Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out). The Llama 3.3 instruction tuned text only model...

Prompt $/1M

$0.130

Completion $/1M

$0.400

Context

131,072 tok

Best provider

83 tok/s · Google

Specs

Model id: meta-llama/llama-3.3-70b-instruct
Display name: Meta: Llama 3.3 70B Instruct
Modality: text->text
Tokenizer: Llama3
Instruct type: llama3
Context length: 131,072
Max completion: 128,000
Prompt $/1M: $0.130
Completion $/1M: $0.400
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
Googlefastest	83	322 ms	414 ms
Artificial Analysis	83	628 ms	—
Friendli	62	182 ms	188 ms
WandB	42	218 ms	244 ms
SambaNova	41	910 ms	1,250 ms
Cloudflare	25	466 ms	744 ms
Parasail	24	701 ms	936 ms
Together	21	701 ms	1,068 ms
Novita	19	848 ms	967 ms
Nebius	17	695 ms	1,021 ms
DeepInfra	13	491 ms	678 ms
AkashML	12	836 ms	1,706 ms
Groq	12	334 ms	385 ms
Inceptron	7	645 ms	857 ms