Meta Llama 3.1 70 B Instruct Pricing & Specs | AI Models

Meta Llama 3.1 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 Vertex AI (Llama)).

Capabilities

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

Specifications

Model Key	`nebius/meta-llama/Meta-Llama-3.1-70B-Instruct`
Provider	Nebius
Provider ID	nebius
Mode	Text
Canonical Name	llama-3.1-70b
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	12.5#161
Coding Index	10.9#126
Math Index	4.0#131
MMLU-Pro	0.7#126
GPQA	0.4#167
HLE	0.0#126
LiveCodeBench	0.2#140
AIME	0.2#69
IFBench	0.3#114
Time to First Token	0.47s#117
SciCode	0.3#122
MATH-500	0.6#102
AIME 2025	0.0#131
LCR	0.1#140
TerminalBench Hard	0.0#121
TAU2	0.2#135

Price Comparison by Provider

Compare prices for Meta Llama 3.1 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, $
Vertex AI (Llama)	vertex_ai/meta/llama-3.1-70b-instruct-maas	N/A	N/A
Vercel AI Gateway	vercel_ai_gateway/meta/llama-3.1-70b	0.720	0.720
Together AI	together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	0.880	0.880
Snowflake	snowflake/llama3.1-70b	N/A	N/A
Perplexity	perplexity/llama-3.1-70b-instruct	1.00	1.00
OVHcloud	ovhcloud/Meta-Llama-3_1-70B-Instruct	0.670	0.670
Nebius	nebius/meta-llama/Meta-Llama-3.1-70B-Instruct	0.130	0.400
AWS Bedrock	meta.llama3-1-70b-instruct-v1:0	0.990	0.990
Lambda	lambda_ai/llama3.1-70b-instruct-fp8	0.120	0.300
Hyperbolic	hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct	0.120	0.300
FriendliAI	friendliai/meta-llama-3.1-70b-instruct	0.600	0.600
Fireworks AI	fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b	0.100	0.100
DeepInfra	deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	0.100	0.280
Cerebras	cerebras/llama3.1-70b	0.600	0.600
Azure AI	azure_ai/Meta-Llama-3.1-70B-Instruct	2.68	3.54

All Variants

All available versions, regions, and API endpoints for Meta Llama 3.1 70B Instruct.

Model Key	Provider	Mode	Input Price, $	Output Price, $	Context	Max Output	Vision	Functions
meta.llama3-1-70b-instruct-v1:0	AWS Bedrock	Text	0.990	0.990	128K	2K	no	yes
us.meta.llama3-1-70b-instruct-v1:0	AWS Bedrock	Text	0.990	0.990	128K	2K	no	yes
azure_ai/Meta-Llama-3.1-70B-Instruct	Azure AI	Text	2.68	3.54	128K	2K	no	no
cerebras/llama3.1-70b	Cerebras	Text	0.600	0.600	128K	128K	no	yes
deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct	DeepInfra	Text	0.400	0.400	131K	131K	no	yes
deepinfra/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	DeepInfra	Text	0.100	0.280	131K	131K	no	yes
fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct	Fireworks AI	Text	0.900	0.900	131K	131K	no	no
fireworks_ai/accounts/fireworks/models/llama-v3p1-70b-instruct-1b	Fireworks AI	Text	0.100	0.100	4K	4K	no	no
friendliai/meta-llama-3.1-70b-instruct	FriendliAI	Text	0.600	0.600	8K	8K	no	yes
hyperbolic/meta-llama/Meta-Llama-3.1-70B-Instruct	Hyperbolic	Text	0.120	0.300	33K	33K	no	yes
lambda_ai/llama3.1-70b-instruct-fp8	Lambda	Text	0.120	0.300	131K	131K	no	yes
nebius/meta-llama/Meta-Llama-3.1-70B-Instruct	Nebius	Text	0.130	0.400	128K	128K	no	yes
ovhcloud/Meta-Llama-3_1-70B-Instruct	OVHcloud	Text	0.670	0.670	131K	131K	no	no
perplexity/llama-3.1-70b-instruct	Perplexity	Text	1.00	1.00	131K	131K	no	no
snowflake/llama3.1-70b	Snowflake	Text	N/A	N/A	128K	8K	no	no
together_ai/meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo	Together AI	Text	0.880	0.880	N/A	N/A	no	yes
vercel_ai_gateway/meta/llama-3.1-70b	Vercel AI Gateway	Text	0.720	0.720	128K	8K	no	no
vertex_ai/meta/llama-3.1-70b-instruct-maas	Vertex AI (Llama)	Text	N/A	N/A	128K	2K	yes	no

← Back to All Models