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 —
LLMnovitaRuns open models on its own infrastructure
Qwen3 Coder 480B A35B
List price
$0.30 / $1.30 per 1M
✓ Sourced from LiteLLM — retrieved Aug 2, 2026 — single source.
Same model, other providers
243% price spread across 12 providers — the same model does not cost the same everywhere.
siliconflowRuns open models on its own infrastructureview
$0.25/1M in✓ src
siliconflow-cnRuns open models on its own infrastructureview
$0.25/1M in✓ src
abacusRoutes requests to other providers — price may include a margin and terms can differview
$0.29/1M in✓ src
jiekouRoutes requests to other providers — price may include a margin and terms can differview
$0.29/1M in✓ src
novitaRuns open models on its own infrastructurethis page
$0.30/1M in✓ src
llmgatewayRoutes requests to other providers — price may include a margin and terms can differview
$0.30/1M in✓ src
merge-gatewayRoutes requests to other providers — price may include a margin and terms can differview
$0.22/1M in✓ src
novita-aiRuns open models on its own infrastructureview
$0.38/1M in✓ src
deepinfraRuns open models on its own infrastructureview
$0.40/1M in✓ src
fireworks-aiRuns open models on its own infrastructureview
$0.45/1M in✓ src
cortecsRuns open models on its own infrastructureview
$0.44/1M in✓ src
302aiRoutes requests to other providers — price may include a margin and terms can differview
$0.86/1M in✓ src