Rates are the upstream official list price — zero markup, published line by line on pricing→

PixCode models

Three aliases, 31 official names. What changes is what runs underneath; what stays is each alias’s role and its rate.

Turn counts are derived from the published rates, assuming a typical agent request of 30k input and 2k output.

Relative cost

Turns per the same amount of crystals. One max turn costs twenty fast turns, so do not give it the chores.

fast1×
pro2.9×
max20×

All models. Call the official names directly. The price is the upstream official list price — zero markup.

31 available · live rates

ModelContextAPICache readInputOutput
PixCode
pixcode-max1Manthropic$0.26$1.40$4.40
pixcode-fast1Manthropic$0.0032$0.16$0.32
pixcode-pro1Manthropic$0.004$0.5$1.00
Claude
claude-fable-51Manthropic$1.00$10.00$50.00
claude-opus-51Manthropic$0.5$5.00$25.00
claude-sonnet-51Manthropic$0.2$2.00$10.00
claude-haiku-4-5-20251001200Kanthropic$0.1$1.00$5.00
GPT
gpt-5.6-luna1.1Mopenai$0.02$0.2$1.20
gpt-5.6-terra1.1Mopenai$0.2$2.00$12.00
gpt-5.6-sol1.1Mopenai$0.5$5.00$30.00
Gemini
gemini-3.5-flash1.0Mopenai$0.15$1.50$9.00
gemini-3.1-pro-preview1.0Mopenai$0.2$2.00$12.00
DeepSeek
deepseek-v3.2164Kanthropic$0.1345$0.269$0.4
deepseek-v3.2-exp164Kanthropic$0.27$0.27$0.41
deepseek-v3.1131Kanthropic$0.135$0.27$1.00
deepseek-v3-0324164Kanthropic$0.135$0.27$1.12
deepseek-v3-turbo64Kanthropic$0.4$0.4$1.30
deepseek-r1-0528164Kanthropic$0.35$0.7$2.50
deepseek-r1-turbo64Kanthropic$0.7$0.7$2.50
Kimi
kimi-k31.0Manthropic$0.3$3.00$15.00
kimi-k2.5262Kanthropic$0.1$0.6$3.00
kimi-k2-thinking262Kanthropic$0.15$0.6$2.50
kimi-k2-0905262Kanthropic$0.6$0.6$2.50
kimi-k2-instruct131Kanthropic$0.57$0.57$2.30
GLM
glm-5.21.0Manthropic$0.26$1.40$4.40
glm-5203Kanthropic$0.2$1.00$3.20
glm-4.7205Kanthropic$0.11$0.6$2.20
glm-4.6205Kanthropic$0.11$0.55$2.20
glm-4.6v131Kanthropic$0.055$0.3$0.9
glm-4.5131Kanthropic$0.11$0.6$2.20
glm-4.5v66Kanthropic$0.11$0.6$1.80

USD per 1M tokens. Models marked anthropic also accept the OpenAI endpoint; openai-only models must use /v1/chat/completions. Cache-write rates are in the docs.

Start on pro, switch when you need to.

The aliases are three defaults. All 31 official names can be called by name at any time — one config line apart.