AI Tools Hub
AI Models/Models/Llama 3.3 70B Instruct
Back to model explorerlanguage model

Llama 3.3 70B Instruct

meta/llama-3.3-70b

Model overview, pricing signals, context window, capabilities, and latest tracked AI Gateway endpoint data.

Provider

meta

Context window

128K

Max output

8.2K

Input price

$0.72 / 1M

Model overview
AI Gateway model metadata from the latest Supabase snapshot.

Creator

meta

Provider

meta

Type

language

Output price

$0.72 / 1M

Tags and capabilities
Used for filtering and future route selection logic.
tool-usetool use

Latest route highlights

Best routes in the latest Supabase AI Gateway snapshot. Recommendations are scoped to tracked endpoints only.

Fastest route

101ms

groq | meta/llama-3.3-70b

Lowest p50 latency in the latest AI Gateway snapshot.

Most reliable

100%

bedrock | meta/llama-3.3-70b

Highest recent uptime in the latest AI Gateway snapshot.

Cheapest route

$1.38 / 1M

groq | meta/llama-3.3-70b

Lowest combined input plus output price in the latest AI Gateway snapshot.

Balanced route

groq

groq | meta/llama-3.3-70b

Best weighted score in the latest AI Gateway snapshot.

Score 100/100. Score = 45% latency rank + 35% uptime rank + 20% price rank across tracked endpoints.

Endpoint comparison
Latest Supabase endpoint snapshot from 5/17/2026, 7:37:40 AM.
Provider routes

2

Latency p50 range

101ms - 157ms

Best uptime

100%

Snapshot

May 17, 7:37 AM

ProviderStatusLatency p50Latency p95UptimeThroughputInput / 1MOutput / 1MContextMax outputSupported parameters
groqgroq | meta/llama-3.3-70b
0101ms194ms100%—$0.59 / 1M$0.79 / 1M128K32.8K
max_tokenstemperaturestoptoolstool_choice
bedrockbedrock | meta/llama-3.3-70b
0157ms551ms100%189 tok/s$0.72 / 1M$0.72 / 1M128K8.2K
max_tokenstemperaturestoptoolstool_choice

Historical trends

Compact trend data generated from Supabase AI Gateway endpoint snapshots. Trends become meaningful after multiple snapshot runs.

Latency p50
Lower is better.
bedrock: 160ms at May 16, 9:58 AMbedrock: 157ms at May 17, 7:24 AMbedrock: 157ms at May 17, 7:37 AMgroq: 120ms at May 16, 9:58 AMgroq: 101ms at May 17, 7:24 AMgroq: 101ms at May 17, 7:37 AM
May 16, 9:58 AMMay 17, 7:37 AM
bedrock
157ms
groq
101ms

Updated May 17, 7:37 AM

Uptime
Latest availability samples.
bedrock: 100% at May 16, 9:58 AMbedrock: 100% at May 17, 7:24 AMbedrock: 100% at May 17, 7:37 AMgroq: 100% at May 16, 9:58 AMgroq: 100% at May 17, 7:24 AMgroq: 100% at May 17, 7:37 AM
May 16, 9:58 AMMay 17, 7:37 AM
bedrock
100%
groq
100%

Updated May 17, 7:37 AM

Throughput p50
Output token speed by provider route.
bedrock: 186 tok/s at May 16, 9:58 AMbedrock: 189 tok/s at May 17, 7:24 AMbedrock: 189 tok/s at May 17, 7:37 AM
May 16, 9:58 AMMay 17, 7:37 AM
bedrock
189 tok/s

Updated May 17, 7:37 AM

Price history
Input plus output price per 1M tokens.
bedrock: $1.44 at May 16, 9:58 AMbedrock: $1.44 at May 17, 7:24 AMbedrock: $1.44 at May 17, 7:37 AMgroq: $1.38 at May 16, 9:58 AMgroq: $1.38 at May 17, 7:24 AMgroq: $1.38 at May 17, 7:37 AM
May 16, 9:58 AMMay 17, 7:37 AM
bedrock
$1.44
groq
$1.38

Updated May 17, 7:37 AM

AI Gateway data status
Supabase snapshots ready

Tracked models

10

23 endpoint rows

Chart models

10

3 snapshot hours

Models updated

May 17, 7:37 AM

Fresh Supabase snapshot

Endpoint updated

May 17, 7:37 AM

Newest snapshot May 17, 7:37 AM

Data note

Model and endpoint data are read from Supabase AI Gateway snapshots generated by the ingestion pipeline. Pricing, routing, and availability may change, so verify with official providers before production use.