KosComputeAPI
Models

MiMo-V2.6 Flash RL Uncensored (Heretic)

Capabilities, limits, pricing, and endpoints for kosmik/mimo-v2.6-flash-uncensored.

View Markdown

Canonical model ID: kosmik/mimo-v2.6-flash-uncensored

Uncensored MiMo-V2.6 Flash RL (Heretic refusal-removal adapter) for text chat, reasoning and tools. Runs only on rental spare capacity: rentals take priority and the model can become unavailable without notice; handle 503 with backoff. Reduced guardrails: you are responsible for how outputs are used.

Runtime metadata

This table is generated from public model metadata. Readiness and capacity are refreshed from GET /v1/models on page load.

Property Value
Kind chat
Input text
Output text
Context 262,144 tokens
Maximum output 32,768 tokens
Supported endpoints /v1/chat/completions, /v1/responses, /v1/messages
Capabilities tool_calling, json_mode, structured_outputs, reasoning
Pricing Input $0.15 / 1M · Output $0.45 / 1M tokens

Reasoning

Reasoning support and controls are model-dependent.

Supported efforts: none, low, medium, high.

See the reasoning guide for budget semantics.

Use this model

Copy the canonical ID into the model field. Check the endpoint guide before using optional capabilities.

Type to search guides, models, and API reference.