How accurate is Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct answered 34 of 80 questions correctly (42.5%) in our 2026-10-27 run, ranking #52 of 78 models.

How fast is Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct generated a median of 42 output tokens per second in our 2026-10-27 run, ranking #63 of 78. Median time to first token was 0.7 s.

What is the latency of Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct had a median time to first token of 0.7 s in our 2026-10-27 run, ranking #33 of 78 models.

How much does Llama 3.3 70B Instruct cost?

Llama 3.3 70B Instruct cost $0.00053 per question on average as billed in our 2026-10-27 run, reasoning tokens included.

What is Llama 3.3 70B Instruct API pricing?

Llama 3.3 70B Instruct is listed at $0.1 per million input tokens and $0.32 per million output tokens on OpenRouter.

What is the context window of Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct accepts up to 131,072 tokens of context, according to OpenRouter's model catalogue.

Is Llama 3.3 70B Instruct open source?

Yes. Llama 3.3 70B Instruct is an open-weights model: Meta publishes the weights, so you can run it yourself as well as through an API.

Who makes Llama 3.3 70B Instruct?

Llama 3.3 70B Instruct is made by Meta. We tested it through OpenRouter using the model ID meta-llama/llama-3.3-70b-instruct.

Where can I use Llama 3.3 70B Instruct via API?

Through OpenRouter, Llama 3.3 70B Instruct is served by 6 hosts: AkashML, Cloudflare, DeepInfra, Groq, Novita, Parasail.

MetaOpen weightsReleased 6 Dec 2024

Llama 3.3 70B Instruct benchmarks, speed and API pricing

Reviewed by LLM Verifications team · Tested 26 Oct 2026

Compare

Available through OpenRouter on

DeepInfra$0.1 in · $0.32 out
Novita$0.135 in · $0.4 out
Parasail$0.22 in · $0.5 out
AkashML$0.2 in · $0.52 out
CoreWeave$0.71 in · $0.71 out
Google$0.72 in · $0.72 out
Groq$0.59 in · $0.79 out
SambaNova$0.45 in · $0.9 out
Cloudflare$0.293 in · $2.253 out

Intelligence42.5% correct#52 of 72

Speed42tok/s#63 of 72

Cost$0.00053per question#18 of 72List $0.1 in · $0.32 out per 1M

Verbosity855tokens per question#28 of 72

Summary

Answers 34 of 80 verification questions correctly (42.5%), placing #52 of 72 models tested on the current suite.
Generates 42 output tokens per second, faster than 13% of the models we measure.
Starts responding after 0.7 s (median time to first token).
Costs $0.00053 per question as billed, #9 cheapest of 29 models priced $0.15 to $1 per 1M tokens.

Specifications

Reasoning: No
Input: text
Output: text
Context window: 131k tokens
Weights: Open weights
Knowledge cutoff: 31 Dec 2023
OpenRouter ID: meta-llama/llama-3.3-70b-instruct
Last tested: 26 Oct 2026

Peer group: 31 models with a blended list price $0.15 to $1 per 1M tokens (3 input : 1 output). Charts below compare Llama 3.3 70B Instruct with all models; cost and speed charts focus on this peer group.

