Meta: Llama 3.3 70B Instruct

70B

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

Context
131K
Max output
16K
Input price
$0.1/1M tokens
Output price
$0.32/1M tokens

Capabilities

Reasoning & Interaction
Tool Calling
Output Control
Structured Output
JSON Mode

Details

Model IDmeta-llama/llama-3.3-70b-instruct
Provider OpenRouter
Creator meta-llama
Familyllama-3.3
License—
Status—
Typechat
Input modalitiestext
Output modalitiestext
Open weight—
Parameters70B
Architecture—
Context window131K tokens
Max input—
Max output16K tokens
Reasoning tokens—
Knowledge cutoff—
Release date
Sourceofficial

Tools

Function Callingfunction_calling
Call external functions and APIs

Pricing

Input
$0.1
Output
$0.32
Cache write
—
Cache read
$0.3
Batch in
—
Batch out
—

Family Comparison: llama-3.3

ModelContextMax outPricing
Meta: Llama 3.3 70B Instruct (free)131K——
Meta: Llama 3.3 70B Instruct131K16K$0.1$0.32
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5131K16K$0.4$0.4

API

GET/v1/models/openrouter/meta-llama/llama-3.3-70b-instruct

Meta: Llama 3.3 70B Instruct

meta-llama/llama-3.3-70b-instruct

The Meta Llama 3.3 multilingual large language model (LLM) is a pretrained and instruction tuned generative model in 70B (text in/text out).

Changes · 17 entries
meta-llama/llama-3.3-70b-instructupdateca7a400Nov 2, 2026, 03:02 AM
pricingcached input$0.295
meta-llama/llama-3.3-70b-instructupdate03ad82bOct 17, 2026, 06:33 AM
max_output_tokens32768→16384
pricinginput$0.59→$0.1output$0.79→$0.32
meta-llama/llama-3.3-70b-instructupdate29d19afOct 13, 2026, 06:43 AM
max_output_tokens16384→32768
pricinginput$0.22→$0.59output$0.5→$0.79cached input$0.11→$0.295
meta-llama/llama-3.3-70b-instructupdate70614e7Oct 9, 2026, 06:39 AM
pricinginput$0.1→$0.22output$0.32→$0.5
meta-llama/llama-3.3-70b-instructupdateda0e420Oct 8, 2026, 06:41 AM
pricinginput$0.22→$0.1output$0.5→$0.32
meta-llama/llama-3.3-70b-instructupdate00710a0Oct 6, 2026, 06:38 AM
pricinginput$0.1→$0.22output$0.32→$0.5
meta-llama/llama-3.3-70b-instructupdate632cde3Oct 5, 2026, 06:54 AM
pricinginput$0.22→$0.1output$0.5→$0.32
meta-llama/llama-3.3-70b-instructupdate8c3d4a3Oct 4, 2026, 08:18 AM
pricinginput$0.1→$0.22output$0.32→$0.5cached input$0.71→$0.11
meta-llama/llama-3.3-70b-instructupdated79e481Sep 3, 2026, 06:38 AM
max_output_tokens115200→16384
pricinginput$0.71→$0.1output$0.71→$0.32
meta-llama/llama-3.3-70b-instructupdatee3d7dedAug 31, 2026, 04:13 AM
max_output_tokens16384→115200
pricinginput$0.1→$0.71output$0.32→$0.71cached input$0.71
meta-llama/llama-3.3-70b-instructupdate19c9fe3Aug 5, 2026, 03:04 PM
max_output_tokens128000→16384
pricinginput$0.13→$0.1output$0.4→$0.32
meta-llama/llama-3.3-70b-instructupdate20c73acJul 17, 2026, 02:34 AM
max_output_tokens16384→128000
pricinginput$0.1→$0.13output$0.32→$0.4
meta-llama/llama-3.3-70b-instructupdate80802beApr 22, 2026, 02:56 PM
max_output_tokens131072→16384
pricinginput$0.12→$0.1output$0.38→$0.32
meta-llama/llama-3.3-70b-instructupdate6231fb5Apr 22, 2026, 02:50 AM
max_output_tokens16384→131072
pricinginput$0.1→$0.12output$0.32→$0.38
meta-llama/llama-3.3-70b-instructupdate1cd659eMar 24, 2026, 04:19 AM
capabilitiesjson modeyes
meta-llama/llama-3.3-70b-instructupdate2b100acMar 23, 2026, 05:30 AM
model_typechat
parameters70
release_date2024-12-06
taglineThe Meta Llama 3.3 multilingual large language model (LLM...
tools["function_calling"]
meta-llama/llama-3.3-70b-instructcreate7f5c66fMar 21, 2026, 05:16 AM