InclusionAI / inclusionai/ling-3.0-flash

Ling 3.0 Flash - access through LLMTR

Ling 3.0 Flash is InclusionAI's 124-billion-parameter Mixture-of-Experts model, activating roughly 5.1 billion parameters per token. It is tuned for token efficiency in agentic workloads: it supports native tool calling, reads repeated prefixes from a prompt cache, and offers a 256K context window. It reasons by default, returning that chain separately in `reasoning_content`, whose tokens are counted inside `completion_tokens`. To turn reasoning off, send `reasoning_effort: "none"` or append the `:none` suffix to the model id - that is the only level with a measured effect on this model, so the others are not offered even though the upstream accepts them. A single response can be at most 32,768 tokens. It accepts text only - no image or audio input, and no schema-enforced JSON output. With reasoning on, the model can think at length on some prompts and exhaust the budget; when you need a short, direct answer, `none` is both faster and cheaper.

Technical specifications

Canonical IDinclusionai/ling-3.0-flash
ProviderInclusionAI
Context window262,144 tokens
OperationsCHAT_COMPLETIONS
Modalitiestext

Pricing

An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.

OperationMetricUnitPrice
CHAT_COMPLETIONSINPUT_TEXTPER_1M_TOKENS$0.060000
CHAT_COMPLETIONSCACHE_READPER_1M_TOKENS$0.012000
CHAT_COMPLETIONSOUTPUT_TEXTPER_1M_TOKENS$0.180000

Example usage

With existing OpenAI SDK flows, change only the base URL and model identifier.

curl https://llmtr.com/v1/chat/completions \
  -H "Authorization: Bearer llmtr-your_key" \
  -H "Content-Type: application/json" \
  -d '{"model":"inclusionai/ling-3.0-flash","messages":[{"role":"user","content":"Hello"}]}'

Related models