Abliterated Model Router icon

Abliterated Model Router

Abliterated Model Router provides one OpenAI-compatible API for routing abliterated language models across multiple providers. It is intended for developers and safety researchers who need model comparison, modality-aware selection, and provider fallback in a shared integration.

Abliterated Model Router

A shared API for abliterated language models

Abliterated Model Router is an AllModels API layer for accessing abliterated language models through one OpenAI-compatible endpoint. It aggregates model deployments from multiple providers and presents their availability, capabilities, context limits, latency, and token prices in a shared catalog.

Abliterated models use modified weights to reduce or remove learned refusal behavior. AllModels positions these models for security research, red-teaming, and safety testing, while warning that they are more likely to generate harmful or unsafe material. The router can select compatible providers, apply modality-aware routing, and fall back when a provider lacks capacity.

Router and API features

Federated model access

The router exposes one public model ID across deployments from independent providers, so applications can use the same model identifier while provider routes change.

Automatic capacity fallback

Requests can fall back to another eligible provider when the selected route is unavailable or capacity constrained, without requiring an application code change.

Modality-aware selection

The router considers request modality when selecting a route. Text requests can use eligible text providers, while image requests are sent only to providers that can process images.

OpenAI-compatible endpoints

Applications can use OpenAI-compatible Chat Completions with messages, streaming, and function tools, or the Responses API with streaming events, reasoning controls, structured output, custom tools, and hosted web search.

Controlled web search

Router-hosted web search provides a common search tool and URL citations through the AllModels layer, including for models whose underlying provider does not offer search.

Provider comparison

The catalog exposes provider availability, context limits, modalities, capabilities, latency, speed, and token pricing for individual model routes. For example, the listed DeepSeek model has five providers and the listed GLM 5.3 model has three.

Practical use cases

  • Safety research and red-teaming

    Researchers can compare abliterated model variants and provider routes when investigating refusal behavior, model safety, and controlled adversarial prompts.

  • Safety-system evaluation

    Teams testing safety controls can use modified-weight models to examine how applications behave when a model provides fewer refusal responses, provided testing is isolated and governed by safeguards.

  • Multi-provider application development

    Developers can connect an existing OpenAI SDK integration to the AllModels endpoint, then compare model IDs, provider availability, context limits, and token prices without building separate provider integrations.

  • Mixed-modality workflows

    Applications that accept both text and image inputs can use the router’s modality-aware selection to avoid sending image requests to text-only provider routes.

  • Capacity-sensitive inference

    Services that need continuity across changing inference capacity can use automatic fallback to try another compatible route when a provider is unavailable or overloaded.

Pros and Cons

Pros

  • One OpenAI-compatible integration can access multiple abliterated model deployments and providers.
  • Automatic fallback can preserve access when an eligible provider is unavailable or capacity constrained.
  • Modality-aware routing helps direct image requests only to providers that support image input.
  • The catalog provides model- and provider-level comparison data, including token prices, context limits, capabilities, latency, and speed.
  • Chat Completions, Responses, function tools, structured output, and router-hosted web search are available through documented API paths.

Cons

  • Abliterated models can produce harmful or unsafe outputs and require controlled use with appropriate safeguards.
  • Provider availability, limits, latency, speed, and pricing vary by model and route, so the catalog must be checked for the specific deployment.
  • The listed catalog contains four abliterated models, so breadth is narrower than a general-purpose model marketplace.

FAQ

How do I connect to the router?

Use an OpenAI-compatible client with the base URL https://api.allmodels.io/oai and an ALLMODELS_API_KEY. The service supports Chat Completions at /oai/chat/completions and Responses at /oai/responses; the model ID is supplied in the request.

How does provider routing and fallback work?

The router selects compatible provider routes for each request. Text requests can use eligible text routes, while image or multimodal requests are sent only to providers that support the requested modality. If a provider is unavailable or capacity constrained, AllModels can try another eligible route without requiring a model-ID or code change.

Which abliterated models are available?

The catalog lists four abliterated models: Z.ai GLM 5.3 Abliterated, DeepSeek V4.1 Flash 1017 Abliterated, Qwen3.8 27B Abliterated, and Z.ai GLM 5.3 Flash Abliterated. Provider counts and supported modalities differ by model.

What does “abliterated” mean, and what are the safety considerations?

Abliterated models use modified weights intended to reduce or remove learned refusal behavior. The site says they can refuse virtually no prompts and may therefore produce harmful or unsafe outputs. They should be used only in controlled environments with appropriate safeguards.

How is usage priced and controlled?

AllModels states that its pay-as-you-go pricing adds a 5.5% platform fee to the downstream provider cost and does not mark up provider pricing. The pricing page also describes a free option, spending limits per API key, and provider restrictions for keys; applicable taxes and provider-specific usage limits may apply.

Quick Facts

Category
LLM API router
Catalog
4 abliterated models listed
API compatibility
OpenAI-compatible Chat Completions and Responses endpoints
Cataloged providers
Provider count varies by model; listed examples have 1–5 providers
Representative model context
Up to 1M tokens on the listed DeepSeek and GLM 5.3 Abliterated pages
Pricing model
Free option and pay-as-you-go pricing; pricing page states a 5.5% platform fee on downstream cost