TokenPad

LLM API pricing, with sources

42 models from 6 providers. Every price below was read from the provider’s own documentation — each row carries the date it was checked and a link to the page it came from, so you can verify any figure in one click instead of trusting us. Last full review: August 5, 2026.

Find a model by what you actually need

42 of 42 models match. Cheapest on a 3:1 input-to-output mix is GPT-5 nano at $0.138 per million blended.

OpenAI

18 models · pricing quirks and token counting →

OpenAI model prices per million tokens
ModelInputCached inOutputContextToken countVerified
GPT-5.6 Sol$5.00$0.5000$30.001.05MExact2026-08-03
GPT-5.6 Terra$2.00$0.2000$12.001.05MExact2026-08-03
GPT-5.6 Luna$0.2000$0.0200$1.201.05MExact2026-08-03
GPT-5.5$5.00$0.5000$30.00Exact2026-08-03
GPT-5.4$2.50$0.2500$15.00Exact2026-08-03
GPT-5.4 mini$0.7500$0.0750$4.50Exact2026-08-03
GPT-5.4 nano$0.2000$0.0200$1.25Exact2026-08-03
GPT-5.1$1.25$0.1250$10.00Exact2026-08-03
GPT-5$1.25$0.1250$10.00Exact2026-08-03
GPT-5 mini$0.2500$0.0250$2.00Exact2026-08-03
GPT-5 nano$0.0500$0.005000$0.4000Exact2026-08-03
GPT-4.1 legacy$2.00$0.5000$8.00Exact2026-08-03
GPT-4.1 mini legacy$0.4000$0.1000$1.60Exact2026-08-03
GPT-4o legacy$2.50$1.25$10.00Exact2026-08-03
GPT-4o mini legacy$0.1500$0.0750$0.6000Exact2026-08-03
o3 legacy$2.00$0.5000$8.00Exact2026-08-03
o4-mini legacy$1.10$0.2750$4.40Exact2026-08-03
GPT-3.5 Turbo legacy$0.5000$1.50Exact2026-08-03

Source: OpenAI pricing documentation

Anthropic

8 models · pricing quirks and token counting →

Anthropic model prices per million tokens
ModelInputCached inOutputContextToken countVerified
Claude Fable 5$10.00$1.00$50.001MEstimate2026-08-03
Claude Opus 5$5.00$0.5000$25.001MEstimate2026-08-03
Claude Opus 4.8$5.00$0.5000$25.001MEstimate2026-08-03
Claude Opus 4.6$5.00$0.5000$25.001MEstimate2026-08-03
Claude Sonnet 5Introductory pricing through 31 Aug 2026. From 1 Sep 2026: $3 input / $15 output per 1M tokens.$2.00$0.2000$10.001MEstimate2026-08-03
Claude Sonnet 4.6$3.00$0.3000$15.001MEstimate2026-08-03
Claude Sonnet 4.5 legacy$3.00$0.3000$15.00200KEstimate2026-08-03
Claude Haiku 4.5$1.00$0.1000$5.00200KEstimate2026-08-03

Source: Anthropic pricing documentation

Google

5 models · pricing quirks and token counting →

Google model prices per million tokens
ModelInputCached inOutputContextToken countVerified
Gemini 3.6 Flash$1.50$7.50Estimate2026-08-03
Gemini 3.5 Flash$1.50$9.00Estimate2026-08-03
Gemini 3.5 Flash-Lite$0.3000$2.50Estimate2026-08-03
Gemini 2.5 Flash legacy$0.3000$2.501MEstimate2026-08-03
Gemini 2.5 Flash-Lite legacy$0.1000$0.4000Estimate2026-08-03

Source: Google pricing documentation

DeepSeek

2 models · pricing quirks and token counting →

DeepSeek model prices per million tokens
ModelInputCached inOutputContextToken countVerified
DeepSeek V4 Flash$0.1400$0.002800$0.28001MEstimate2026-08-03
DeepSeek V4 Pro$0.4350$0.003625$0.87001MEstimate2026-08-03

Source: DeepSeek pricing documentation

xAI

3 models · pricing quirks and token counting →

xAI model prices per million tokens
ModelInputCached inOutputContextToken countVerified
Grok 4.5Rates shown are for prompts under 200K tokens. Above that threshold xAI charges double on every line: $4.00 input, $0.60 cached, $12.00 output.$2.00$0.3000$6.00500KEstimate2026-08-05
Grok 4.3Rates shown are for prompts under 200K tokens. Above that threshold every rate doubles: $2.50 input, $0.40 cached, $5.00 output.$1.25$0.2000$2.501MEstimate2026-08-05
Grok Build 0.1Rates shown are for prompts under 200K tokens; above that they double to $2.00 input and $4.00 output.$1.00$0.2000$2.00256KEstimate2026-08-05

Source: xAI pricing documentation

Mistral AI

6 models · pricing quirks and token counting →

Mistral AI model prices per million tokens
ModelInputCached inOutputContextToken countVerified
Mistral Medium 3.5Mistral advertises a 90% discount on cached input tokens but does not publish a per-model cached rate, so no cached figure is shown here rather than an inferred one.$1.50$7.50256KEstimate2026-08-05
Mistral Large 3Open-weight model, so self-hosting is an alternative to these API rates. Cached input is discounted but not published per model.$0.5000$1.50256KEstimate2026-08-05
Mistral Small 4$0.1500$0.6000256KEstimate2026-08-05
Magistral MediumReasoning model. Reasoning tokens are billed at the output rate and do not appear in the visible answer.$2.00$5.00256KEstimate2026-08-05
Devstral 2Aimed at coding and agentic work. Code tokenizes denser than prose, so token counts for the same character count run higher here than on text workloads.$0.4000$2.00256KEstimate2026-08-05
Ministral 3 8BInput and output are priced identically, which is unusual and makes output-heavy work disproportionately cheap here relative to models that charge a premium on output.$0.1500$0.1500256KEstimate2026-08-05

Source: Mistral AI pricing documentation

How to use this table

All figures are US dollars per million tokens, at standard on-demand rates. Batch processing, enterprise agreements and regional premiums are not reflected. Cached input is what you pay for prompt content the provider has already processed and retained — usually about a tenth of the base input rate, and the largest lever available on a repetitive workload.

The token count column is the one most price tables omit. A rate per million tokens is only meaningful if you know how many tokens your text becomes, and that depends on a tokenizer that not every provider publishes. Where we can run the real encoder, the column says exact; where we cannot, it says estimate. The methodology page explains what sits behind each label.

Put your own numbers against these rates in the cost calculator, or measure a real prompt first in the token counter.

If you are choosing between two specific models rather than surveying the field, the head-to-head comparisons price both across four workload shapes at a million requests a month — which is where a ranking taken from the headline rate sometimes reverses.