Llama 3.3 70B Instruct vs Llama 3.1 8B Instruct

One line per model: the best value available from any of its providers at each point, which is what a caller routing to the healthy endpoint would see.

CompareLlama 3.3 70B InstructLlama 3.1 8B Instruct


Llama 3.3 70B Instruct	6/14	100% AkashML	99.80% Groq	99.84% CoreWeave	364ms Groq	1.08s Groq	232 tps Groq	131K	$0.100 / $0.320 DeepInfra
Llama 3.1 8B Instruct	5/5	100% Cloudflare	100% CoreWeave	99.96% CoreWeave	128ms Groq	1.05s Groq	368 tps Groq	131K	$0.020 / $0.040 DeepInfra

Measured 2m ago. Each figure is the best available across that model's providers.

History

Availability

Best uptime available from any provider. Axis starts at 90%; it expands to 0 when a model falls below.

Time to first token

Fastest P50 available from any provider. Logarithmic axis.

Throughput

Best median tokens per second available.