Llama 3.3 70 B Instruct Pricing & Specs | AI Models

Llama 3.3 70B Instruct is a text model from Nebius with a context window of 128K tokens and max output of 128K tokens. Pricing starts at 0.13 per million input tokens and 0.40 per million output tokens (cheapest at Together AI).

Capabilities

✗ Vision✓ Function Calling✗ Reasoning✗ JSON Schema✗ System Messages✗ Web Search✗ Prompt Caching✗ Audio Input✗ Audio Output

Specifications

Model Key	`nebius/meta-llama/Llama-3.3-70B-Instruct`
Provider	Nebius
Provider ID	nebius
Mode	Text
Canonical Name	llama-3.3-70b
Context Window	128K tokens
Max Output	128K tokens

Pricing

Type	Per 1K Tokens	Per 1M Tokens
Input Tokens	0.000130	0.130
Output Tokens	0.000400	0.400

Benchmarks

Intelligence Index	14.5#136
Coding Index	10.7#130
Math Index	7.7#120
MMLU-Pro	0.7#102
GPQA	0.5#136
HLE	0.0#172
LiveCodeBench	0.3#115
AIME	0.3#48
IFBench	0.5#47
Time to First Token	0.53s#127
SciCode	0.3#128
MATH-500	0.8#74
AIME 2025	0.1#120
LCR	0.1#121
TerminalBench Hard	0.0#121
TAU2	0.3#94

Price Comparison by Provider

Compare prices for Llama 3.3 70B Instruct across different providers. The same model may be available through multiple providers at different price points.

Provider	Model Key	Input Price, $	Output Price, $
IBM watsonx	watsonx/meta-llama/llama-3-3-70b-instruct	0.710	0.710
Weights & Biases	wandb/meta-llama/Llama-3.3-70B-Instruct	0.071	0.071
Vercel AI Gateway	vercel_ai_gateway/meta/llama-3.3-70b	0.720	0.720
AWS Bedrock	us.meta.llama3-3-70b-instruct-v1:0	0.720	0.720
Together AI	together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free	N/A	N/A
Snowflake	snowflake/snowflake-llama-3.3-70b	N/A	N/A
SambaNova	sambanova/Meta-Llama-3.3-70B-Instruct	0.600	1.20
OVHcloud	ovhcloud/Meta-Llama-3_3-70B-Instruct	0.670	0.670
Oracle Cloud (OCI)	oci/meta.llama-3.3-70b-instruct	0.720	0.720
Nscale	nscale/meta-llama/Llama-3.3-70B-Instruct	0.200	0.200
Novita AI	novita/meta-llama/llama-3.3-70b-instruct	0.135	0.400
Nebius	nebius/meta-llama/Llama-3.3-70B-Instruct	0.130	0.400
Meta Llama	meta_llama/Llama-3.3-70B-Instruct	N/A	N/A
Lambda	lambda_ai/llama3.3-70b-instruct-fp8	0.120	0.300
Hyperbolic	hyperbolic/meta-llama/Llama-3.3-70B-Instruct	0.120	0.300
Groq	groq/llama-3.3-70b-versatile	0.590	0.790
Gradient AI	gradient_ai/llama3.3-70b-instruct	0.650	0.650
Fireworks AI	fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct	0.900	0.900
DeepInfra	deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo	0.130	0.390
Databricks	databricks/databricks-meta-llama-3-3-70b-instruct	0.500	1.50
Cerebras	cerebras/llama-3.3-70b	0.850	1.20
Azure AI	azure_ai/Llama-3.3-70B-Instruct	0.710	0.710

All Variants

All available versions, regions, and API endpoints for Llama 3.3 70B Instruct.

Model Key	Provider	Mode	Input Price, $	Output Price, $	Context	Max Output	Vision	Functions
meta.llama3-3-70b-instruct-v1:0	AWS Bedrock	Text	0.720	0.720	128K	4K	no	yes
us.meta.llama3-3-70b-instruct-v1:0	AWS Bedrock	Text	0.720	0.720	128K	4K	no	yes
azure_ai/Llama-3.3-70B-Instruct	Azure AI	Text	0.710	0.710	128K	2K	no	yes
cerebras/llama-3.3-70b	Cerebras	Text	0.850	1.20	128K	128K	no	yes
databricks/databricks-meta-llama-3-3-70b-instruct	Databricks	Text	0.500	1.50	128K	128K	no	no
deepinfra/meta-llama/Llama-3.3-70B-Instruct	DeepInfra	Text	0.230	0.400	131K	131K	no	yes
deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo	DeepInfra	Text	0.130	0.390	131K	131K	no	yes
fireworks_ai/accounts/fireworks/models/llama-v3p3-70b-instruct	Fireworks AI	Text	0.900	0.900	131K	131K	no	no
gradient_ai/llama3.3-70b-instruct	Gradient AI	Text	0.650	0.650	2K	N/A	no	no
groq/llama-3.3-70b-versatile	Groq	Text	0.590	0.790	128K	33K	no	yes
hyperbolic/meta-llama/Llama-3.3-70B-Instruct	Hyperbolic	Text	0.120	0.300	131K	131K	no	yes
watsonx/meta-llama/llama-3-3-70b-instruct	IBM watsonx	Text	0.710	0.710	128K	128K	no	yes
lambda_ai/deepseek-llama3.3-70b	Lambda	Text	0.200	0.600	131K	131K	no	yes
lambda_ai/llama3.3-70b-instruct-fp8	Lambda	Text	0.120	0.300	131K	131K	no	yes
meta_llama/Llama-3.3-70B-Instruct	Meta Llama	Text	N/A	N/A	128K	4K	no	yes
nebius/meta-llama/Llama-3.3-70B-Instruct	Nebius	Text	0.130	0.400	128K	128K	no	yes
novita/meta-llama/llama-3.3-70b-instruct	Novita AI	Text	0.135	0.400	131K	120K	no	yes
nscale/meta-llama/Llama-3.3-70B-Instruct	Nscale	Text	0.200	0.200	N/A	N/A	no	no
oci/meta.llama-3.3-70b-instruct	Oracle Cloud (OCI)	Text	0.720	0.720	128K	4K	no	yes
ovhcloud/Meta-Llama-3_3-70B-Instruct	OVHcloud	Text	0.670	0.670	131K	131K	no	yes
sambanova/Meta-Llama-3.3-70B-Instruct	SambaNova	Text	0.600	1.20	131K	131K	no	yes
snowflake/llama3.3-70b	Snowflake	Text	N/A	N/A	128K	8K	no	no
snowflake/snowflake-llama-3.3-70b	Snowflake	Text	N/A	N/A	8K	8K	no	no
together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo	Together AI	Text	0.880	0.880	N/A	N/A	no	yes
together_ai/meta-llama/Llama-3.3-70B-Instruct-Turbo-Free	Together AI	Text	N/A	N/A	N/A	N/A	no	yes
vercel_ai_gateway/meta/llama-3.3-70b	Vercel AI Gateway	Text	0.720	0.720	128K	8K	no	yes
wandb/meta-llama/Llama-3.3-70B-Instruct	Weights & Biases	Text	0.071	0.071	128K	128K	no	no

← Back to All Models