# RouterHub

> Uncensored and abliterated AI models — GLM, DeepSeek, Qwen and Kimi variants plus GPT, Claude, Gemini and Grok — through one API key. OpenAI-compatible and Anthropic-compatible APIs. Use each model’s supported API. Pay per token.
> Web chat and one prepaid API key for 26 models. Pay per token, no subscription. Catalogue prices as of 2026-11-08.

## Uncensored and abliterated models

Uncensored models are reduced-refusal language model variants for open-ended generation, coding and creative work. Abliteration reduces refusal behavior through weight-level changes. Use the exact model IDs and supported protocols in the public catalogue.

## APIs

- Base URL: https://routerhub.si/v1
- Responses (GPT, Codex): POST https://routerhub.si/v1/responses, header `Authorization: Bearer $ROUTERHUB_API_KEY`. IDs: `gpt-6.1-sol`, `gpt-6-astra`, `gpt-6.1-terra`
- Anthropic Messages (Claude): POST https://routerhub.si/v1/messages, headers `x-api-key: $ROUTERHUB_API_KEY` and `anthropic-version: 2023-06-01`. IDs: `claude-fable-5-1`, `claude-opus-5-5`, `claude-sonnet-5-5`, `claude-haiku-5-5`
- Chat Completions (DeepSeek, GLM, Grok, Gemini, Qwen, Kimi): POST https://routerhub.si/v1/chat/completions, header `Authorization: Bearer $ROUTERHUB_API_KEY`. IDs: `gemini-4-argon`, `grok-4.7`, `deepseek-v4-pro`, `deepseek-v4-pro-uncensored`, `deepseek-v4-pro-abliterated`, `deepseek-v4.1-flash`, `deepseek-v4.1-flash-uncensored`, `deepseek-v4.1-flash-abliterated`, `deepseek-v4.1-flash-1017-abliterated`, `glm-5.3`, `glm-5.3-uncensored`, `glm-5.3-abliterated`, `glm-5.3-flash`, `glm-5.3-flash-uncensored`, `glm-5.3-flash-abliterated`, `qwen3.8-max`, `qwen3.8-max-uncensored`, `kimi-k3.1-pro`, `kimi-k3.1-pro-uncensored`

## Tool compatibility

OpenCode supports the published Responses, Anthropic Messages, and Chat Completions models. Continue supports compatible models on these APIs. Cline supports Chat Completions and Claude models available in its Anthropic model picker; choose OpenCode or Continue for a Claude model missing from that picker. Codex requires Responses; Claude Code and Claude Desktop require Anthropic Messages. DeepSeek, GLM, Grok, Gemini, Qwen and Kimi use Chat Completions. Each setup guide and MCP list_models with a tool filter returns only compatible model IDs.

## Pricing

Prepaid credits, billed per token at each model's published rate. No subscription or monthly fee. Creating an account is free; chat and the API are paid from prepaid credits. Up to $5 free on your first top-up of $20 or more. A typical chat message (about 1,000 input and 500 output tokens) costs a fraction of a cent on most models.

## Links

- Web chat (account and prepaid credits required): https://routerhub.si/
- Models and prices: https://routerhub.si/models
- Pricing: https://routerhub.si/pricing
- Uncensored models: https://routerhub.si/models/uncensored
- Abliterated models: https://routerhub.si/models/abliterated
- Uncensored vs abliterated: https://routerhub.si/guides/uncensored-vs-abliterated
- Uncensored AI API setup: https://routerhub.si/guides/uncensored-ai-api
- Evaluating uncensored models: https://routerhub.si/guides/evaluating-uncensored-models
- Exact model pages: https://routerhub.si/models/EXACT_MODEL_ID (Markdown: https://routerhub.si/models/EXACT_MODEL_ID.md)
- Connect your agent: https://routerhub.si/agents
- Agent instructions: https://routerhub.si/agents.md
- Full agent setup context: https://routerhub.si/agent-setup.md (query: tool, model, shell)
- Read-only MCP endpoint: https://routerhub.si/mcp (Streamable HTTP; no API key; list_models and get_setup_guide)
- Human setup guides: https://routerhub.si/docs
- DeepSeek API pricing and setup: https://routerhub.si/guides/deepseek
- GLM API pricing and setup: https://routerhub.si/guides/glm
- Grok API pricing and setup: https://routerhub.si/guides/grok
- Kimi API pricing and setup: https://routerhub.si/guides/kimi
- Agent quickstart: https://routerhub.si/quickstart.md
- Complete setup reference: https://routerhub.si/llms-full.txt
- Public model catalogue with protocols and rates: https://routerhub.si/models.json
- OpenAPI inference reference: https://routerhub.si/openapi.json
- Status: https://routerhub.si/status
- Create account: https://routerhub.si/register
- API keys: https://routerhub.si/dashboard/keys
- Billing and credits: https://routerhub.si/dashboard/billing
- Usage: https://routerhub.si/dashboard/usage
- Support tickets: https://routerhub.si/dashboard/support

