AI Gateway Models

Reference for all models available through Salad AI Gateway, including context windows, capabilities, and recommended use cases.

Last Updated: May 18, 2026

Salad AI Gateway is currently in closed beta. The model catalog will expand as the service moves toward general availability.

Available Models

qwen3.6-35b-a3b

Property	Value
Model ID	qwen3.6-35b-a3b
Model name	Qwen3.6 35B-A3B
Context window	262,144 tokens
Max input	262,144 tokens
Max output	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
Context window	262,144 tokens
Max input	262,144 tokens
Max output	262,144 tokens
Input	Text, image
Output	Text

Best for: General-purpose tasks requiring a balance of capability and speed.

A strong all-around model. Slightly faster than qwen3.6-35b-a3b on simpler tasks, with comparable instruction-following quality. A good choice when you need consistent performance across a range of task types.

---

qwen3.5-9b

Property	Value
Model ID	qwen3.5-9b
Model name	Qwen3.5 9B
Context window	262,144 tokens
Max input	262,144 tokens
Max output	262,144 tokens
Input	Text, image
Output	Text

Best for: High-volume queries, simple Q&A, fast responses where latency matters.

The fastest model in the lineup. Well-suited for applications that need quick turnaround on straightforward prompts. May struggle with complex multi-step reasoning or large codebases compared to the larger models.

---

Choosing a Model

Use Case	Recommended Model
Agentic coding (Cline, Roo Code)	qwen3.6-35b-a3b
Complex reasoning / planning	qwen3.6-35b-a3b
General chat / assistant	qwen3.6-27b
Simple Q&A / high volume	qwen3.5-9b
Fast autocomplete	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_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_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.
• Context window limits are enforced server-side. If your input exceeds the limit, the request will return an error.
• Additional models will be added during the beta period and at general availability.