Ling 3.1 Flash
InclusionAI · Open weights · Released Oct 2, 2026 · inclusionai/ling-3.1-flash
Best $0.045 in / $0.135 out via Novita
1M contextToolsReasoningPrompt cachingOpen weights
Available from 1 providerUSD / MTOK · PRICES 11 HOURS AGO · SPEED 15 DAYS AGO
EST. MONTHLY COSTclick a row for detail · click headers to sort
| PROVIDER | INPUT | OUTPUT | CACHE | CONTEXT | QUANT | TTFT | TPS | UPTIME |
|---|---|---|---|---|---|---|---|---|
| $0.045 | $0.135 | $0.009 | 1M | — | 2.5s | 117 tok/s | 100.0% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · methodology v1.1 · measured 15 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Input price history · best listed price, observed
↓ 40% SINCE NOV 7, 2026
$0.075 · NOV 7, 2026$0.045 · TODAY
Pricing variants · USD / MTok in / out
STANDARD
$0.045 / $0.135
per MTok in / out
CACHE READ $0.009
Recent changesRSS ↗
Nov 12, 2026endpoint removed · deepinfra2 → 1
Nov 7, 2026price decreased · input0.075 → 0.045
Nov 7, 2026price decreased · output0.225 → 0.135
Nov 5, 2026endpoint removed · cheaperinference3 → 2
Oct 28, 2026context changed262144 → 1000000
Oct 23, 2026endpoint added · cheaperinference2 → 3
Oct 15, 2026endpoint added · deepinfra1 → 2
Oct 3, 2026model added
About
Ling 3.1 Flash is a hybrid reasoning mixture-of-experts model from inclusionAI, with 25B active parameters out of 560B total.
Specifications
Context window1,000,000
Max output262,144
Modalities intext
Modalities outtext
LicenseOpen weights
ReleasedOct 2, 2026
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/inclusionai/ling-3.1-flash)Sources
OpenRouter API11 hours ago
AGGREGATORHugging Face11 hours ago
COMMUNITYModelIndex benchmarks16 days ago
MEASUREDVerified 11 hours ago · list prices, not negotiated rates.