Preview build — figures marked “✓” or in green are sourced (benchmarks by Artificial Analysis); treat everything else (value scores, “Est.” figures, unmarked prices and changes) as illustrative. Methodology
← All LLM modelsEst. score — Est. value — Context — Released —
LLMsiliconflow-cnRuns open models on its own infrastructure
Qwen/Qwen3-VL-30B-A3B-Thinking
List price
$0.29 / $1.00 per 1M
✓ Sourced from models.dev — retrieved Aug 2, 2026 — single source.
Same model, other providers
186% price spread across 7 providers — the same model does not cost the same everywhere.
fireworks-aiRuns open models on its own infrastructureview
$0.15/1M in✓ src
novita-aiRuns open models on its own infrastructureview
$0.20/1M in✓ src
novitaRuns open models on its own infrastructureview
$0.20/1M in✓ src
siliconflow-cnRuns open models on its own infrastructurethis page
$0.29/1M in✓ src
siliconflowRuns open models on its own infrastructureview
$0.29/1M in✓ src
kiloRoutes requests to other providers — price may include a margin and terms can differview
$0.13/1M in✓ src
openrouterRoutes requests to other providers — price may include a margin and terms can differview
$0.20/1M in✓ src