// AI Platform Drift

Llama 3.3 70B Instruct pricing increased 120% prompt, 56% completion

OpenRouter model catalogue · published 2026-10-04 05:56 UTC
ACTION NEEDED BUDGET PRICINGMODEL
WHAT CHANGEDOpenRouter raised pricing for meta-llama/llama-3.3-70b-instruct effective now: prompt tokens from $0.10/M to $0.22/M (+120%), completion tokens from $0.32/M to $0.50/M (+56.3%). Total cost per request increases 58-71% depending on prompt-to-completion ratio.
WHY IT MATTERSIf you are calling this model in production, your inference costs just increased by more than half. A workload generating ten completion tokens per prompt token now costs 58% more per request; shorter completions see steeper increases.
WHAT TO DOPull last 30 days of usage for meta-llama/llama-3.3-70b-instruct from your logs, calculate new monthly cost at the updated rates, and update your budget forecast. If the increase is material, evaluate whether to switch models or negotiate volume pricing with OpenRouter.
Model-reported confidence 95% (not measured accuracy) Primary source ↗ written by anthropic/claude-sonnet-4.5
Show the reasoning — raw diff, triage verdict, confidence
RAW DIFF
 id: meta-llama/llama-3.3-70b-instruct
 name: Meta: Llama 3.3 70B Instruct
-pricing.prompt: 0.0000001
-pricing.completion: 0.00000032
+pricing.prompt: 0.00000022
+pricing.completion: 0.0000005
 context_length: 131072
 top_provider.max_completion_tokens: 16384
HOW IT WAS JUDGED
Triage signals below are model-reported assertions, preserved verbatim; they are not independent arithmetic verification.
triage verdictMATERIAL at 0.95, needed 0.5
triage reasoningPricing for an active model increased significantly on both prompt and completion tokens.
signalspricing.prompt increased 2.2x · pricing.completion increased 1.56x · both price changes on active model
suppression—
triage modelanthropic/claude-haiku-4.5 ($0.00000)
writer modelanthropic/claude-sonnet-4.5 ($0.00000)