Skip to content

Prices · Calculator

LLM cost calculator

API prices for all 19 models in llmwise, as of October 2026, run from $0.10 to $10.00 per million input tokens. Set the tokens in and out per request and your requests a month to see what every model costs through its API, and which llmwise plan covers the same use.

Calculator

Set the tokens in and out per request and your requests a month: every model's API cost, and the llmwise plan whose allowance covers as many messages. It all runs in the page.

A request under 64,000 tokens counts as 1 message in llmwise. An everyday model's count is per day; it's spread over 30 days here.

ModelAPI, per requestAPI, per monthIn llmwise: the plan that covers it
Claude Haiku 5.5Anthropic$0.00075$0.75Pro, $20/month (up to 60 a day)
GPT-6 LunaOpenAI$0.00075$0.75Pro, $20/month (up to 60 a day)
GLM 5.3 FlashZ.ai$0.00095$0.95Pro, $20/month (up to 60 a day)
DeepSeek V4.1 FlashDeepSeek$0.0020$2.04Pro, $20/month (up to 60 a day)
Mistral Large 4Mistral$0.0042$4.18Ultra, $100/month (up to 1,800 a month)
DeepSeek V4 ProDeepSeek$0.0044$4.40Ultra, $100/month (up to 1,800 a month)
Gemini 3.8 FlashGoogle$0.0056$5.63Ultra, $100/month (up to 1,800 a month)
Claude Haiku 4.5Anthropic$0.0075$7.50Ultra, $100/month (up to 1,800 a month)
GLM 5.3Z.ai$0.0087$8.68Ultra, $100/month (up to 1,800 a month)
Grok 4.7xAI$0.01$12.20Ultra, $100/month (up to 1,800 a month)
Claude Sonnet 5.5Anthropic$0.01$15.00Studio, $200/month (up to 2,000 a month)
Claude Sonnet 5Anthropic$0.01$15.00Studio, $200/month (up to 2,000 a month)
GPT-6.1 SolOpenAI$0.01$15.00Studio, $200/month (up to 2,000 a month)
GPT-6 SolOpenAI$0.01$15.00Studio, $200/month (up to 2,000 a month)
Gemini 3.1 ProGoogle$0.02$16.40Studio, $200/month (up to 2,000 a month)
Kimi K3Moonshot$0.02$22.50Studio, $200/month (up to 2,000 a month)
Claude Opus 5.5Anthropic$0.03$30.00Studio, $200/month (up to 1,000 a month)
Claude Fable 5.1Anthropic$0.08$75.00More than Studio gives (up to 500 a month)
GPT-6 AstraOpenAI$0.08$75.00More than Studio gives (up to 500 a month)

API cost: each model's catalog price per million tokens, before any caching or batch discount a provider offers. Plans: what each paid plan's allowance gives on the model, as the app charges it.

Every model's API price

API prices for every model
ModelInput / output per 1M tokensTypical messageContext windowIn llmwise
Claude Haiku 5.5Anthropic$0.10 / $0.50$0.00081M tokens60/day on Pro
GPT-6 LunaOpenAI$0.10 / $0.50$0.00081.05M tokens60/day on Pro
GLM 5.3 FlashZ.ai$0.15 / $0.50$0.00101.05M tokens60/day on Pro
DeepSeek V4.1 FlashDeepSeek$0.30 / $1.20$0.00201.05M tokens60/day on Pro
Mistral Large 4Mistral$0.68 / $2.09$0.00421.05M tokens250/mo on Pro
DeepSeek V4 ProDeepSeek$0.40 / $4.00$0.00441.05M tokens250/mo on Pro
Gemini 3.8 FlashGoogle$0.75 / $3.75$0.00561.05M tokens250/mo on Pro
Claude Haiku 4.5Anthropic$1.00 / $5.00$0.0075200K tokens250/mo on Pro
GLM 5.3Z.ai$1.40 / $4.40$0.00871.05M tokens250/mo on Pro
Grok 4.7xAI$2.00 / $6.00$0.0122500K tokens250/mo on Pro
Claude Sonnet 5.5Anthropic$2.00 / $10.00$0.01501M tokens125/mo on Pro
Claude Sonnet 5Anthropic$2.00 / $10.00$0.01501M tokens125/mo on Pro
GPT-6.1 SolOpenAI$2.00 / $10.00$0.01501.05M tokens125/mo on Pro
GPT-6 SolOpenAI$2.00 / $10.00$0.01501.05M tokens125/mo on Pro
Gemini 3.1 Pro (preview)Google$2.00 / $12.00$0.01641.05M tokens125/mo on Pro
Kimi K3Moonshot$3.00 / $15.00$0.02251.05M tokens125/mo on Pro
Claude Opus 5.5Anthropic$4.00 / $20.00$0.03001M tokens62/mo on Pro
Claude Fable 5.1Anthropic$10.00 / $50.00$0.07501M tokens31/mo on Pro
GPT-6 AstraOpenAI$10.00 / $50.00$0.07501.05M tokens31/mo on Pro
Per-token prices in our model catalog as of October 2026 (Anthropic: Anthropic's list price; OpenAI: OpenAI's list price; Z.ai: Z.ai's list price; DeepSeek: the price of the OpenRouter endpoints llmwise uses, not DeepSeek's own API; Mistral: Mistral's price, served through OpenRouter; Google: Google's list price; xAI: xAI's price, served through OpenRouter; Moonshot: Moonshot's list price). A typical message is 4,000 tokens in and 700 out. Claude Haiku 5.5: the rate for prompts up to 100K tokens; $0.50 / $2.50 a million over that. Mistral Large 4: a sale price, half its list price of $1.36 / $4.18. Gemini 3.8 Flash: an introductory price, through December 31, 2026. Grok 4.7: xAI charges more for very long prompts. Gemini 3.1 Pro (preview): the standard rate, for prompts up to 200K tokens. Providers change prices; check theirs before you build on them.

Every limit is published. Paid plans also have a monthly fair-use limit on AI cost: Pro $7.50, Max $20, Ultra $42, Studio $85. Using every message on your plan at typical sizes stays under it; very large messages and heavy research use it faster. Every limit, explained.

API or chat?

  • Building an app, a script or a pipeline that calls a model? You need an API: the provider's own, or a router in front of several. llmwise isn't one.

  • Want to ask questions, write, analyse files or code with a model yourself? A chat is simpler: no keys, no token maths, and in llmwise a fixed price per message you see before you send.

Questions

How is an LLM's cost worked out?

Tokens in times the input price, plus tokens out times the output price, each divided by a million. Tokens in include the whole conversation the model rereads, not just your latest question.

Is this what llmwise charges?

No. llmwise shows how many messages you have left on each model before you send; a plan is a monthly allowance, not a per-token bill. The calculator's last column says which plan's allowance covers the same number of messages.

Does it include caching or batch discounts?

Standard prices only. Prompt caching and batch processing lower some providers' prices for repeated or delayed requests; a plain request pays the standard price.

How many tokens is my prompt?

The token counter counts the tokens in a text you paste and prices that text on every model; this calculator starts from sizes and a monthly volume.

Claude, GPT, Gemini, DeepSeek, Grok, Kimi, GLM, and Mistral, in one chat.

See what a message costs before you send it. Free is 5 messages to try; sign in with an email link, no password or card.