Enhanced Auto-Routing & 5 New Free Models via RouteWay

We're excited to expand our auto-routing capabilities with 5 new free models through our RouteWay provider integration! These models enhance our intelligent routing system by providing more cost-effective alternatives.

🤖 Auto-Routing with Free Models

Expanded Free Options: Our intelligent routing system now has more free alternatives to choose from.

Example Usage: Use auto-routing with the free_models_only flag to prioritize these cost-effective models:

1curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
2  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "auto",
6    "free_models_only": true,
7    "messages": [
8      {
9        "role": "user",
10        "content": "Explain quantum computing in simple terms"
11      }
12    ]
13  }'

1curl -X POST "https://api.llmgateway.io/v1/chat/completions" \
2  -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \
3  -H "Content-Type: application/json" \
4  -d '{
5    "model": "auto",
6    "free_models_only": true,
7    "messages": [
8      {
9        "role": "user",
10        "content": "Explain quantum computing in simple terms"
11      }
12    ]
13  }'

The system will automatically select the best available free model from the expanded pool, including these new RouteWay options.

🆓 New Free Models

All models are available with generous usage limits and zero per-token costs:

DeepSeek R1T2 Chimera (Free)

1deepseek-r1t2-chimera-free

1deepseek-r1t2-chimera-free

• Cost: $0.00 input/output tokens
• Context Window: 128,000 tokens
• Capabilities: Streaming, JSON output

GLM-4.5 Air (Free)

1glm-4.5-air-free

1glm-4.5-air-free

• Cost: $0.00 input/output tokens
• Context Window: 128,000 tokens
• Capabilities: Streaming, JSON output

Kimi K2 (Free)

1kimi-k2-free

1kimi-k2-free

• Cost: $0.00 input/output tokens
• Context Window: 128,000 tokens
• Capabilities: Streaming, JSON output

GPT-OSS 20B (Free)

1gpt-oss-20b-free

1gpt-oss-20b-free

• Cost: $0.00 input/output tokens
• Context Window: 128,000 tokens
• Capabilities: Streaming, JSON output

GPT-4.1 (Free)

1gpt-4.1-free

1gpt-4.1-free

• Cost: $0.00 input/output tokens
• Context Window: 128,000 tokens
• Capabilities: Streaming, JSON output

🚀 Getting Started

Auto-Routing: These models are automatically available in our routing system - no configuration needed.

Direct Access: Use the model identifiers above (with -free suffix) to access specific models directly.

Browse Models: Visit our Models Directory to explore and compare all available options.

This expansion significantly enhances our auto-routing system's ability to provide cost-effective AI solutions while maintaining high quality and availability.