Files

hzhang b7fad6dd26 docs: clarify Token Plan vs pay-per-token billing (key + model matrix)

Field investigation against the live API:
- sk-cp- (Token Plan)  + MiniMax-M2.7           → ✅ works
- sk-cp- (Token Plan)  + MiniMax-M2.7-highspeed → ❌ "Token Plan Starter
  (0/0 used)" — the base Token Plan EXCLUDES the highspeed variant
- sk-api- (pay-per-token) + either model        → ✅ structurally
  (needs balance > 0; otherwise "insufficient_balance (1008)")

Plugin code already handles both key types via the same
Authorization: Bearer header — no functional change needed. README now
makes the matrix explicit so operators don't try highspeed on a
plan-only key and wonder why "0/0 used" comes back.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-05-31 16:10:11 +01:00

2.8 KiB

Raw Permalink Blame History

Plexum-minimax-provider

Plexum ProviderPlugin that serves MiniMax models via MiniMax's Anthropic-compatible HTTP endpoint.

Status

v0.1 — current: API key auth, streaming SSE, declared models MiniMax-M2.7 + MiniMax-M2.7-highspeed. Backend fixed to api (global https://api.minimax.io/anthropic or CN https://api.minimaxi.com/anthropic).

Deferred: OAuth (Code Plan portal), MiniMax Portal provider, image / TTS / video / music providers (separate plugins later if wanted).

API key + model matrix

MiniMax issues two key types from the same Anthropic-compatible endpoint; this plugin sends both with Authorization: Bearer <key> and lets the server decide. The key prefix tells you which billing model you're on:

key prefix	billing	`MiniMax-M2.7`	`MiniMax-M2.7-highspeed`
`sk-cp-...`	Token Plan (per-plan quota)	✅ included	❌ `Token Plan Starter (0/0 used)` — highspeed is NOT in the base Token Plan
`sk-api-...`	pay-per-token (per-request billed)	✅ if balance > 0; else `insufficient_balance (1008)`	✅ if balance > 0

Takeaway: if you only have a Token Plan key, set the agent's model to MiniMax-M2.7 (base). For the highspeed variant you need a funded sk-api- key. The plugin doesn't reject highspeed at startup — the error surfaces in the agent's response when the model is invoked.

Install

cd ~/Plexum-minimax-provider
./scripts/install.sh

Then:

Write API key to ~/.plexum/plugins/plexum-minimax-provider/config.json:
```
{
  "api_key": "sk-cp-..."
}
```
(chmod 600 it.)

Allow the plugin in ~/.plexum/plexum.json:

{"plugins": {"allow": ["plexum-minimax-provider"]}}

Point an agent at a MiniMax model:

plexum agent-add --model MiniMax-M2.7 my-agent

Restart the gateway and talk:

systemctl --user restart plexum
plexum say --agent-id my-agent --session-id $(plexum new-session --agent-id my-agent) "hello"

Config options

Field	Default	Notes
`api_key`	(required)	`sk-cp-...` style key from MiniMax
`region`	`global`	`cn` switches to `api.minimaxi.com`
`base_url`	–	override either region's default
`max_tokens_default`	`4096`	used when `TurnRequest.MaxTokens` is unset

Architecture

internal/anthropic/ — minimal HTTP+SSE Anthropic Messages client
internal/translate/ — canonical.TurnRequest ↔ Anthropic Messages, SSE Event → canonical.TurnEvent per-block state machine
cmd/plexum-minimax-provider-plugin/ — Plexum SDK ProviderPlugin entry

Both text, thinking, and tool_use content blocks round-trip losslessly (signatures preserved for thinking blocks).

License

Same as Plexum.

2.8 KiB Raw Permalink Blame History Unescape Escape