Metallama familyActive

Llama 3.3 70B Turbo

Compact Llama instruction model for fast chat and local deployment

JSONEmbed chartCompare
Context
131,072
Max output
131,072
Input / 1M
$0.10
Output / 1M
$0.32
Providers
2
01Profile

Profile

Released
2024-12-06
Last updated
2026-07-02
Knowledge cutoff
Weights
Open
02Capabilities

Capabilities

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

Pricing across 2 providers

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

ProviderProvider model idInputOutputCache readContext
deepinframeta-llama/Llama-3.3-70B-Instruct-Turbo$0.10$0.32Not listed131,072
togetheraimeta-llama/Llama-3.3-70B-Instruct-Turbo$1.04$1.04Not listed131,072
04History

Change history

6+ recent events since 2024-12-06

2026-07-02Price uptogetheraiinput / 1M$0.88→ $1.04
2026-07-02Price uptogetheraioutput / 1M$0.88→ $1.04
2026-03-14ContextdeepinfraMax output→ 16,384
2026-03-13Addeddeepinfraoffering→ new
2026-02-10ContexttogetheraiMax output66,536→ 131,072
2025-07-25Addedtogetheraioffering→ new
as of 2026-09-16
About ·Corrections ·Contact ·Privacy ·EN / 中文 / 繁體
HomeModelsLabsProvidersToolsRankingsChangesNews