// Model-lineage compat for "minimax"; regenerated from the frozen census using class taxonomy selectors.

class "minimax" {
	// Replaces the MiniMax M2 mandatory-reasoning fallback on every host.
	family "m2" {
		thinking-requires-effort #true
	}
	// Replaces the MiniMax lineage branch in both OpenAI baselines.
	reasoning-deltas-may-be-cumulative #true
	// Replaces the identity default: M2/M3 thinking rides Anthropic adaptive
	// thinking on every Messages route, custom provider ids included.
	on-api "anthropic-messages" {
		family "m2" {
			thinking-mode "anthropic-adaptive"
		}
		family "m3" {
			thinking-mode "anthropic-adaptive"
		}
	}
	on "aimlapi" "coreweave" "fireworks" "huggingface" "kilo" "nanogpt" "novita" "nvidia" \
		"opencode-go" "opencode-zen" "together" "venice" "wafer-serverless" "zenmux" {
		family "m3" {
			thinking-efforts "minimal" "low" "medium" "high" "xhigh"
		}
	}
	on "alibaba-coding-plan" "amazon-bedrock" "coreweave" "fireworks" "huggingface" "kilo" \
		"minimax" "minimax-cn" "minimax-code" "minimax-code-cn" "nanogpt" "novita" "nvidia" \
		"ollama-cloud" "opencode-go" "opencode-zen" "openrouter" "together" "venice" "vercel-ai-gateway" \
		"zenmux" {
		family "m2" {
			thinking-requires-effort #true
		}
	}
	// The M2 generation accepts exactly low/medium/high for reasoning_effort
	// and 400s on minimal/xhigh/none, on every host.
	family "m2" {
		thinking-efforts "low" "medium" "high"
	}
	// MiniMax-M3: 512K is the standard pricing-tier boundary leaked into
	// upstream metadata, not the model ceiling (documented: 1M in / 128K out).
	// Exact selectors are case-sensitive, so both served spellings are listed:
	// MiniMax hosts publish `MiniMax-M3`, Charm Hyper publishes `minimax-m3`.
	on "charm-hyper" "minimax" "minimax-cn" "minimax-code" "minimax-code-cn" "sambanova" {
		models "MiniMax-M3" "minimax-m3" {
			limits-patch {
				context-window 1000000
				max-tokens 128000
			}
		}
	}
	// MiniMax's standard API doubles every rate above 512K input tokens;
	// subscription hosts retain the same rates only as usage estimates.
	on "minimax" "minimax-cn" "minimax-code" "minimax-code-cn" {
		models "MiniMax-M3" {
			long-context-cost {
				input-threshold 512000
				multiplier 2.0
			}
		}
	}
	on "alibaba-coding-plan" "minimax-code" "minimax-code-cn" "wafer-serverless" {
		supports-developer-role #false
	}
	// pi ladders these hosts on the generic four-tier scale; priority resolves
	// the intentional overlap with the class-wide M2 rule.
	on "amazon-bedrock" "ollama-cloud" priority=1 {
		thinking-efforts "minimal" "low" "medium" "high"
	}
	on "kilo" "novita" {
		family "m1" {
			thinking-efforts "minimal" "low" "medium" "high" "xhigh"
		}
	}
	on "minimax" "minimax-cn" "minimax-code" "minimax-code-cn" "vercel-ai-gateway" {
		thinking-mode "anthropic-adaptive"
		family "m2" {
			// Replaces the Anthropic-route MiniMax effort remap table.
			thinking-effort-map {
				low "adaptive"
				medium "adaptive"
				high "adaptive"
			}
		}
		family "m3" {
			// Replaces the Anthropic-route MiniMax effort remap table.
			thinking-effort-map {
				low "adaptive"
				medium "adaptive"
				high "adaptive"
			}
			thinking-efforts "low" "medium" "high"
		}
	}
	// MiniMax-M3.1-Flash (and its bundled `-Preview` id) always thinks
	// (`thinking.type: "disabled"` and effort `none` 400 with error 2013) and
	// tunes depth through `output_config.effort` from `low` to `max` (the
	// default when omitted). The identity map replaces the M3 family's
	// adaptive-tag-only map so each level reaches the wire. Like the M2 family,
	// thinking cannot be turned off: `thinking-requires-effort` hides the off
	// level and clamps forced-off requests to the lowest effort instead of
	// sending `disabled`. The launch id also rejects sampling params
	// (`temperature`, `top_p`, `top_k`).
	on "minimax" "minimax-cn" "minimax-code" "minimax-code-cn" {
		models "MiniMax-M3.1-Flash" "MiniMax-M3.1-Flash-Preview" {
			thinking-requires-effort #true
			thinking-efforts "low" "medium" "high" "xhigh" "max"
			thinking-effort-map {
				low "low"
				medium "medium"
				high "high"
			}
		}
		models "MiniMax-M3.1-Flash" {
			supports-sampling-params #false
		}
	}
	// Token Plan rows ride the Anthropic route; these OpenAI-only wire axes
	// serve the legacy lightning rows that stay on the OpenAI-compatible one.
	on "minimax-code" "minimax-code-cn" {
		supports-reasoning-effort #false
		supports-store #false
	}
	on "minimax-code" "minimax-code-cn" "wafer-serverless" {
		reasoning-content-field "reasoning_content"
	}
	// M3 reasoning reaches omp as its plaintext trace on every host, and
	// MiniMax asks agents to pass all earlier reasoning back.
	family "m3" {
		portable-reasoning #true
		// residue: M3.1 Flash Preview classifies as family m3 (no revision is
		// extracted), but it is a different model.
		models "*m3.1*" {
			portable-reasoning #false
		}
	}
}