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

Llama 3.3 70B Instruct circled; dashed line joins models no cheaper model beats

Score vs. end-to-end response time

Llama 3.3 70B Instruct circled · accurate and quick sits top left

Score vs. tokens per question

Llama 3.3 70B Instruct circled · output tokens, reasoning included

Verification score

All models tested on the current suite

61 more models · see the full leaderboard

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, by token type

Peer group: blended price $0.15 to $1

1Llama 4 Scout$0.00025
2GPT-6 Luna$0.00025
3Ministral 3 8B 2512$0.00027
4Llama 3.3 70B Instruct$0.00031
5Ministral 3 14B 2512$0.00031
6GLM 5.3 Flash$0.00033
7gpt-oss-120b$0.00038
8Inkling Small$0.00047
9Claude Haiku 5.5$0.00048
10MiMo-V2.6-Flash$0.00056
11Llama 4 Maverick$0.00057
12GLM 5.3$0.00076
13DeepSeek V4.1 Flash 1017$0.00084
14MiniMax M3.1 Flash$0.0009
15DeepSeek V4 Flash Vision Exp$0.00092
16Hy3$0.0013
17Gemma 4 31B$0.0014
18Nemotron 3.5 Super VL$0.0014
19Qwen3 Coder Next$0.0017
20Solar Pro 4$0.0018
21Mistral Small 4$0.0019
22MiMo-V2.6-Pro$0.002
23Trinity Large Thinking$0.0025
24MiniMax M3$0.0027
25LongCat 2.0$0.0032
26Qwen3.7 Plus$0.0033
27Gemini 3.5 Flash Lite$0.0034
28Qwen3.6 35B A3B$0.0034
29Qwen3.8 27B$0.0049

Input Reasoning Answer

Cost per question, as billed

All models · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
18Llama 3.3 70B Instruct$0.00053

61 more models · see the full leaderboard

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Output speed

Peer group ($0.15 to $1) · higher is better

16 more models · see the full leaderboard

Time to first token

Peer group ($0.15 to $1) · lower is better

16 more models · see the full leaderboard

End-to-end response time

Peer group ($0.15 to $1) · lower is better

16 more models · see the full leaderboard

Latency vs. output speed

Llama 3.3 70B Instruct circled · quick to start and fast sits top left

Results by category

Questions answered correctly in each category

Science11/30

Engineering2/15

Medicine6/11

Economics5/9

Law1/6

Humanities & social science9/9

More from Meta

Meta#7Muse Wonder78.8% verification score175 tok/s16.1 s first token$0.021 / question

Meta#9Muse Spark Open77.5% verification score220 tok/s0.5 s first token$0.0045 / question

Meta#40Llama 4 Maverick59.0% verification score13 tok/s0.7 s first token$0.00059 / question

All Meta models →

Compare Llama 3.3 70B Instruct

Head to head with its closest rivals, other Meta models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

Host	Input / 1M	Output / 1M	Context	Max output	Quantization
DeepInfra	$0.1	$0.32	131k	16k	fp8
Novita	$0.135	$0.4	12k	11k	bf16
Parasail	$0.22	$0.5	131k	16k	fp8
AkashML	$0.2	$0.52	131k	128k	fp8
CoreWeave	$0.71	$0.71	128k	115k	fp16
Google	$0.72	$0.72	128k	8k	—
Groq	$0.59	$0.79	131k	33k	—
SambaNova	$0.45	$0.9	131k	3k	—
Cloudflare	$0.293	$2.253	24k	22k	fp8

Sources

Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.

Llama 3.3 70B Instruct on OpenRouter: list prices and hosts
Model card on Hugging Face: weights and licence
SuperGPQA (paper): 50 of the questions, ODC-BY 1.0
MMLU-Pro (paper): 30 of the questions, MIT
OpenRouter generation records: where billed cost and native token counts come from
Our methodology and editorial standards

Llama 3.3 70B Instruct: frequently asked questions

How accurate is Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct answered 34 of 80 questions correctly (42.5%) in our 2026-10-27 run, ranking #52 of 78 models.
How fast is Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct generated a median of 42 output tokens per second in our 2026-10-27 run, ranking #63 of 78. Median time to first token was 0.7 s.
What is the latency of Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct had a median time to first token of 0.7 s in our 2026-10-27 run, ranking #33 of 78 models.
How much does Llama 3.3 70B Instruct cost?: Llama 3.3 70B Instruct cost $0.00053 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
What is Llama 3.3 70B Instruct API pricing?: Llama 3.3 70B Instruct is listed at $0.1 per million input tokens and $0.32 per million output tokens on OpenRouter.
What is the context window of Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct accepts up to 131,072 tokens of context, according to OpenRouter's model catalogue.
Is Llama 3.3 70B Instruct open source?: Yes. Llama 3.3 70B Instruct is an open-weights model: Meta publishes the weights, so you can run it yourself as well as through an API.
Who makes Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct is made by Meta. We tested it through OpenRouter using the model ID meta-llama/llama-3.3-70b-instruct.
Where can I use Llama 3.3 70B Instruct via API?: Through OpenRouter, Llama 3.3 70B Instruct is served by 6 hosts: AkashML, Cloudflare, DeepInfra, Groq, Novita, Parasail.

