Skip to content
AI Atlas
ModelActiveRestricted weights

Llama 3.1 70B Instruct

Meta AIfamily · Llama 3.1huggingface.co/meta-llama/Llama-3.1-70B-Instruct

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong...

Open in Graph
data quality50

Updated 6 h ago · first seen 11 Sept 2026

model_01M294WWPBTMRSH3C54C1WQF2T

Overview

Identity

Canonical model
Yesidentity confidence: highOne row per real model release. Artifacts (checkpoints, quantisations, conversions) and folded evaluation variants point here.
Official checkpoints
official_checkpoints = hf_repo identifiers carried by the model itself; artifacts are separate entities pointing here through canonical_id.
Artifacts
None recordedSeparate entities (checkpoint · quantization · conversion · packaging) pointing to this model through canonical_id.
Provider deployments
1
API aliases
meta-llama/llama-3.1-70b-instructIdentifiers under which providers and evaluators refer to this model.
Folded evaluation variants
1Effort / thinking variants (…-high, …-non-reasoning) are result configurations of this model, not separate models. Their old URLs redirect here.

Openness

Restricted weights— weights downloadable under Llama-3.1-Community; commercial use allowed; redistribution allowed; derivatives allowed; 4 dimensions unknown.

Weights downloadable, but the licence restricts commercial use, hosting, derivatives or field of use (community, research and RAIL licences).

  • Weights

    Yes

  • Inference code

    —

  • Training code

    —

  • Training data

    —

  • Dataset

    —

  • Commercial use

    Yes

  • Redistribution

    Yes

  • Derivatives

    Yes

Licence: Llama 3.1 Community License (community · stated as “llama3.1”)

dimensions marked null are unknown, not false

Key facts

Release date

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Openrouter id

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Architecture

Architecture

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Model type

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Parameters

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Weights dtype

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

File size

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Library name

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Pipeline tag

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 16 h agomedium

Hugging Face repo

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Capabilities

Modalities

Modalities
text
Input
text
Output
text

Capabilities

  • Tool calling

    Yes

    OpenRouter public model & pricing listing · T2

  • Structured output

    Yes

    OpenRouter public model & pricing listing · T2

  • Reasoning

    Unavailable

  • Vision

    Unavailable

  • Audio

    Unavailable

  • Fine-tuning available

    Unavailable

Context window

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Max output

Source:OpenRouter public model & pricing listingT2observed 12 h agomedium

Knowledge cutoff

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Languages

Source:Hugging Face Hub (public pages, model cards, papers)T2observed 15 h agomedium

Tokenizer

Source:OpenRouter public model & pricing listingT2observed 16 h agomedium

Providers & Pricing1

All offers in the price terminal →
Provider deployments, cheapest output first
ProviderContextInput / 1MOutput / 1MStatusObservedSource
OpenRoutercheapest outputmeta-llama/llama-3.1-70b-instruct131.1Kout 8.19Kactive7 h agosince 12 Sept 2026openrouter.aiT2

USD per 1M tokens as published by each provider; native units (per-request fees, flex/priority tiers) are kept verbatim. Rows are append-only — every price change is kept in the history below. Cost of a workload →

Price history

Step lines per provider; amber markers are recorded changes. Click a marker or a row for the evidence behind that price.

Output price · USD / 1M tokens 1 provider

Output price history of Llama 3.1 70B Instruct$0$0.20$0.40$0.60$0.80$1Sept 26Sept 26Sept 26OpenRouter: first observed → $0.40 · 11 Sept 2026OpenRouter: $0.40 → $0.72 · 12 Sept 2026
  • OpenRouter
  • OpenRouter$0.40 → $0.7212 Sept 2026
  • OpenRouterfirst observed $0.4011 Sept 2026

Input price · USD / 1M tokens 1 provider

Input price history of Llama 3.1 70B Instruct$0$0.20$0.40$0.60$0.80$1Sept 26Sept 26Sept 26OpenRouter: first observed → $0.40 · 11 Sept 2026OpenRouter: $0.40 → $0.72 · 12 Sept 2026
  • OpenRouter
  • OpenRouter$0.40 → $0.7212 Sept 2026
  • OpenRouterfirst observed $0.4011 Sept 2026

Hardware fit37

Estimated

23 of 37 device × quantization combinations fit.

