50 models7 providersprices scraped nightly — no estimates
meta · llama familyVerified May 18, 2026

Llama 3.1 405B Instruct

405B params · 131K context · llama-3 · released 2024-07 · 5 providers

Meta's Llama 3.1 405B Instruct was the largest open-weights model ever released at launch (July 2024) and remains the benchmark for "what's possible with open weights." At 405 billion dense parameters and a 131K context window, it competes with frontier closed models on most evaluations — but at 5-10x the per-token cost of a 70B model on most providers. Realistic hosted pricing in 2026 ranges from $2.70/$2.70 per 1M tokens on the cheapest providers up to $3.50/$3.50 on Together. Worth running for high-stakes tasks where output quality justifies the price gap: complex agents, long-context analysis, or critical content generation. For most chat and RAG workloads, Llama 3.3 70B delivers 90% of the quality at 10% of the cost.

Cheapest right now
DeepInfra$8.00/1M out
sticky while scrolling · verified May 18, 2026
Cheapest now
$8.00
DeepInfra · fp8 · $/1M out
90-day price Δ
cheapest-host trend
Fastest TTFT
600 ms
Fireworks AI · 80 tok/s
Providers
5
indexed providers
✓ verified May 18, 2026
#Provider$/1M in$/1M outTTFT p50tok/sQuant
1DeepInfraCHEAPEST$2.70$8.00700 ms65fp8go ↗
2Together AI$3.50$3.50fp8go ↗
3Fireworks AIFASTEST$3.00$9.00600 ms80fp8go ↗
4Hyperbolic$4.00$4.001100 ms35fp8go ↗
5OpenRouter$3.50$10.50unknowngo ↗

Prices verified May 18, 2026 by scraping 5 providers. Methodology · Raw data