Supported Providers and Models
Routor connects to 13 providers out of the box. All routing happens automatically. You do not choose a provider - Routor picks based on the request.📷 [Screenshot: Provider health dashboard showing all 13 providers with green status indicators]
Providers
| Provider | Models available | Notes |
|---|---|---|
| OpenAI | GPT-5.4, GPT-5.5 | Strong general and coding |
| Anthropic | Claude Opus 4.6 / 4.7 / 4.8, Sonnet 4.5 / 4.6, Haiku 4.5 | Best creative writing and long context |
| Gemini 3.1 Flash-Lite, Gemini 3.1 Pro, Gemini 3.5 Flash, Gemma 4 | Fast and cheap at scale | |
| DeepSeek | DeepSeek V4 Flash, DeepSeek V4 Pro | Best reasoning-per-dollar |
| xAI | Grok 4, Grok 4.1 Fast Reasoning | Strong general model |
| NVIDIA | Nemotron 3 Ultra | Fast open-weight inference |
| Moonshot | Kimi K2.6, Kimi K2.7 Code | Long context, strong at code |
| MiniMax | MiniMax M3 | Strong value across most tasks |
| Z.AI | GLM-5.2, GLM-4.7 Flash | Open-weight, competitive with frontier |
| Alibaba (Qwen) | Qwen3.5-397B, Qwen3.6-27B, Qwen3.7-Max | Strong multilingual |
| Mistral | Mistral Large 3, Medium 3.5, Small 4, Devstral 2 | Strong European-hosted option |
| Microsoft | Phi-4, Mai-Code-1-Flash | Enterprise / compliance-friendly routing |
| Xiaomi | MiMo-V2.5-Pro | Efficient bilingual reasoning |
Model Pricing
Input and output costs at provider list price. Routor adds a 10% routing margin - see Plans & Pricing.| Model | Tier | Input /1M tokens | Output /1M tokens | Context |
|---|---|---|---|---|
microsoft/phi-4 | NANO | $0.10 | $0.10 | 128K |
zai/glm-4.7-flash | NANO | $0.20 | $0.20 | 128K |
google/gemini-3.1-flash-lite-preview | NANO | $0.25 | $1.50 | 1M |
qwen/qwen3.6-27b | SIMPLE | $0.30 | $1.50 | 128K |
anthropic/claude-haiku-4.5 | SIMPLE | $1.00 | $5.00 | 200K |
zai/glm-5.2 | SIMPLE | $1.40 | $4.40 | 128K |
deepseek/deepseek-v4-flash | LIGHT | $0.14 | $0.28 | 128K |
moonshot/kimi-k2.6 | LIGHT | $0.68 | $3.42 | 256K |
google/gemini-3.5-flash | LIGHT | $1.50 | $9.00 | 1M |
mistral/mistral-large-3 | STANDARD | $2.00 | $6.00 | 128K |
openai/gpt-5.4 | STANDARD | $2.50 | $15.00 | 200K |
anthropic/claude-sonnet-4.6 | STANDARD | $3.00 | $15.00 | 200K |
deepseek/deepseek-v4-pro | COMPLEX | $0.44 | $0.87 | 128K |
xai/grok-4 | COMPLEX | $3.00 | $15.00 | 131K |
anthropic/claude-opus-4.8 | COMPLEX | $5.00 | $25.00 | 200K |
openai/gpt-5.5 | COMPLEX | $5.00 | $30.00 | 200K |
Prices as of June 2026. Model pricing changes frequently - check the Models page in your dashboard for current rates.
Model Capabilities
Not every model supports every capability. Routor filters the pool automatically based on what your request needs.| Provider / Model | Vision | Files | Tools | Audio | Video |
|---|---|---|---|---|---|
| OpenAI GPT-5.5 | Yes | Yes | Yes | Yes | No |
| OpenAI GPT-5.4 | Yes | No | Yes | No | No |
| Claude Opus 4.8 | Yes | Yes | Yes | No | No |
| Claude Sonnet 4.6 | Yes | Yes | Yes | No | No |
| Claude Haiku 4.5 | Yes | No | Yes | No | No |
| Gemini 3.1 Pro | Yes | Yes | Yes | Yes | Yes |
| Gemini 3.5 Flash | Yes | Yes | Yes | Yes | No |
| DeepSeek V4 Pro | No | No | No | No | No |
| GLM-5.2 | Yes | No | Yes | No | No |
| Qwen3.7-Max | No | No | Yes | No | No |
How Providers Are Validated
When Routor starts, it pings every configured provider using their/models endpoint. No tokens consumed, no cost. Any provider that fails because of an invalid key, network error, or rate limit gets removed from routing until the next restart.
You will never get routed to a broken provider. Check the current status of all providers in the Provider Health dashboard.