MetaOpen weightsReleased 6 Dec 2024

Llama 3.3 70B Instruct benchmarks, speed and API pricing

Reviewed by LLM Verifications team · Tested 26 Oct 2026

Compare

Available through OpenRouter on

DeepInfra$0.1 in · $0.32 out
Novita$0.135 in · $0.4 out
Parasail$0.22 in · $0.5 out
AkashML$0.2 in · $0.52 out
CoreWeave$0.71 in · $0.71 out
Google$0.72 in · $0.72 out
Groq$0.59 in · $0.79 out
SambaNova$0.45 in · $0.9 out
Cloudflare$0.293 in · $2.253 out

Intelligence42.5% correct#52 of 72

Speed42tok/s#63 of 72

Cost$0.00053per question#18 of 72List $0.1 in · $0.32 out per 1M

Verbosity855tokens per question#28 of 72

Summary

Answers 34 of 80 verification questions correctly (42.5%), placing #52 of 72 models tested on the current suite.
Generates 42 output tokens per second, faster than 13% of the models we measure.
Starts responding after 0.7 s (median time to first token).
Costs $0.00053 per question as billed, #9 cheapest of 29 models priced $0.15 to $1 per 1M tokens.

Specifications

Reasoning: No
Input: text
Output: text
Context window: 131k tokens
Weights: Open weights
Knowledge cutoff: 31 Dec 2023
OpenRouter ID: meta-llama/llama-3.3-70b-instruct
Last tested: 26 Oct 2026

Intelligence

Verification score: the share of 80 questions from open datasets answered correctly. See the benchmark datasets.

Score vs. cost per question

Llama 3.3 70B Instruct circled; dashed line joins models no cheaper model beats

Score vs. end-to-end response time

Llama 3.3 70B Instruct circled · accurate and quick sits top left

Score vs. tokens per question

Llama 3.3 70B Instruct circled · output tokens, reasoning included

Verification score

All models tested on the current suite

61 more models · see the full leaderboard

Cost

Average cost of one question, split into input, reasoning and answer tokens at each model's list price. Reasoning tokens are billed as output.

Cost per question, by token type

Peer group: blended price $0.15 to $1

1Llama 4 Scout$0.00025
2GPT-6 Luna$0.00025
3Ministral 3 8B 2512$0.00027
4Llama 3.3 70B Instruct$0.00031
5Ministral 3 14B 2512$0.00031
6GLM 5.3 Flash$0.00033
7gpt-oss-120b$0.00038
8Inkling Small$0.00047
9Claude Haiku 5.5$0.00048
10MiMo-V2.6-Flash$0.00056
11Llama 4 Maverick$0.00057
12GLM 5.3$0.00076
13DeepSeek V4.1 Flash 1017$0.00084
14MiniMax M3.1 Flash$0.0009
15DeepSeek V4 Flash Vision Exp$0.00092
16Hy3$0.0013
17Gemma 4 31B$0.0014
18Nemotron 3.5 Super VL$0.0014
19Qwen3 Coder Next$0.0017
20Solar Pro 4$0.0018
21Mistral Small 4$0.0019
22MiMo-V2.6-Pro$0.002
23Trinity Large Thinking$0.0025
24MiniMax M3$0.0027
25LongCat 2.0$0.0032
26Qwen3.7 Plus$0.0033
27Gemini 3.5 Flash Lite$0.0034
28Qwen3.6 35B A3B$0.0034
29Qwen3.8 27B$0.0049

Input Reasoning Answer

Cost per question, as billed

All models · lower is better

1Granite 4.0 Micro$0.000051
2gpt-oss-20b$0.000066
3Granite 4.2 8B$0.000077
4Nova Micro 1.0$0.000087
5Mercury 2.5$0.00011
6Phi 4$0.00012
7gpt-oss-120b$0.00013
8GLM 5.3 Flash$0.00015
9Ministral 3 3B 2512$0.00019
10GPT-6 Luna$0.00025
18Llama 3.3 70B Instruct$0.00053

61 more models · see the full leaderboard

Speed and latency

Median of 3 streamed runs of the same prompt, measured 25 Oct 2026.

