Skip to main content
Morse logo

Llama 3.3 70B API pricing on Morse

Every Morse Llama 3.3 70B rate we track, compared against 14 providers serving the same model.

Input from /1M
$0.125
Output /1M
$0.400
Input price rank
#3 of 14
Last updated
November 21, 2026

The cheapest Llama 3.3 70B input price we currently track is $0.100/1M on Deep Infra.

The cheapest Llama 3.3 70B output price is $0.320/1M on Deep Infra.

Morse Llama 3.3 70B rates

Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.

Morse Llama 3.3 70B pricing by mode
ModeInputOutput
Standard$0.125/1M$0.400/1M

About Llama 3.3 70B

Creator
Meta
Context
128K
Modalities
text
Knowledge cutoff
Mar 2024
Tool calling
Yes
Open weights
Yes
Full Llama 3.3 70B details and every provider →Compare API pricing for every Llama model →

Llama 3.3 70B on other providers

About Morse

Morse is a privacy-focused inference gateway that serves open-weight chat models through one OpenAI-compatible API. Each request or API key sets a privacy tier (Private, TEE or E2EE), and Morse routes only to upstream providers that meet it, refusing a request it cannot serve at that tier rather than sending it lower. The same gateway runs the Morse chat app.

Frequently Asked Questions

How much does Llama 3.3 70B cost on Morse?

Morse serves Llama 3.3 70B from $0.125 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.

Is Morse the cheapest way to run Llama 3.3 70B?

Morse ranks #3 of 14 providers we track serving Llama 3.3 70B on input price. The cheapest input price right now is on Deep Infra. The lowest output price is $0.320/1M on Deep Infra. Rates change often, and throughput, latency and context limits differ between providers — check the comparison above before committing.

Does Morse offer batch or cached pricing for Llama 3.3 70B?

We track 1 Llama 3.3 70B offering from Morse. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.