The one to put in your config
What you should be on most of the time. A 1M context means feeding in large parts of the codebase directly instead of retrieving in circles, and with prefix caching the repeated context costs very little.
1M
Context window
175
turns / 1,000 crystals (estimate)
2.9×
Cost vs the cheapest model
Good for
- Day-to-day feature work
- Multi-file changes
- Reading a large repo to find a problem
Not for
- Autonomous runs beyond half an hour
Rates
Published price per million tokens — what your crystals are charged at. It is the upstream official list price; check it yourself.
Cache read$0.0036$0.0036
Input$0.4350$0.4350
Output$0.8700$0.8700
Turns per the same amount of crystals.
fast
pro
max
Turn counts are derived from the published rates, assuming a typical agent request of 30k input and 2k output.
How to use it. Put it in an environment variable to call it by name, bypassing the alias default.
Environment variables
export ANTHROPIC_BASE_URL="https://api.pixcode.ai/anthropic"
export ANTHROPIC_AUTH_TOKEN="sk-px-..."
export ANTHROPIC_MODEL="pixcode-pro"Other tools are covered in the docs.
Which plans include it.
Starter $19/moPro $49/moMax $129/mo