Output speed

Peer group ($0.15 to $1) · higher is better

16 more models · see the full leaderboard

Time to first token

Peer group ($0.15 to $1) · lower is better

16 more models · see the full leaderboard

End-to-end response time

Peer group ($0.15 to $1) · lower is better

16 more models · see the full leaderboard

Latency vs. output speed

Llama 3.3 70B Instruct circled · quick to start and fast sits top left

Results by category

Questions answered correctly in each category

Science11/30

Engineering2/15

Medicine6/11

Economics5/9

Law1/6

Humanities & social science9/9

More from Meta

Meta#7Muse Wonder78.8% verification score175 tok/s16.1 s first token$0.021 / question

Meta#9Muse Spark Open77.5% verification score220 tok/s0.5 s first token$0.0045 / question

Meta#40Llama 4 Maverick59.0% verification score13 tok/s0.7 s first token$0.00059 / question

All Meta models →

Compare Llama 3.3 70B Instruct

Head to head with its closest rivals, other Meta models and the top models overall.

Hosts and prices

Every host serving this model through OpenRouter, from OpenRouter's catalogue

Host	Input / 1M	Output / 1M	Context	Max output	Quantization
DeepInfra	$0.1	$0.32	131k	16k	fp8
Novita	$0.135	$0.4	12k	11k	bf16
Parasail	$0.22	$0.5	131k	16k	fp8
AkashML	$0.2	$0.52	131k	128k	fp8
CoreWeave	$0.71	$0.71	128k	115k	fp16
Google	$0.72	$0.72	128k	8k	—
Groq	$0.59	$0.79	131k	33k	—
SambaNova	$0.45	$0.9	131k	3k	—
Cloudflare	$0.293	$2.253	24k	22k	fp8

Sources

Scores, speed and billed cost are our own measurements. Prices, context window and hosts come from OpenRouter's catalogue on the test date.

Llama 3.3 70B Instruct on OpenRouter: list prices and hosts
Model card on Hugging Face: weights and licence
SuperGPQA (paper): 50 of the questions, ODC-BY 1.0
MMLU-Pro (paper): 30 of the questions, MIT
OpenRouter generation records: where billed cost and native token counts come from
Our methodology and editorial standards

Llama 3.3 70B Instruct: frequently asked questions

How accurate is Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct answered 34 of 80 questions correctly (42.5%) in our 2026-10-27 run, ranking #52 of 78 models.
How fast is Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct generated a median of 42 output tokens per second in our 2026-10-27 run, ranking #63 of 78. Median time to first token was 0.7 s.
What is the latency of Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct had a median time to first token of 0.7 s in our 2026-10-27 run, ranking #33 of 78 models.
How much does Llama 3.3 70B Instruct cost?: Llama 3.3 70B Instruct cost $0.00053 per question on average as billed in our 2026-10-27 run, reasoning tokens included.
What is Llama 3.3 70B Instruct API pricing?: Llama 3.3 70B Instruct is listed at $0.1 per million input tokens and $0.32 per million output tokens on OpenRouter.
What is the context window of Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct accepts up to 131,072 tokens of context, according to OpenRouter's model catalogue.
Is Llama 3.3 70B Instruct open source?: Yes. Llama 3.3 70B Instruct is an open-weights model: Meta publishes the weights, so you can run it yourself as well as through an API.
Who makes Llama 3.3 70B Instruct?: Llama 3.3 70B Instruct is made by Meta. We tested it through OpenRouter using the model ID meta-llama/llama-3.3-70b-instruct.
Where can I use Llama 3.3 70B Instruct via API?: Through OpenRouter, Llama 3.3 70B Instruct is served by 6 hosts: AkashML, Cloudflare, DeepInfra, Groq, Novita, Parasail.