Llama 3.1 Tulu3 405B

Free

Llama 3.1 Tulu3 405B is a text-based AI model by Allen Institute for AI. It features 0 tok/s output speed, free pricing. It scores 14.1 on the intelligence index.

Strengths

+Completely free to use

Weaknesses

-Slower than average output (0 tok/s)

Benchmarks

Intelligence14.1CodingN/AMathN/A

MMLU-Pro

0.7

GPQA

0.5

LiveCodeBench

0.3

Intelligence

14.1

Output Speed

0 tok/s

Latency (TTFT)

0.00s

Blended Price

$0.00/M

Pricing per 1M Tokens

Input (Prompt)	Free
Output (Completion)	Free
Cache Read	Free
Cache Write	Free

Specifications

Context Length	N/A
Max Output Tokens	N/A
Input Modalities	Text
Output Modalities	Text
Tokenizer	N/A

Compare Llama 3.1 Tulu3 405B with:

vs Gemini 3.1 Pro Preview vs GPT-5.4 (xhigh)vs GPT-5.3 Codex (xhigh)

Alternatives to Llama 3.1 Tulu3 405B

Gemini 3.1 Pro Preview57.2

Google$2.00

GPT-5.4 (xhigh)57.2

OpenAI$2.50

GPT-5.3 Codex (xhigh)54.0

OpenAI$1.75

Claude Opus 4.6 (Adaptive Reasoning, Max Effort)53.0

Anthropic$5.00

Claude Sonnet 4.6 (Adaptive Reasoning, Max Effort)

More from Allen Institute for AI

Frequently Asked Questions

How much does Llama 3.1 Tulu3 405B cost?

Llama 3.1 Tulu3 405B is completely free to use.

How fast is Llama 3.1 Tulu3 405B?

Llama 3.1 Tulu3 405B generates output at 0 tok/s. Time to first token is 0.00s.

Is there a free version of Llama 3.1 Tulu3 405B?

Yes, Llama 3.1 Tulu3 405B is available for free.

What are alternatives to Llama 3.1 Tulu3 405B?

See the alternatives section above for models with similar capabilities. You can also compare Llama 3.1 Tulu3 405B head-to-head with any model on our comparison page.

Last updated: March 26, 2026