Run locally: your machine →
Estimated hardware fit
HardwareQuantizationDevice memoryEst. memoryFits
Apple M3 Ultra4bit—41.1 GB est.Yes
Mac Studio (Apple M5 Ultra)4bit—41.1 GB est.Yes
Apple M2 Ultra4bit—41.1 GB est.Yes
Apple M1 Ultra4bit—41.1 GB est.Yes
Apple M3 Max4bit—41.1 GB est.Yes
Apple M4 Max4bit—41.1 GB est.Yes
Mac Studio (Apple M5 Max)4bit—41.1 GB est.Yes
MacBook Pro (Apple M5 Max)4bit—41.1 GB est.Yes
Apple M2 Max4bit—41.1 GB est.Yes
Apple M1 Max4bit—41.1 GB est.Yes
Apple M4 Pro4bit—41.1 GB est.Yes
Mac mini (Apple M5 Pro)4bit—41.1 GB est.Yes
MacBook Pro (Apple M5 Pro)4bit—41.1 GB est.Yes
NVIDIA A100 80GB4bit80 GB41.1 GB est.Yes
NVIDIA H100 SXM4bit80 GB41.1 GB est.Yes
NVIDIA H100 NVL4bit94 GB41.1 GB est.Yes
NVIDIA DGX Spark4bit128 GB41.1 GB est.Yes
NVIDIA H2004bit141 GB41.1 GB est.Yes
NVIDIA H200 NVL4bit141 GB41.1 GB est.Yes
NVIDIA B2004bit180 GB41.1 GB est.Yes
AMD Instinct MI300X4bit192 GB41.1 GB est.Yes
AMD Instinct MI325X4bit256 GB41.1 GB est.Yes
NVIDIA DGX B2004bit1,440 GB41.1 GB est.Yes
Apple M3 Pro4bit—41.1 GB est.No
Apple M1 Pro4bit—41.1 GB est.No
Apple M2 Pro4bit—41.1 GB est.No
Apple M44bit—41.1 GB est.No
iMac (Apple M4)4bit—41.1 GB est.No
Mac mini (Apple M6)4bit—41.1 GB est.No
MacBook Air (Apple M5)4bit—41.1 GB est.No
MacBook Pro (Apple M5)4bit—41.1 GB est.No
Apple M24bit—41.1 GB est.No
Apple M34bit—41.1 GB est.No
Apple M14bit—41.1 GB est.No
NVIDIA GeForce RTX 30904bit24 GB41.1 GB est.No
NVIDIA GeForce RTX 40904bit24 GB41.1 GB est.No
NVIDIA GeForce RTX 50904bit32 GB41.1 GB est.No
Assumptions (7)
  • Estimated, not measured: weights = parameters × bytes/param × 1.15 runtime overhead (or the observed artifact file size when one is recorded).
  • bytes/param: 4bit = 0.5, 8bit = 1.0, fp16 = 2.0 (uniform quantization, no per-layer exceptions).
  • KV cache: 2 × layers × kv_heads × head_dim × 2 bytes × context × batch when the architecture is known; otherwise 0.5 GB per 8 192 tokens (× batch), independent of architecture (GQA/MLA models need less).
  • A model 'fits' when the estimate is at most the device memory minus 2 GB reserved for the OS and framework.
  • Mixture-of-experts models are estimated on total parameters (all experts must be resident); active parameters are ignored.
  • Device memory uses the largest configuration when several are listed (e.g. Apple silicon tiers).
  • Multi-GPU: device memories are summed; interconnect bandwidth, tensor-parallel replication and pipeline bubbles are not modelled.

Lineage

Open in Graph →
Explicit derived_from / fine_tuned_from / distilled_from relations stated by sources; artifacts collapsed by kind.
ANCESTORS 2Llama-3.1-70BMeta AILlama-3.1-70B — Meta AIMeta-Llama-3.1-70BMeta AIMeta-Llama-3.1-70B — Meta AILlama 3.1 70B Instruct70.5B params · this modelLlama 3.1 70B Instruct — 70.5B params · this model

Versions & Artifacts0

Version history

Max output1 change

11 Sept 2026→12 Sept 2026current

Context windowfirst observation only

11 Sept 2026current

Knowledge cutofffirst observation only

11 Sept 2026current

Licensefirst observation only

11 Sept 2026current

Opennessfirst observation only

11 Sept 2026current

Parametersfirst observation only

11 Sept 2026current

Each hop is a claim: click a value for its source, tier and observation time. Nothing is overwritten — a new observation closes the previous claim.

Artifacts 0

No artifact (checkpoint, quantisation, conversion or packaging) points to this model yet.

