The Orchestrator › Models › InclusionAI
InclusionAI: inclusionAI: Ling 3.1 Flash
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Specifications
| Provider | InclusionAI |
| Model ID | inclusionai/ling-3.1-flash |
| Context window | 1M tokens (1,000,000) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter, Vercel AI Gateway |
| Released | 2026-10-02 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | On by default |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | inclusionai/ling-3.1-flash | $0.045 | $0.135 | 1M |
| standard | TrustedRouter | inclusionai/ling-3.1-flash | $0.317 | $0.95 | 1M |
| standard | Vercel AI Gateway | inclusionai/ling-3.1-flash | $0.3 | $0.9 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.3 | $0.9 | 262K |
| 2026-11-14 | $0.317 | $0.95 | 1M |
| 2026-11-14 | $0.045 | $0.135 | 1M |
Capabilities
Agentic tool useReasoning mode1M+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, logprobs, max_tokens, presence_penalty, reasoning, repetition_penalty, seed, stop, temperature, tool_choice, tools, top_k, top_logprobs, top_p