## Account and agent safety

A human must create the RouterHub account, add prepaid credits, create the API key, and enter it into the target tool. Agents can provide instructions and configuration, but must not request or handle secrets or initiate billable requests without explicit user approval. Never request, receive, store, or commit the user's password or API key.

## Models

All rates below are USD per million tokens as of 2026-11-08. Read models.json for the latest rates and availability. Never select a model marked unavailable. Missing prices or context limits are not published; do not infer them.

### GPT-6.1 Sol

- ID: `gpt-6.1-sol`
- Details and setup: https://routerhub.si/models/gpt-6.1-sol
- Provider: OpenAI
- Variant: Standard
- Protocols: responses (OpenAI-compatible Responses API, https://routerhub.si/v1/responses)
- Availability: preview
- Input per million tokens: $0.149477
- Output per million tokens: $0.747385
- Cached input per million tokens (cache hit): $0.00747385
- Cache write per million tokens: $0.18684625
- Context limit: 1,050,000 tokens
- Maximum input: 922,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Codex CLI, VS Code + Continue, cURL / Python

### GPT-6 Astra

- ID: `gpt-6-astra`
- Details and setup: https://routerhub.si/models/gpt-6-astra
- Provider: OpenAI
- Variant: Standard
- Protocols: responses (OpenAI-compatible Responses API, https://routerhub.si/v1/responses)
- Availability: preview
- Input per million tokens: $0.747385
- Output per million tokens: $3.736925
- Cached input per million tokens (cache hit): $0.0747385
- Cache write per million tokens: $0.93423125
- Context limit: 1,050,000 tokens
- Maximum input: 922,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Codex CLI, VS Code + Continue, cURL / Python

### GPT-6.1 Terra

- ID: `gpt-6.1-terra`
- Details and setup: https://routerhub.si/models/gpt-6.1-terra
- Provider: OpenAI
- Variant: Standard
- Protocols: responses (OpenAI-compatible Responses API, https://routerhub.si/v1/responses)
- Availability: preview
- Input per million tokens: $0.07
- Output per million tokens: $0.35
- Cached input per million tokens (cache hit): $0.004
- Cache write per million tokens: $0.09
- Context limit: 1,050,000 tokens
- Maximum input: 922,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Codex CLI, VS Code + Continue, cURL / Python

### Claude Fable 5.1

- ID: `claude-fable-5-1`
- Details and setup: https://routerhub.si/models/claude-fable-5-1
- Provider: Anthropic
- Variant: Standard
- Protocols: messages (Anthropic-compatible Messages API, https://routerhub.si/v1/messages)
- Availability: preview
- Input per million tokens: $1.793722
- Output per million tokens: $8.96861
- Cached input per million tokens (cache hit): $0.04484305
- Cache write per million tokens: $2.2421525
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Claude Code, VS Code + Continue, VS Code + Cline, Claude Desktop, cURL / Python

### Claude Opus 5.5

- ID: `claude-opus-5-5`
- Details and setup: https://routerhub.si/models/claude-opus-5-5
- Provider: Anthropic
- Variant: Standard
- Protocols: messages (Anthropic-compatible Messages API, https://routerhub.si/v1/messages)
- Availability: preview
- Input per million tokens: $0.717489
- Output per million tokens: $3.587445
- Cached input per million tokens (cache hit): $0.03587445
- Cache write per million tokens: $0.89686125
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Claude Code, VS Code + Continue, VS Code + Cline, Claude Desktop, cURL / Python