Papers1

Timeline2

Full timeline →
  • Price changedModelLlama 3.1 70B InstructMeta AI

    OpenRouter changed pricing for Llama 3.1 70B Instruct: $0.4 in / $0.4 out per 1M tokens → $0.72 in / $0.72 out per 1M tokens

    $0.40 in / $0.40 out→$0.72 in / $0.72 outopenrouter
    openrouter.ai
  • Max output changedModelLlama 3.1 70B InstructMeta AI

    Llama 3.1 70B Instruct: max output tokens changed from 16384 to 8192

    Max output16.4K tokens→8.19K tokensopenrouter
    openrouter.ai

Change history16

Temporal, append-only claims: a new observation closes the previous claim instead of overwriting it. Rewind the record with the as-of picker.

Viewing AI Atlas as of 1 Jan 2025 — attributes exactly as the atlas knew them on that day; later corrections are not shown.

Back to today →

Llama 3.1 70B Instruct was not yet in AI Atlas on 1 Jan 2025

First seen 11 Sept 2026. Nothing is inferred backwards: no attribute is shown for dates before the first observation.
16 claims · 15 properties

Release daterelease_date1

Claim history for Release date
ValueValid from → toStatusSourceConfidenceExtractor
23 Jul 2024 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Context windowcontext_length1

Claim history for Context window
ValueValid from → toStatusSourceConfidenceExtractor
131.1K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Max outputmax_output_tokens2

Claim history for Max output
ValueValid from → toStatusSourceConfidenceExtractor
8.19K tokens → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic
16.4K tokens → supersededOpenRouter public model & pricing listingT2mediumdeterministic

Knowledge cutoffknowledge_cutoff1

Claim history for Knowledge cutoff
ValueValid from → toStatusSourceConfidenceExtractor
Dec 2023 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Modalitiesmodalities1

Claim history for Modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Input modalitiesmodalities_input1

Claim history for Input modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Output modalitiesmodalities_output1

Claim history for Output modalities
ValueValid from → toStatusSourceConfidenceExtractor
text → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tokenizertokenizer1

Claim history for Tokenizer
ValueValid from → toStatusSourceConfidenceExtractor
Llama3 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Hugging Face repohf_repo1

Claim history for Hugging Face repo
ValueValid from → toStatusSourceConfidenceExtractor
meta-llama/Meta-Llama-3.1-70B-Instruct → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Descriptiondescription1

Claim history for Description
ValueValid from → toStatusSourceConfidenceExtractor
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases. It has demonstrated strong... → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Instruct typeinstruct_type1

Claim history for Instruct type
ValueValid from → toStatusSourceConfidenceExtractor
llama3 → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Openrouter idopenrouter_id1

Claim history for Openrouter id
ValueValid from → toStatusSourceConfidenceExtractor
meta-llama/llama-3.1-70b-instruct → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Structured outputstructured_output1

Claim history for Structured output
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Supported parameterssupported_parameters1

Claim history for Supported parameters
ValueValid from → toStatusSourceConfidenceExtractor
frequency_penalty, logit_bias, max_tokens, min_p, presence_penalty, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Tool callingtool_calling1

Claim history for Tool calling
ValueValid from → toStatusSourceConfidenceExtractor
Yes → currentcurrentOpenRouter public model & pricing listingT2mediumdeterministic

Claims are temporal and append-only: a new observation closes the previous claim (valid_to) instead of overwriting it. Conflicting claims from different sources are kept side by side and flagged — never averaged. Methodology →

Provenance

Attributed facts

41

Source tiers

T241

Freshest observation

6 h ago

Conflicts

None

Source documents 3

Source documents
SourceDocumentTypeTierLast observedSnapshots
OpenRouter public model & pricing listingopenrouter.ai/api/v1/models catalogueT2· Quality secondary7 h ago7
Hugging Face Hub (public pages, model cards, papers)huggingface.co/meta-llama/Llama-3.1-70B-Instruct model_pageT2· Quality secondary10 h ago4
Hugging Face Hub (public pages, model cards, papers)huggingface.co/models?author=meta-llama&p=0&sort=downloads listingT2· Quality secondary10 h ago6

Tier 1 = official/primary, 2 = quality secondary, 3 = community, 4 = unverified. Every snapshot is archived; see all sources and the methodology.

Data quality (50/100) measures how well AI Atlas knows this entity — completeness, primary-source ratio, freshness, conflicts — never how good the model is. Methodology →