Ling 3.1 Flash
by Inclusionai · inclusionai/ling-3.1-flash · #30 cheapest of 457 paid models
Prices updated Nov 18, 2026, 7:43 AM UTC · refreshed nightly
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.045
per 1M tokens
Output
$0.135
per 1M tokens
Blended (3:1)
$0.068
3 input : 1 output
Cache read
$0.0090
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Ling 3.1 Flash with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.068 | $0.004725 | — |
| 50% | $0.054 | $0.002925 | −38% |
| 90% | $0.043 | $0.001485 | −69% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $6.30e-5 | $0.063 |
| Document summary | 8,000 | 1,000 | $0.000495 | $0.495 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.00162 | $1.62 |
| Long-context analysis | 150,000 | 5,000 | $0.007425 | $7.42 |
Performance
Intelligence Index
29.6
AA composite quality
Coding Index
—
Math Index
—
Agentic Index
—
Output speed
—
median
Time to first token
—
median
Time to first answer
—
after reasoning tokens
Specs
Context window
1M
tokens
Max output
262K
tokens
Input modalities
text
Tokenizer
Other