Skip to content
OSMEXO

Ling 3.0 Flash VL

inclusionai/ling-3.0-flash-vl
  • Inclusionai
  • Family · Ling 3 Flash VL
  • Released 10 Sep 2026
  • Open weights
  • Text · Image · Video → Text
  • Tools · JSON · Vision
Not on OSMEXO yet
Spec & list price
Context128K
Max output32K
Input / 1M$0.06
Output / 1M$0.183× input
Scores · standing
Intelligence24.6#102/490
Coding57.0#50/196
Usage
Tokens / day240.3M▼ 20% 7d
Usage rank#256
Requests / day82.0K
Tool calls / req0.16
Per request · 30 days
Avg input7.8K0.5× median
Avg output4090.6× median
Cache hit71%about median
Reasoning share64%1.1× median
Tool-call failures1.8%about median

Consumption

4.0B8.0B12.0B3 Oct17 Oct1 Nov
Peak 11.8B 6 OctLow 21.3K 26 OctRank today #256

News & trends

News · latest from Inclusionai

Benchmarks

bar = share of the top score · Benchmark data: Artificial Analysis
GPQA Diamond#78 of 445
86.2%
Long-context reasoning#70 of 393
78.3%
Terminal-Bench 2.1#49 of 182
64.4%
Coding index#50 of 196
57.0
τ-Bench Banking#31 of 154
34.4%
SciCode#88 of 160
44.2%
Intelligence index#102 of 490
24.6
Humanity's Last Exam#134 of 465
22.0%
Speed · median across providers, latest day
Output speed#232/33449 tok/s1.3× slower than median
First token#820.6 s1.7× quicker than median

#2 cheapest of 31 with a similar score

Value
Intelligence Index
24252627$0.05$0.1$0.2$0.5Ling 3.0 Flash VL
Blended price per 1M tokens (log)

Technical details

Tokenizer
Other
License
MIT
Parameters
125B
Moderation
none
Downloads · likes
10.6K · 126
Request parameters 17
  • tools
  • tool_choice
  • response_format
  • structured_outputs
  • reasoning
  • include_reasoning
  • temperature
  • top_p
  • top_k
  • min_p
+7 more
  • max_tokens
  • stop
  • seed
  • frequency_penalty
  • logit_bias
  • presence_penalty
  • repetition_penalty

Interesting facts

  1. Less output room than similar models (32.8K against a 131.1K median).
  2. Released 53 days ago.

When to use

Best for

  • Image and video understanding in chat apps
  • Self-hosted multimodal deployments (open weights)
  • Science question answering with visual context
  • Tool calling with structured output

Think twice for

  • Very large outputs (short output cap)
  • Hardest coding agent work
  • Audio input

Alternatives

other vendors · similar capability

Want Ling 3.0 Flash VL on OSMEXO?

Sign in to request it. Requests are reviewed; a request does not guarantee availability.