How much does Llama 3.3 70B cost?

Llama 3.3 70B costs $0.68 per million input tokens and $0.68 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about $0.10 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.

What is the context window of Llama 3.3 70B?

Llama 3.3 70B has a context window of 128K tokens, roughly 96,000 words of text read at once. A single answer can be up to 131K tokens long.

Is Llama 3.3 70B open source?

Llama 3.3 70B has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.

How good is Llama 3.3 70B compared with other AI models?

On the Epoch Capabilities Index, Llama 3.3 70B scores 127.3 (likely range 122.5 to 129.4), which ranks 172 of 270 models we track. On Arena's human-vote text board it is ranked 137 of 166. Scores close together are a tie in practice.

How does Llama 3.3 70B compare with GPT-4 Turbo (Apr 2024)?

GPT-4 Turbo (Apr 2024) scores higher on 1 of 6 shared quality measures, Llama 3.3 70B on 0. 5 measures are too close to call. Llama 3.3 70B costs about 95% less than GPT-4 Turbo (Apr 2024) on a blended price of $0.68 against $15.00 per million tokens. See the full comparison for every measure.

How current are these numbers for Llama 3.3 70B?

The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.

AI Rankings

Llama 3.3 70B: Score, Price and Context Window

Where Llama 3.3 70B from Meta ranks, what it costs and how much text it can read, in plain numbers with the sources.

Data updated 26 Oct 2026

Meta
Open weights
Released Dec 2024

Its score range overlaps with Mistral Small 3.1, the model just above it, so a small gap in rank is not a meaningful difference.

Best for

Running it yourself: its weights can be downloaded (read the licence terms first).

Skip if

Cutting-edge tasks: its overall Epoch score is in the lower part of the models we track.

These lines are worked out from the numbers on this page, not from hands-on testing.

Key facts

Overall score: 127.3; Rank 172 of 270. Likely range 122.5 to 129.4.
Human preference: chat: 1318; Rank 137 of 166. 54,493 votes.
Human preference: coding: 1346; Rank 140 of 166. 8,735 votes.
Price per million tokens: $0.68 in / $0.68 out; Blended $0.68. Median across hosting providers, checked 26 Oct 2026.
Context window: 128K tokens; About 96,000 words at once. One answer up to 131K tokens.
Weights: Open; The weights can be downloaded. Check the licence before commercial use.

Features listed by the price list: Tool use.

Try itMeta AI in our AI tools directoryMeta's AI assistant for everyday questions, conversation, writing, and image-based creativity in supported apps.

How Llama 3.3 70B stacks up

Each strip shows every model we track as faint bars. The dot is this model. Better is always to the right, even for price.

Llama 3.3 70B compared with all models we trackOverall capability: 127.3. Better than 36% of the other 269 models. Human preference: chat: 1318. Better than 17% of the other 165 models. Human preference: coding: 1346. Better than 15% of the other 165 models. Price: $0.68 per 1M. Cheaper than 63% of the other 200 priced models. Context window: 128K tokens. Larger context window than 19% of the other 198 models.

Overall capability127.3
Better than 36% of the other 269 models
Epoch Capabilities Index: one score that combines many tests.
Human preference: chat1318
Better than 17% of the other 165 models
How often people pick its answers over another model's on Arena.
Human preference: coding1346
Better than 15% of the other 165 models
How often people pick its answers to coding questions on Arena.
Price$0.68 per 1M
Cheaper than 63% of the other 200 priced modelsUpper half
Blended price per million tokens. Lower is better, so the cheapest models sit on the right.
Context window128K tokens
Larger context window than 19% of the other 198 models
How much text it can read at once. Bigger suits long documents.

Compared with the other published models that have each measure. Data updated 26 Oct 2026.

Where Llama 3.3 70B ranks

Leaderboards it appears on, best placing first.

See all leaderboards

Test results

Each test checks one kind of skill. Place shows where it stands among the models that took that test.

GPQA Diamond
Very hard multiple-choice science questions in biology, physics and chemistry, written by experts and designed so a quick web search does not give the answer.
47.4%
Place 146 of 183
OTIS Mock AIME
Maths competition problems in the style of the US AIME exam, from the 2024 and 2025 sets. Every answer is a whole number.
5.1%
Place 152 of 174
SimpleBench
Everyday common-sense and trick questions that most people answer correctly but AI models often get wrong.
19.9%
Place 75 of 80

What it costs in everyday terms

List prices turned into amounts you can picture. Real bills depend on how you use it.

100 chats: $0.10; Cost of 100 chats assumes each chat sends 1,000 tokens (about 750 words) and gets 500 tokens (about 375 words) back.
A 300-page book: $0.07; Cost to read a 300-page book assumes about 100,000 input tokens and no reply. A real book varies with page size and language.
Blended price: $0.68 per 1M; Three parts input to one part output. Our own calculation for comparing models.

Similar models

Models from other makers with a similar overall score.

Learn more

Questions about Llama 3.3 70B

How much does Llama 3.3 70B cost?: Llama 3.3 70B costs $0.68 per million input tokens and $0.68 per million output tokens, using the median price across hosting providers as of 26 Oct 2026. That is about $0.10 for 100 chats of about 1,000 tokens in and 500 tokens back. Confirm on the maker's site before you buy, because prices change.
What is the context window of Llama 3.3 70B?: Llama 3.3 70B has a context window of 128K tokens, roughly 96,000 words of text read at once. A single answer can be up to 131K tokens long.
Is Llama 3.3 70B open source?: Llama 3.3 70B has open weights: its trained parameters can be downloaded. That is not always the same as open source, because licence terms differ, so read the licence before you use it commercially.
How good is Llama 3.3 70B compared with other AI models?: On the Epoch Capabilities Index, Llama 3.3 70B scores 127.3 (likely range 122.5 to 129.4), which ranks 172 of 270 models we track. On Arena's human-vote text board it is ranked 137 of 166. Scores close together are a tie in practice.
How does Llama 3.3 70B compare with GPT-4 Turbo (Apr 2024)?: GPT-4 Turbo (Apr 2024) scores higher on 1 of 6 shared quality measures, Llama 3.3 70B on 0. 5 measures are too close to call. Llama 3.3 70B costs about 95% less than GPT-4 Turbo (Apr 2024) on a blended price of $0.68 against $15.00 per million tokens. See the full comparison for every measure.
How current are these numbers for Llama 3.3 70B?: The newest data on this page is dated 26 Oct 2026. Scores come from Epoch AI and Arena, prices from the open LiteLLM price list.

Where this data comes from

Epoch AI: Benchmark data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0). We match models across sources, rank them and show them in charts. Scores are not changed. Epoch AI does not endorse this site.
Arena (formerly LMArena): Human-preference ratings: Arena (arena.ai) leaderboard dataset, CC BY 4.0. We keep the latest published ratings, match them to models from other sources and rank them. Ratings are not changed. Arena does not endorse this site.
LiteLLM model price list: Prices and context windows: LiteLLM model price list (github.com/BerriAI/litellm, MIT licence). We use the model maker's own price entry when there is one. Prices change often, so always confirm on the maker's site before you buy.

Newest data on this page: 26 Oct 2026. Prices are list prices and change often, so confirm on the maker's site before you buy. Sponsors never change a score or an order. How we calculate this · Report a mistake