AI Gateway Models

Last Updated: October 12, 2026

Salad AI Gateway is currently in beta.

Available Models

qwen3.6-35b-a3b

Property	Value
Model ID	`qwen3.6-35b-a3b`
Model name	Qwen3.6 35B-A3B
Architecture	Mixture of Experts (MoE)
Context window	262,144 tokens
Input	Text, image
Output	Text

Best for: Agentic tasks, complex multi-step reasoning, code generation, instruction following. This is the recommended model for most agentic and coding use cases. It handles tool calling reliably, supports structured output, and performs well in long agentic sessions.

qwen3.6-27b

Property	Value
Model ID	`qwen3.6-27b`
Model name	Qwen3.6 27B
Architecture	Dense
Context window	195,200 tokens
Input	Text, image
Output	Text

Best for: General-purpose workloads that need a balance of capability and speed.

qwen3.5-35b-a3b

Property	Value
Model ID	`qwen3.5-35b-a3b`
Model name	Qwen3.5 35B-A3B
Architecture	Mixture of Experts (MoE)
Active params	~3.5B (35B total)
Context window	262,144 tokens
Input	Text, image
Output	Text

Best for: Agentic tasks, complex multi-step reasoning, code generation, instruction following. The Mixture of Experts architecture activates only a subset of parameters per token, providing strong reasoning capability at lower latency than a dense 35B model. It handles tool calling reliably and performs well in long agentic sessions.

qwen3.5-9b

Property	Value
Model ID	`qwen3.5-9b`
Model name	Qwen3.5 9B
Architecture	Dense
Context window	196,608 tokens
Input	Text, image
Output	Text

Best for: High-volume, simple queries where speed matters most. This is the fastest model in the lineup.

Choosing a Model

Use Case	Recommended Model
Agentic coding (Cline, Roo Code)	`qwen3.6-35b-a3b`
Complex reasoning / planning	`qwen3.6-35b-a3b`
Cost-efficient agentic tasks	`qwen3.5-35b-a3b`
General purpose	`qwen3.6-27b`
High-volume, simple queries	`qwen3.5-9b`

API Usage

Specify the model ID in the model field of your request:

curl https://ai.salad.cloud/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $SALAD_AI_GATEWAY_API_KEY" \
  -d '{
    "model": "qwen3.6-35b-a3b",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

To list available models programmatically:

curl https://ai.salad.cloud/v1/models \
  -H "Authorization: Bearer $SALAD_AI_GATEWAY_API_KEY"

Notes

All models support the /v1/chat/completions endpoint with streaming ("stream": true).
All models support text and image inputs, text outputs, tool calling, structured outputs, and reasoning.
Input and output tokens share the context window. A request’s prompt plus its generated output (max_tokens) cannot exceed the model’s context window.
Context window limits are enforced server-side. If your input exceeds the limit, the request will return an error.
The model catalog may expand during beta.

AI Gateway

How-to Guides

Reference

Integrations

Available Models

qwen3.6-35b-a3b

qwen3.6-27b

qwen3.5-35b-a3b

qwen3.5-9b

Choosing a Model

API Usage

Notes

​Available Models

​qwen3.6-35b-a3b

​qwen3.6-27b

​qwen3.5-35b-a3b

​qwen3.5-9b

​Choosing a Model

​API Usage

​Notes

Available Models

qwen3.6-35b-a3b

qwen3.6-27b

qwen3.5-35b-a3b

qwen3.5-9b

Choosing a Model

API Usage

Notes