Metallama familyActive

Llama-3.3-70B-Instruct

Popular open Llama workhorse for multilingual chat, coding, and self-hosting

JSONEmbed chartCompare
Context
128,000
Max output
4,096
Input / 1M
$1.15
Output / 1M
$1.15
Providers
1
01Profile

Profile

Released
2024-12-06
Last updated
2024-12-06
Knowledge cutoff
2023-12
Weights
Open
02Capabilities

Capabilities

Input
text
Output
text
Reasoning
No
Tool calling
Yes
Structured output
No
Attachments
No
Cache read
Cache write
03Pricing

Pricing across 1 providers

Per 1M tokens, USD. Sorted by input price. First-party row highlighted.

ProviderProvider model idInputOutputCache readContext
evrocnvidia/Llama-3.3-70B-Instruct-FP8$1.15$1.15Not listed128,000
04History

Change history

7+ recent events since 2024-12-06

2026-06-27Removedinceptronofferingremoved→ new
2026-06-24Price cutevrocinput / 1M$1.18→ $1.15
2026-06-24Price cutevrocoutput / 1M$1.18→ $1.15
2026-06-24ContextevrocContext window131,072→ new
2026-06-24ContextevrocMax output32,768→ new
2026-05-21Addedinceptronoffering→ new
2026-02-18Addedevrocoffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews