haidercodedocs
GitHubLog in

Go

Haider Go

Hosted open-weight models behind one subscription — the shortcut, not a requirement.

Models

Fourteen hosted open-weight models across five providers — one subscription, one endpoint.

ModelLaneInputCachedOutput
glm-4.7-flashxEconomy$0.21$0.03$1.20live
qwen3.5-flashEconomy$0.30$0.06$1.20live
minimax-m3Long context$0.90$0.18$3.60live
qwen3-coder-nextCoding$0.90$0.18$4.50live
qwen3.7-plusBalanced$1.20$0.24$4.80live
qwen3.8-27bCompact$1.20$0.12$9.00live
deepseek-v4-flashDefault$1.32$0.04$3.96live
kimi-k2.7-codePremium coding$2.85$0.57$12.00live
deepseek-v4-proDefault+$3.96$0.13$11.88live
glm-5.2Premium planner$4.20$0.78$13.20live
glm-5.3Premium coding$4.20$0.78$13.20live
qwen3.8-2.4t-a95bOpen flagship$6.00$0.60$18.00live
qwen3.8-maxFrontier$6.00$0.75$18.00live
kimi-k3Flagship$9.00$0.90$45.00live

Rates per 1M tokens. Cached input meters at the cached rate automatically; usage is drawn from your weekly allowance first, then usage-credits.

GET /v1/models lists what is live on this deployment right now; models roll out as upstream lanes are switched on.

GET /v1/account returns your own plan and remaining weekly allowance, authenticated with the same key as inference — so a harness can show your status without a browser. It refreshes once a minute; calls inside that window return the cached snapshot with "cached": true.

curl https://haidercode.ai/v1/account \
  -H "Authorization: Bearer $HAIDER_GO_KEY"

Plans

PlanPriceAllowance
Go$40/monthStarter — a limited weekly allowance
Go Max$200/month20× the usage of Go

Allowances are metered over a rolling 7-day window, not a calendar week — there is no reset day to game.

usage-credits

usage-credits are dollars, not mystery units. When the weekly allowance runs out, spend continues from your usage-credits balance. Top up any time — see Billing & usage-credits.

The harness stays free

Haider itself is free with your own provider keys. Go is the shortcut for people who would rather not manage keys — never a requirement.