Ling 3.1 Flash
Trial capped at 256K context; inclusionAI says it will enable ~1M context and open-source the model after the two-week trial (press, not an official page). No weights, license or official pricing yet; update open_weights/license/pricing when released. Served on Vercel by Novita.
- Context window
- 262,144 tokens
- Max output
- 32,768 tokens
- Input
- text
- Output
- text
- License
- proprietary
- Pricing
- input: $0 · output: $0 (per 1M tokens (USD); free trial on gateways (Vercel lists free through 2026-10-13)) source
- Verified
- 2026-10-02
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| OpenRouter | inclusionai/ling-3.1-flash | openrouter.ai/inclusionai/ling-3.1-flash | — |
| Vercel AI Gateway | inclusionai/ling-3.1-flash | vercel.com/ai-gateway/models/ling-3.1-flash | — |
Notable capabilities (1)
- 560B-total / 25B-active hybrid-reasoning MoE: Sparse MoE for coding, agents and tool use; reasoning enabled by default (can be turned off via the reasoning parameter on OpenRouter); tools and tool_choice supported. source
Free trial model as of Oct 2, 2026. Example (OpenRouter, OpenAI-compatible):
curl https://openrouter.ai/api/v1/chat/completions -H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" -d '{"model":"inclusionai/ling-3.1-flash","messages":[{"role":"user","content":"Hello"}]}'
Timeline entry
- Ant Group's inclusionAI launches Ling 3.1 Flash, a 560B-parameter MoE, as a free trial with open weights promised ★★★
Around Sept 29–30, 2026 Ant Group's AI unit inclusionAI released Ling 3.1 Flash, a hybrid-reasoning mixture-of-experts model with 560B total and 25B active parameters, aimed at coding, agents and tool use. It launched as a two-week free trial (256K context) on gateways such as Vercel AI Gateway…