### Claude Sonnet 5.5

- ID: `claude-sonnet-5-5`
- Details and setup: https://routerhub.si/models/claude-sonnet-5-5
- Provider: Anthropic
- Variant: Standard
- Protocols: messages (Anthropic-compatible Messages API, https://routerhub.si/v1/messages)
- Availability: preview
- Input per million tokens: $0.3587445
- Output per million tokens: $1.7937225
- Cached input per million tokens (cache hit): $0.03587445
- Cache write per million tokens: $0.448430625
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Claude Code, VS Code + Continue, VS Code + Cline, Claude Desktop, cURL / Python

### Claude Haiku 5.5

- ID: `claude-haiku-5-5`
- Details and setup: https://routerhub.si/models/claude-haiku-5-5
- Provider: Anthropic
- Variant: Standard
- Protocols: messages (Anthropic-compatible Messages API, https://routerhub.si/v1/messages)
- Availability: preview
- Input per million tokens: $0.0179375
- Output per million tokens: $0.0896875
- Cached input per million tokens (cache hit): $0.00179375
- Cache write per million tokens: $0.022421875
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, Claude Code, VS Code + Continue, VS Code + Cline, Claude Desktop, cURL / Python

### Gemini 4 Argon

- ID: `gemini-4-argon`
- Details and setup: https://routerhub.si/models/gemini-4-argon
- Provider: Google
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: available
- Input per million tokens: $0.25
- Output per million tokens: $1.25
- Cached input per million tokens (cache hit): $0.0125
- Context limit: 1,048,576 tokens
- Maximum input: 1,048,575 tokens
- Maximum output: 65,536 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### Grok 4.7

- ID: `grok-4.7`
- Details and setup: https://routerhub.si/models/grok-4.7
- Provider: xAI
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.071749
- Output per million tokens: $0.215247
- Cached input per million tokens (cache hit): $0.01793725
- Context limit: 500,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4 Pro

- ID: `deepseek-v4-pro`
- Details and setup: https://routerhub.si/models/deepseek-v4-pro
- Provider: DeepSeek
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.15
- Output per million tokens: $0.3
- Cached input per million tokens (cache hit): $0.0016
- Context limit: 1,000,000 tokens
- Maximum output: 384,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4 Pro Uncensored

- ID: `deepseek-v4-pro-uncensored`
- Details and setup: https://routerhub.si/models/deepseek-v4-pro-uncensored
- Provider: DeepSeek
- Variant: Uncensored
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.2
- Output per million tokens: $0.4
- Cached input per million tokens (cache hit): $0.0016
- Context limit: 1,000,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4 Pro Abliterated

- ID: `deepseek-v4-pro-abliterated`
- Details and setup: https://routerhub.si/models/deepseek-v4-pro-abliterated
- Provider: DeepSeek
- Variant: Abliterated
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.4
- Output per million tokens: $1.6
- Cached input per million tokens (cache hit): $0.04
- Cache write per million tokens: $0.4
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4.1 Flash

- ID: `deepseek-v4.1-flash`
- Details and setup: https://routerhub.si/models/deepseek-v4.1-flash
- Provider: DeepSeek
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.1
- Output per million tokens: $0.4
- Cached input per million tokens (cache hit): $0.0026906
- Context limit: 1,000,000 tokens
- Maximum output: 384,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4.1 Flash Uncensored

- ID: `deepseek-v4.1-flash-uncensored`
- Details and setup: https://routerhub.si/models/deepseek-v4.1-flash-uncensored
- Provider: DeepSeek
- Variant: Uncensored
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.15
- Output per million tokens: $0.6
- Cached input per million tokens (cache hit): $0.0026906
- Context limit: 1,000,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4.1 Flash Abliterated

- ID: `deepseek-v4.1-flash-abliterated`
- Details and setup: https://routerhub.si/models/deepseek-v4.1-flash-abliterated
- Provider: DeepSeek
- Variant: Abliterated
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.3
- Output per million tokens: $1.25
- Cached input per million tokens (cache hit): $0.055
- Cache write per million tokens: $0.3
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### DeepSeek V4.1 Flash 1017 Abliterated

- ID: `deepseek-v4.1-flash-1017-abliterated`
- Details and setup: https://routerhub.si/models/deepseek-v4.1-flash-1017-abliterated
- Provider: DeepSeek
- Variant: Abliterated
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.3
- Output per million tokens: $1.25
- Cached input per million tokens (cache hit): $0.055
- Cache write per million tokens: $0.3
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### GLM 5.3

