Prices are USD per 1 million tokens, input / output.

ModelInput /1MOutput /1MContext window
DeepSeek V4-Flash$0.14$0.281M tokens
Kimi K2.6$0.60$2.50262,144 tokens
Claude Haiku 4.5$1.00$5.00200,000 tokens
Gemini 3.5 Flash$1.50$9.001,048,576 tokens
DeepSeek V4-Pro$1.74$3.481M tokens
Claude Sonnet 5 (intro, to 31 Aug 2026)$2.00$10.001M tokens
Gemini 3.1 Pro (approx.)~$2.00~$12.002M tokens (3.1 family)
Grok 4.5$2.00$6.00500,000 tokens
Qwen 3.7-Max$2.50$7.501M tokens
Claude Sonnet 5 (standard, from 1 Sep 2026)$3.00$15.001M tokens
Claude Opus 4.8$5.00$25.001M tokens
Claude Opus 4.7$5.00$25.001M tokens
GPT-5.5 (Thinking)$5.00$30.001M tokens (400K in Codex CLI)
Claude Fable 5$10.00$50.001M tokens
Claude Opus 4.8 (fast mode)$10.00$50.001M tokens
GPT-5.5 Pro$30.00$180.001M tokens

Frequently asked questions

How is LLM API cost calculated?

Monthly cost = (input tokens ÷ 1,000,000 × input price per 1M) + (output tokens ÷ 1,000,000 × output price per 1M). This calculator uses published list prices only; prompt-caching, batch and cache-hit discounts can lower real bills substantially (e.g. Claude Opus 4.7's page lists up to 90% savings with prompt caching).

Which LLM API is cheapest in 2026?

On the list prices tracked here, DeepSeek V4-Flash ($0.14/$0.28 per 1M) is the lowest, followed by Kimi K2.6 ($0.60/$2.50) and Claude Haiku 4.5 ($1/$5). Cheapest per token is not always cheapest per solved task — quality and retry rates matter.

Why are some models missing?

We never estimate prices. Models without a publicly confirmed USD rate card are excluded: GPT-5.6 (preview, pricing TBD), GPT-Live (voice models in ChatGPT — API pricing TBD), Mistral Small 4 (pricing TBD), Grok 5 (unreleased), Doubao Seed 2.1 (priced in CNY — ¥6/¥30 per 1M — with no verified USD card), Gemma 4 (open weights, no first-party API price) and Cursor 3 (an IDE with subscription tiers, not a per-token API).

Do these prices include caching or batch discounts?

No — list price only. Several vendors publish separate discounted paths (Gemini 3.5 Flash cached input at $0.15/1M; Doubao cache-hit input from ¥1.2/1M; Anthropic prompt caching and batch discounts). If your workload is cache-friendly, treat these numbers as an upper bound.

Data sources: the AI Model Hub pages linked in the rate table above, each of which cites vendor rate cards and independent trackers. Excluded (no confirmed USD per-token pricing): GPT-5.6, GPT-Live (API pricing TBD), Mistral Small 4, Grok 5, Doubao Seed 2.1 (CNY only), Gemma 4 (open weights), Cursor 3 (subscription IDE).