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 —
LLMopenrouterRoutes requests to other providers — price may include a margin and terms can differ
Qwen2.5 72B
List price
$0.36 / $0.40 per 1M
✓ Sourced from models.dev — retrieved Aug 2, 2026 — single source.
Same model, other providers
726% price spread across 12 providers — the same model does not cost the same everywhere.
cortecsRuns open models on its own infrastructureview
$0.062/1M in✓ src
hyperbolicRuns open models on its own infrastructureview
$0.12/1M in✓ src
abacusRoutes requests to other providers — price may include a margin and terms can differview
$0.11/1M in✓ src
kiloRoutes requests to other providers — price may include a margin and terms can differview
$0.12/1M in✓ src
deepinfraRuns open models on its own infrastructureview
$0.12/1M in✓ src
nebiusRuns open models on its own infrastructureview
$0.13/1M in✓ src
nano-gptRoutes requests to other providers — price may include a margin and terms can differview
$0.36/1M in✓ src
openrouterRoutes requests to other providers — price may include a margin and terms can differthis page
$0.36/1M in✓ src
novita-aiRuns open models on its own infrastructureview
$0.38/1M in✓ src
novitaRuns open models on its own infrastructureview
$0.38/1M in✓ src
siliconflowRuns open models on its own infrastructureview
$0.59/1M in✓ src
alibaba-cnview
$0.57/1M in✓ src