Ling 3.0 Flash VL
InclusionAI · Open weights · Released Sep 10, 2026 · inclusionai/ling-3.0-flash-vl
Best $0.06 in / $0.18 out via DeepInfra · fp16
131K contextVisionToolsReasoningStructured outputPrompt cachingOpen weights
Available from 2 providersUSD / MTOK · PRICES 29 MINUTES 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 |
|---|---|---|---|---|---|---|---|---|
 CheaperInferenceDIRECTMARKETPLACE | $0.05 | $0.15 | — | — | — | — | — | — |
 DeepInfra | $0.06 | $0.18 | $0.012 | 131K | fp16 | 0.71s | 60 tok/s | 99.4% |
TTFT/TPS: median (P50) over trailing 504h · chat10k profile (~10K in / 200 out) · measured via OpenRouter routing · ✕ = probed, endpoint returned no measurable stream · methodology v1.1 · measured 15 days ago
SERVE THIS MODEL AND NOT LISTED? LIST YOUR INFERENCE →
Pricing variants · USD / MTok in / out
STANDARD
$0.06 / $0.18
per MTok in / out
CACHE READ $0.012
Recent changesRSS ↗
Oct 23, 2026endpoint added · cheaperinference1 → 2
Oct 14, 2026endpoint removed · novita2 → 1
Oct 14, 2026context changed262144 → 131072
Sep 23, 2026endpoint added · novita1 → 2
Sep 23, 2026context changed131072 → 262144
Sep 12, 2026model added
About
Ling 3.0 Flash VL builds on Ling 3.0 Flash (124B total / 5.5B active MoE from InclusionAI), further strengthening its language capabilities while adding native visual perception and advanced visual...
Specifications
Context window131,072
Max output32,768
Modalities intext, image, video
Modalities outtext
LicenseOpen weights
ReleasedSep 10, 2026
TokenizerOther
WeightsHugging Face ↗
Embed badge
[](https://modelindex.ai/models/inclusionai/ling-3.0-flash-vl)Sources
OpenRouter API29 minutes ago
AGGREGATORHugging Face29 minutes ago
COMMUNITYModelIndex benchmarks20 days ago
MEASUREDVerified 29 minutes ago · list prices, not negotiated rates.