Skip to content
Model Pareto

Ling-3.0-flash-VL

inclusionAI (Ant Group)Open weightshuggingface.co ↗
Input
$0.075/M tok
Output
$0.22/M tok
Blended
$0.111/M tok · 3:1
Speed
147tok/s
Context
262Ktokens
Cost per task
~$0.09/taskest.

Open weights (MIT); 124B total / 5.5B active vision-language MoE.

Rankings

Self-hostingEstimated

How we estimate →

What it would cost to run these open weights yourself on rented GPUs, compared with the API price above.

Hardware
2× H200 141GB
FP8 weights
Throughput
~9,381 tok/s
many requests batched
Price
$0.083–0.68 /M tok
busy → light use
On your own machine
Mac Studio M5 Max 128GB (int4, ~160 tok/s single-stream)
single consumer GPU or Mac
Assumptions (5)
  • FP8 weights (124B params, 5.5B active per token) + 25% KV-cache headroom ≈ 155 GB
  • 2× H200 141GB at $3.59–$7.91/GPU-hour on-demand (2026-09-24)
  • ~9,381 output tok/s aggregate at batch 337 (bandwidth-bound); MoE compute scales with active params
  • Blended 3:1 input:output; prefill ~170,014 tok/s
  • Low = 75% utilization at the low GPU price; high = 20% at the high price

Benchmark scores

~ italic, dashed = no published score yet, estimated from related benchmarks.

Coding

LiveCodeBenchEstimated
~#15 of 28 (estimated)~66.4%
  1. #1Qwen3.8-Omni-Flash92.6%
  2. #2Qwen3.8 Flash-Next91.9%
  3. #14Maple-Preview75.1%
  4. ~#15Ling-3.0-flash-VLEstimated66.4%
  5. #15Mistral Small 464.0%
No published score — estimated from related benchmarks
~#24 of 26 (estimated)~31.4
  1. #1Claude Opus 5.561.7
  2. #2Claude Opus 559.7
  3. #23Gemini 3.8 Flash33.3
  4. ~#24Ling-3.0-flash-VLEstimated31.4
  5. #24GPT-6 Luna31.1
No published score — estimated from related benchmarks

Vision

Hard reasoning

Agents