Models / Meta

Llama 3.3 70B Instruct API pricing

$0.40 in, $1.28 out per million tokens.

llama-3.3-70b-instructmanaged routeOpenAI SDK

Price · per million tokens, USD

Get a key
TokensMeta list priceUplinkSwitchSaving
Input—$0.40—
Cached input—$0.20—
Output—$1.28—
No list price on record. Prices read from the live catalog on 2026-11-16; the page follows the catalog.
Real-model check: Steady since Oct 29

Llama 3.3 70B Instruct specs

Context window
131,072 tokens
Input
text
Released
December 6, 2024

Llama 3.3 70B Instruct: what it is · from Meta’s own model page, read 2026-10-29

Meta’s 70B Llama 3.3 Instruct, a multilingual text model released on December 6, 2024. Meta’s card lists eight supported languages (English, German, French, Italian, Portuguese, Hindi, Spanish and Thai), pretraining on more than 15T tokens of public data with a December 2023 cutoff, and tuning with supervised fine-tuning and RLHF. It is served as llama-3.3-70b-instruct at $0.40 input and $1.28 output per million tokens, on the same key as every other model in the catalog.

Llama 3.3 70B Instruct
DeveloperMeta
Parameters70B, dense
Context128k tokens on Meta’s card; served with a 131,072-token window
Licensethe Llama 3.3 Community License
Published2024-12-06
SourceMeta’s Llama 3.3 model card

From Meta’s Llama 3.3 model card, read 2026-10-29.

curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"llama-3.3-70b-instruct","max_tokens":1024,"messages":[{"role":"user","content":"Hello"}]}'

Llama 3.3 70B Instruct next to Meta’s other models · per million tokens, live

ModelHere, in / out1,000 chat turns
Llama 3.2 3B Instruct$0.08 / $0.20$0.26
Muse Spark 1.3 Contributor$0.15 / $0.30$0.45
Llama 3.3 70B Instruct$0.40 / $1.28$1.44
Muse Glimmer 30B$1.50 / $1.50$3.75
Muse Spark Open$4.375 / $14.875$16.19

A chat turn is 2,000 input and 500 output tokens. Live from the catalog, ordered by the cost of 1,000 turns.

Worked for Llama 3.3 70B Instruct: 1,000 turns are 2,000,000 input tokens and 500,000 output tokens. At $0.40 input and $1.28 output per million tokens, that is $0.80 + $0.64 = $1.44, paid from prepaid credit with no subscription.

Llama 3.3 70B Instruct API key · base URL and setup

  1. Create a key in the console at uplinkswitch.ai/console. Credit is prepaid from $10 with no subscription, and the key works at once.
  2. Point your SDK or tool at https://api.uplinkswitch.com/v1, for example with OPENAI_BASE_URL, and send the key as the bearer token.
  3. Send llama-3.3-70b-instruct as the model. The same key calls every other model in the catalog.
Python · OpenAI SDK
from openai import OpenAI

client = OpenAI(
    base_url="https://api.uplinkswitch.com/v1",
    api_key="sk-uplink-live-...",
)

completion = client.chat.completions.create(
    model="llama-3.3-70b-instruct",
    messages=[{"role": "user", "content": "Summarize this in one line."}],
)
print(completion.choices[0].message.content)
TypeScript · OpenAI SDK
import OpenAI from 'openai';

const client = new OpenAI({
  baseURL: 'https://api.uplinkswitch.com/v1',
  apiKey: 'sk-uplink-live-...',
});

const completion = await client.chat.completions.create({
  model: 'llama-3.3-70b-instruct',
  messages: [{ role: 'user', content: 'Summarize this in one line.' }],
});
console.log(completion.choices[0].message.content);
curl
curl https://api.uplinkswitch.com/v1/chat/completions \
  -H "authorization: Bearer sk-uplink-live-..." \
  -H "content-type: application/json" \
  -d '{"model":"llama-3.3-70b-instruct","messages":[{"role":"user","content":"Hello"}]}'

What would it cost? · paste a prompt, priced before you send it

Input is counted at about 4 characters per token.

Cheapest first. A real request is billed on the provider's own token count. Same estimate as JSON: POST https://api.uplinkswitch.com/v1/estimate, no key needed.

Llama 3.3 70B Instruct questions

Llama 3.3 70B Instruct is a model from Meta, released December 6, 2024, with a 131,072-token context window, taking text input. Through UplinkSwitch it answers the OpenAI SDK on one key as llama-3.3-70b-instruct.

$0.40 per million input tokens and $1.28 per million output tokens, with cached input at $0.20.

It is pay as you go: prepaid credit from $10, with no subscription or monthly fee, billed per token. A 1,000-token prompt with a 500-token reply costs about $0.001.

Llama 3.3 70B Instruct has a 131,072-token context window. It takes text input.

llama-3.3-70b-instruct. Send it as the model through the OpenAI SDK with base URL https://api.uplinkswitch.com/v1.

Create one in the console at uplinkswitch.ai/console: prepaid credit from $10, no subscription, and the key is live at once. The same key calls Llama 3.3 70B Instruct and every other model in the catalog; send it as the bearer token with base URL https://api.uplinkswitch.com/v1.

Every day each model gets the same test prompt, and the results are public on /proof. Llama 3.3 70B Instruct's latest result: Steady since Oct 29.

Yes: llama-3.3-70b-instruct on the OpenAI format at https://api.uplinkswitch.com/v1, $0.40 input and $1.28 output per million tokens. No weights to download and no GPU of your own; the key also runs every other model in the catalog.

70B, dense, per Meta’s Llama 3.3 model card.

128k tokens on Meta’s card; served with a 131,072-token window, per Meta’s Llama 3.3 model card.

Its weights are open on Hugging Face (meta-llama/Llama-3.3-70B-Instruct); the license is the Llama 3.3 Community License.

$0.144 for 100 chat turns of 2,000 input and 500 output tokens each, at $0.40 input and $1.28 output per million tokens, from prepaid credit with no subscription.

Llama 3.3 70B Instruct is Meta’s model as released; the abliterated build has its refusals removed at the weight level. Llama 3.3 70B Instruct is $0.40 / $1.28 per million tokens in / out, $1.44 for 1,000 chat turns; Llama 3.3 70B Abliterated is $2.80 / $2.80 per million tokens in / out, $7.00 for 1,000 chat turns. Both run on the same key, so send the same prompt to each.
Join on Telegram