Meta: Llama 3.1 8B Instruct

meta-llama/llama-3.1-8b-instruct

Llama 3.1 8B Instruct (Meta) is a compact 8B open-weight model priced near the bottom of the board, at $0.05/$0.08 per million input/output tokens, served by 10 independent hosts. For the money it delivers #229 of 235 on the TryAii Score. It's among the fastest models we track, at roughly 20-125 tokens/sec.

Prompt $/1M

$0.050

Completion $/1M

$0.080

Context

131,072 tok

Best provider

304 tok/s · Cerebras

Specs

Model id: meta-llama/llama-3.1-8b-instruct
Display name: Meta: Llama 3.1 8B Instruct
Modality: text->text
Tokenizer: Llama3
Instruct type: llama3
Context length: 131,072
Max completion: 117,964
Prompt $/1M: $0.050
Completion $/1M: $0.080
Free tier: no

Capabilities

Function callingno
JSON modeno
System promptyes
Visionno
Moderatedno

Benchmark scores

Each axis is one benchmark, normalized to the best model in the field.

No benchmark data for this model.

Speed by provider

Provider	tok/s	TTFT	Total latency
Cerebrasfastest	304	146 ms	160 ms
Friendli	171	207 ms	223 ms
Groqfastest	127	190 ms	245 ms
CoreWeave	118	125 ms	147 ms
WandB	107	172 ms	200 ms
Novita	80	478 ms	499 ms
DeepInfra	22	552 ms	636 ms
Nebius	20	399 ms	1,105 ms
Cloudflare	17	662 ms	757 ms
SambaNova	12	1,383 ms	2,098 ms
meta-llamafastest	—	—	—
Artificial Analysis	0	0 ms	—