qwen3-6-35b-a3b
Low-cost Chinese-language chat for batch processing, customer support, and lightweight coding.
Pricing: Input 24 credits / 1M tokens (≈ $0.12), Output 216 credits / 1M tokens (≈ $1.08).
Prices updated
How can I help you today?
This demo page does not include the full memory features of the client. For the complete experience, please use the client or the CLI.
Qwen3.6 35B A3B API
Low-cost Chinese-language chat for batch processing, customer support, and lightweight coding.
Recommended uses
Batch classification, extraction, summaries, and Chinese customer-service replies. Use Flash for inexpensive output, 27B for a dense model, or 35B A3B for sparse expert inference.
Context, tools, and reasoning
Catalog context: 262,144 tokens; default provider: 262,144; maximum output: 235,929. Supports tools, tool_choice, structured output, and optional reasoning (enabled by default). Context limits depend on the selected upstream provider.
Pricing
Per 1M tokens: input 24 credits; output 216 credits. Rates follow upstream cost × the admin chat markup. Cached input uses its upstream discount; reasoning tokens count as output. Final charges follow actual upstream usage, rounded up to whole credits.
API usage
Send model qwen3-6-35b-a3b and an OpenAI-style messages array to POST /v1/chat/completions. Use stream: true for SSE; pass tools and tool_choice for tool calls.
| Input | 24 credits 1M tokens≈ $0.12 |
| Output | 216 credits 1M tokens≈ $1.08 |
Billed per token: input and output are priced separately, and thinking tokens count as output. The Playground charges exactly the same way.
Read API docs →AI Agents · Claude Code / Cursor / Trae →curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen3-6-35b-a3b","messages":[{"role":"user","content":"Hello"}]}'