← Model list

Llama-3.3-70B-Instruct

meta·meta/llama-3.3-70b-instruct·Deprecated·Open weights·llama series

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

At a glance
Official price$0 / $0 per 1M
Cache read · Llama
Lowest paid$0.05 / $0.23
NanoGPT Gateway · 58.4× spread
3 more $0 channels
Context128,000
⚠ Providers report 16,384–131,072; the table below is authoritative
Output limit4,096
Capabilities
ReasoningTool useStructured outputTemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Knowledge cutoff2023-12
Released / updated2024-12-06 / 2024-12-06

Quality & performance

Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.

Available at 36 providers32 with public prices · 3 free

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
NvidiaFirst-partyFree128,0004,096
LlamaOfficialFirst-partyFree128,0004,096
Vercel AI Gateway
meta/llama-3.3-70b
CloudFree128,0004,096
NanoGPTGateway$0.05$0.23$0.025131,07216,384
Meganova
meta-llama/Llama-3.3-70B-Instruct
Gateway$0.10$0.30131,07216,384
OpenRouterGateway$0.10$0.32131,07216,384
Eden AI
deepinfra/meta-llama/Llama-3.3-70B-Instruct
Gateway$0.10$0.32131,0724,096
Kilo GatewayGateway$0.10$0.32131,07216,384
IO.NET
meta-llama/Llama-3.3-70B-Instruct
Cloud$0.13$0.38$0.065$0.26128,0004,096
CortecsGateway$0.129$0.399131,000131,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1NanoGPT$18.50
2Nebius Token Factory$31.96
3Meganova$35.00
4OpenRouter$36.00
5Eden AI$36.00
6Kilo Gateway$36.00

3 more channels offer $0 (Nvidia, Llama, Vercel AI Gateway); free tiers usually have rate limits and no SLA, excluded from ranking.

The cheapest paid channel is the only channel.

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index10.7indexSource ↗
SciCode26percent correctSource ↗
Terminal-Bench Hard3success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.095$02026-08-052026-08-132026-08-05 · Input list $02026-08-06 · Input list $02026-08-07 · Input list $02026-08-08 · Input list $02026-08-09 · Input list $02026-08-10 · Input list $02026-08-11 · Input list $02026-08-12 · Input list $02026-08-13 · Input list $02026-08-05 · Output list $02026-08-06 · Output list $02026-08-07 · Output list $02026-08-08 · Output list $02026-08-09 · Output list $02026-08-10 · Output list $02026-08-11 · Output list $02026-08-12 · Output list $02026-08-13 · Output list $02026-08-05 · Min blended $0.0952026-08-06 · Min blended $0.0952026-08-07 · Min blended $0.0952026-08-08 · Min blended $0.0952026-08-09 · Min blended $0.0952026-08-10 · Min blended $0.0952026-08-11 · Min blended $0.0952026-08-12 · Min blended $0.0952026-08-13 · Min blended $0.095