InclusionAIText

Ling-3.0-flash

Ling-3.0-flash is InclusionAI's model at $0.07 input and $0.22 output per million tokens, with a 262K context window. On a typical 3:1 input-to-output mix that blends to roughly $0.11 per million tokens, placing it in the budget band of the 87 models tracked here — cheaper than 92% of them.

Open cost calculator View provider

MODEL OVERVIEW

Context window262K

Input price$0.07 / 1M

Output price$0.22 / 1M

Output speed180 tok/s

Quality score80

Data updatedUpdated Aug 2026

Price verified2026-08-16 · Official

Price note124B MoE activating ~5.1B parameters per token; list price is ¥0.40 / ¥1.20 per 1M tokens, with a launch promotion running 65% off on OpenRouter

By price, Ling-3.0-flash ranks 7th cheapest of 87 on input and 10th on output. Its quality score of 80 ranks 61st of 87, and on value (quality score ÷ output price) it ranks 10th of 87. Its blended rate sits 97% below the catalog average.

In real billing terms: a support chatbot handling 50,000 turns a month (2,000 input / 500 output tokens each) costs about $13 per month on Ling-3.0-flash, while a RAG workload of 20,000 queries (8,000 input / 800 output tokens each) runs about $15. Because output is priced 3.1× input here, long-generation tasks scale cost fastest — cap output length before you optimise anything else.

A 262K context window holds roughly 349 pages of A4 text (at ~750 tokens per page), ranking 51st of 87 here. That covers typical RAG and multi-turn chat, though book-length inputs still need retrieval and chunking. Output runs at about 180 tok/s (15th fastest of 87), fast enough for real-time interaction and high-throughput batches.

We track 1 InclusionAI models, and Ling-3.0-flash's blended rate sits 0% above that provider's average. If your task tolerates a little less headroom, qwen3.7-flash (Alibaba) blends about 49% cheaper at a quality score of 82, and is worth benchmarking first. Going the other way, mercury-2.5-preview scores 82 on quality for about 37% less.

Our read on it

$0.07/$0.22 with a 262K context at 180 tokens/second — a textbook entry priced to buy adoption.

The MoE architecture is why this price is possible

Ling-3.0-flash is a 124B-parameter mixture-of-experts model that activates roughly 5.1B parameters per token. That is the technical reason it can hit 180 tokens/second and a $0.07 input rate at the same time: inference cost tracks active parameters, not total ones.

One caveat has to be stated plainly. The list price is ¥0.40/¥1.20 per 1M tokens, and a launch promotion currently running 65% off on OpenRouter is what produces the dollar figures on this page. When the promotion ends, the rate returns to list. Budget against the list price, not against what you see today.

Against the same speed band, context is the edge

The 180 tokens/second band also holds claude-haiku-4-5 ($1/$5, quality 82, 200K context) and deepseek-v4-flash ($0.14/$0.28, quality 88, 1,000K context). Ling gives you 30% more context than haiku for a small fraction of the money. Against deepseek-v4-flash the picture reverses: more context and six more quality points, for a price difference that is small in absolute terms.

So the honest ranking is that if you want fast, cheap and long-context, deepseek-v4-flash is usually the more complete answer — unless its peak-hour surcharge is a problem for your traffic pattern. Flat, all-hours pricing is Ling's most durable advantage over it.

Where it belongs in an architecture

The quality score of 80 draws the boundary. That is enough for classification, routing, extraction, rewriting, first drafts and high-volume first-pass filtering. It is not enough to carry reasoning, and it should not be producing final copy that reaches a customer unedited.

The highest-value use is the top of a funnel: let Ling handle 80% of requests at close to zero marginal cost, and escalate only the cases it flags as hard to claude-sonnet-5 or deepseek-reasoner-v4. In a tiered setup the $0.07 input rate shows up directly on the invoice while the quality risk is absorbed by the layer above. That is the question worth asking about any ultra-cheap model — not whether it can replace your main one, but how much unnecessary traffic it can take away from it.

Estimated monthly cost

Monthly API spend across four common workloads, next to the cheapest model we track.

Workload	Usage assumption	This model	Cheapest model
Support chatbot	2,000 input / 500 output tokens per turn, 50,000 turns per month	$13	$3.00
RAG document Q&A	8,000 input / 800 output tokens per query, 20,000 queries per month	$15	$3.84
Coding assistant	12,000 input / 2,000 output tokens per request, 10,000 requests per month	$13	$3.20
Batch summarization	4,000 input / 400 output tokens per item, 200,000 items per month	$74	$19

Derived directly from the rates on this page. Excludes prompt caching, batch discounts and free tiers.

How it compares

The alternatives worth benchmarking alongside it, from the same dataset.

Model	Provider	Blended /1M	Quality	Price delta
Ling-3.0-flash	InclusionAI	$0.11	80	—
qwen3.7-flashCheaper option	Alibaba	$0.055	82	-49%
mercury-2.5-previewHigher quality	Inception	$0.068	82	-37%

Best for

ChatbotAffordableFastLong Context

Modalities

Text

Where it fits — and where it doesn't

Good fit

Chat and support: natural multi-turn conversation for user-facing products.
High throughput and real-time UX: 180 tok/s keeps streamed responses feeling instant.
High-volume, cost-sensitive batch work: low rates suit classification, tagging and summarization at scale.

Poor fit

Hard reasoning: a quality score of 80 is on the low side here; pick a stronger model for complex planning or maths.
Image understanding: this model is text-only, so vision tasks need a multimodal alternative.

Frequently asked questions

How much does the Ling-3.0-flash API cost?

Ling-3.0-flash costs $0.07 per million input tokens and $0.22 per million output tokens. On a 3:1 input-to-output mix that blends to about $0.11 per million tokens.

What does Ling-3.0-flash cost per month?

It depends on volume. Using the four worked scenarios on this page: a support chatbot runs about $13/month, RAG document Q&A about $15/month, a coding assistant about $13/month, and batch summarization about $74/month. Plug your own token counts into the cost calculator for a tailored figure.

How large is the Ling-3.0-flash context window?

262K tokens — roughly 349 pages of A4 text at ~750 tokens per page, ranking 51st of the 87 models tracked here.

Ling-3.0-flash or qwen3.7-flash — which is better value?

qwen3.7-flash blends to about $0.055 per million tokens versus $0.11 for Ling-3.0-flash — roughly 49% cheaper — at a quality score of 82 against 80. If that quality gap does not show up on your task, take the cheaper one; if it does, stay with Ling-3.0-flash. Benchmark both on your own data before deciding.

What is Ling-3.0-flash best suited for?

Tagged use cases: chatbot, cheap, fast, long-context. Chat and support: natural multi-turn conversation for user-facing products. Less suitable: Hard reasoning: a quality score of 80 is on the low side here; pick a stronger model for complex planning or maths.

How current is this Ling-3.0-flash pricing?

Pricing here was last verified on 2026-08-16 against official documentation. llmprice.app runs a daily collection job, but providers can change rates between runs — confirm against InclusionAI's official pricing page before you commit.