- ID: `glm-5.3`
- Details and setup: https://routerhub.si/models/glm-5.3
- Provider: Z.ai
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.15
- Output per million tokens: $0.471428571429
- Cached input per million tokens (cache hit): $0.116591985714
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### GLM 5.3 Uncensored

- ID: `glm-5.3-uncensored`
- Details and setup: https://routerhub.si/models/glm-5.3-uncensored
- Provider: Z.ai
- Variant: Uncensored
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.2
- Output per million tokens: $0.628571428571
- Cached input per million tokens (cache hit): $0.116591985714
- Context limit: 1,000,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### GLM 5.3 Abliterated

- ID: `glm-5.3-abliterated`
- Details and setup: https://routerhub.si/models/glm-5.3-abliterated
- Provider: Z.ai
- Variant: Abliterated
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.4
- Output per million tokens: $1.33333333333
- Cached input per million tokens (cache hit): $0.16
- Context limit: 1,048,576 tokens
- Maximum input: 917,504 tokens
- Maximum output: 131,072 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### GLM 5.3 Flash

- ID: `glm-5.3-flash`
- Details and setup: https://routerhub.si/models/glm-5.3-flash
- Provider: Z.ai
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.1
- Output per million tokens: $0.333333333333
- Cached input per million tokens (cache hit): $0.013453
- Context limit: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### GLM 5.3 Flash Uncensored

- ID: `glm-5.3-flash-uncensored`
- Details and setup: https://routerhub.si/models/glm-5.3-flash-uncensored
- Provider: Z.ai
- Variant: Uncensored
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.15
- Output per million tokens: $0.5
- Cached input per million tokens (cache hit): $0.013453
- Context limit: 1,000,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### GLM 5.3 Flash Abliterated

- ID: `glm-5.3-flash-abliterated`
- Details and setup: https://routerhub.si/models/glm-5.3-flash-abliterated
- Provider: Z.ai
- Variant: Abliterated
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.3
- Output per million tokens: $1
- Cached input per million tokens (cache hit): $0.12
- Context limit: 1,048,576 tokens
- Maximum input: 917,504 tokens
- Maximum output: 131,072 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### Qwen 3.8 Max

- ID: `qwen3.8-max`
- Details and setup: https://routerhub.si/models/qwen3.8-max
- Provider: Qwen
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: available
- Input per million tokens: $0.2
- Output per million tokens: $0.6
- Cached input per million tokens (cache hit): $0.025
- Cache write per million tokens: $0.25
- Context limit: 1,000,000 tokens
- Maximum input: 983,000 tokens
- Maximum output: 131,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### Qwen 3.8 Max Uncensored

- ID: `qwen3.8-max-uncensored`
- Details and setup: https://routerhub.si/models/qwen3.8-max-uncensored
- Provider: Qwen
- Variant: Uncensored
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.25
- Output per million tokens: $0.75
- Cached input per million tokens (cache hit): $0.03125
- Cache write per million tokens: $0.3125
- Context limit: 1,000,000 tokens
- Maximum input: 983,000 tokens
- Maximum output: 131,000 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### Kimi K3.1 Pro

- ID: `kimi-k3.1-pro`
- Details and setup: https://routerhub.si/models/kimi-k3.1-pro
- Provider: Moonshot AI
- Variant: Standard
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: available
- Input per million tokens: $0.2
- Output per million tokens: $1
- Cached input per million tokens (cache hit): $0.02
- Context limit: 1,048,576 tokens
- Maximum input: 1,048,575 tokens
- Maximum output: 1,048,576 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

### Kimi K3.1 Pro Uncensored

- ID: `kimi-k3.1-pro-uncensored`
- Details and setup: https://routerhub.si/models/kimi-k3.1-pro-uncensored
- Provider: Moonshot AI
- Variant: Uncensored
- Protocols: chat (OpenAI-compatible Chat Completions API, https://routerhub.si/v1/chat/completions)
- Availability: preview
- Input per million tokens: $0.3
- Output per million tokens: $1.5
- Cached input per million tokens (cache hit): $0.03
- Context limit: 1,048,576 tokens
- Maximum input: 1,048,575 tokens
- Maximum output: 1,048,576 tokens
- Compatible tools: OpenCode, VS Code + Continue, VS Code + Cline, Hermes Agent, cURL / Python

## API references

- OpenAPI 3.1: https://routerhub.si/openapi.json
- Quickstart: https://routerhub.si/quickstart.md