Llama 3.1 8B Instruct

by Meta · meta-llama/llama-3.1-8b-instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

Input / 1M tokens
$0.05
Output / 1M tokens
$0.08
Context
131K

Specs

Input price$0.05 / 1M tokens
Output price$0.08 / 1M tokens
Cached input$0.025 / 1M tokens
Context window131K tokens
Max output118K tokens
Readstext
Writestext
Tool callingYes
ReasoningNo
ListedJul 23, 2024

List prices in USD, updated Oct 30, 2026. Providers may charge differently.

Providers

5 providers serve this model, as of Oct 30, 2026, 18:12 UTC.

Providers serving this model, sorted by price
ProviderQuantizationContextMax outputInput / 1MOutput / 1MCache read / 1MUptime (30 min)Latency (median)Throughput (median)SupportsStatus
DeepInfraCheapestfp8131K16.4K$0.02$0.04—100%501 ms35 tok/sNormal
Novitafp816.4K14.7K$0.02$0.05—100%474 ms96 tok/sCode -2
GroqFastest—131K118K$0.05$0.08$0.025100%65 ms362 tok/sNormal
Cloudflarefp832K28.8K$0.152$0.287—100%420 ms19 tok/sNormal
CoreWeavebf16131K118K$0.22$0.22$0.22100%316 ms132 tok/sNormal

"Cheapest" is the lowest input plus output price; "Fastest" the highest median throughput. Columns empty for every provider are not shown.