meta-llama/Llama-3.3-70B-Instruct-Turbo

deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo

textContext 131K

Llama 3.3-70B Turbo is a highly optimized version of the Llama 3.3-70B model, utilizing FP8 quantization to deliver significantly faster inference speeds with a minor trade-off in accuracy. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on various benchmarks, including conversational tasks, language translation, and text generation.

Price

Input$0.1

per 1M tokens

Output$0.32

per 1M tokens

Compare this model

Providers

Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.

Provider	Tag	Quant	Input	Output	Context	Uptime	Status	Source
DeepInfra	—	—	$0.1/1M	$0.32/1M	131K	—	Listed	deepinfra

Monthly bill

Token models use the token counts. Image, video, and audio models use units times the flat rate.

Input tokens Output tokens Units

$0.42 at list price for this workload

Every rate

Unit	Input	Output	Flat	Confidence
token	$0.1/1M	$0.32/1M	Not published—	official

Price history

meta-llama/Llama-3.3-70B-Instruct-Turbo

input or flat output

Daily snapshots

UTC date	Unit	Input	Output	Flat
2026-10-08	token	$0.1	$0.32	Not published—
2026-10-09	token	$0.1	$0.32	Not published—
2026-10-10	token	$0.1	$0.32	Not published—
2026-10-11	token	$0.1	$0.32	Not published—
2026-10-12	token	$0.1	$0.32	Not published—
2026-10-13	token	$0.1	$0.32	Not published—
2026-10-14	token	$0.1	$0.32	Not published—
2026-10-15	token	$0.1	$0.32	Not published—
2026-10-16	token	$0.1	$0.32	Not published—
2026-10-17	token	$0.1	$0.32	Not published—
2026-10-18	token	$0.1	$0.32	Not published—
2026-10-19	token	$0.1	$0.32	Not published—
2026-10-20	token	$0.1	$0.32	Not published—
2026-10-21	token	$0.1	$0.32	Not published—
2026-10-22	token	$0.1	$0.32	Not published—
2026-10-23	token	$0.1	$0.32	Not published—
2026-10-24	token	$0.1	$0.32	Not published—
2026-10-25	token	$0.1	$0.32	Not published—
2026-10-26	token	$0.1	$0.32	Not published—
2026-10-27	token	$0.1	$0.32	Not published—
2026-10-28	token	$0.1	$0.32	Not published—
2026-10-29	token	$0.1	$0.32	Not published—
2026-10-30	token	$0.1	$0.32	Not published—

Alternatives

@cf/cloudflare/clairic$0.1/1M · Compare
@cf/google/gemma-4-26b-a4b-it$0.1/1M · Compare
Amazon: Titan Embeddings G1 - Text$0.1/1M · Compare
Anthropic: Claude Haiku 5.5$0.1/1M · Compare
Anthropic: Claude Haiku Latest$0.1/1M · Compare
Arize AI Qwen 2 1.5B Instruct$0.1/1M · Compare

Parameters (1)

chat

Call this model

OpenRouter id deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo. InferenceList does not send the request.

curl

curl https://openrouter.ai/api/v1/chat/completions \
  -H "Authorization: Bearer $OPENROUTER_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo","messages":[{"role":"user","content":"Hello"}]}'

JavaScript

await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Python

import os, json, urllib.request
req = urllib.request.Request(
    "https://openrouter.ai/api/v1/chat/completions",
    data=json.dumps({"model": "deepinfra/meta-llama/Llama-3.3-70B-Instruct-Turbo", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
    headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())

JSON · History JSON