Blog
Prices, token counts and method notes. Every number has a source.
GPT API pricing, October 2026: every OpenAI model per million tokens
Input, cached and output prices for every GPT model, OpenAI's list price next to ours, and what a chat turn and a long-document request cost on GPT-6 Astra, GPT-6.1 Sol and GPT-6 Luna.
DeepSeek API pricing, October 2026: every model per million tokens
Input, cached and output prices for every DeepSeek model, DeepSeek's list price next to ours, and what a chat turn and a long-document request cost on V4 Pro, V4.1 Flash and V4 Flash.
Gemini API pricing, October 2026: every model per million tokens
Input, cached and output prices for every Gemini model, Google's list price next to ours, and what a chat turn and a long-document request cost on Gemini 4 Argon, 3.1 Pro and 3.8 Flash.
Grok API pricing, October 2026: every xAI model per million tokens
Input, cached and output prices for every Grok model, xAI's list price next to ours, and what a chat turn and a long-document request cost on Grok 4.7, 4.5 and 4.3.
Kimi API pricing, October 2026: every Moonshot AI model per million tokens
Input, cached and output prices for every Kimi model, Moonshot AI's list price next to ours, and what a chat turn and a long-document request cost on Kimi K3, K2.7 Code and K2.5.
GLM API pricing, October 2026: every Z.ai model per million tokens
Input, cached and output prices for every GLM model, Z.ai's list price next to ours, and what a chat turn and a long-document request cost on GLM 5.3, 5.2 and 5.3 Flash.
Qwen API pricing, October 2026: every model per million tokens
Input, cached and output prices for every Qwen model, Qwen's list price next to ours, and what a chat turn and a long-document request cost on Qwen3.7 Max, 3.7 Plus and 3.6 27B.
Kimi, GLM and Qwen coding plans vs pay-per-token API, October 2026
What the Kimi, Z.ai GLM and Alibaba Qwen coding plans cost and include, whether DeepSeek has a code plan, and what the same monthly money buys per token.
Using Cursor with your own API key: what it costs, October 2026
What one Cursor agent request costs on your own key, worked at each developer's list price and ours, and the four settings that point Cursor at it.
Claude API pricing, October 2026: every model per million tokens
Input, cached and output prices for every Claude model, Anthropic's list price next to ours, and what a chat turn and a long-document request cost on Opus, Sonnet and Haiku.
A free AI API: $1 of credit for Claude, GPT, Gemini and more
Every new account can claim $1 of API credit that works on every model. What it buys per model, the rules, and the three steps to a working key.
The hidden prompt tokens in cheap LLM APIs
One fixed prompt of about 90 tokens went to every route of every model on 2026-10-12. Some routes reported 4,469 input tokens. Two reported 14,111.
LLM API pricing comparison, October 2026
Input, cached and output prices for every listed chat model with a developer list price, grouped by developer, the developer's price next to ours. Rebuilt from the live catalog.
What Claude Code costs on API billing, October 2026
The three prices behind a Claude Code bill, what prompt caching does to them, and worked examples at Anthropic's list price and ours.