Skip to content
ModelCap

Llama 3.1 8B Instruct

Current board #89Arena #312Gated access

Meta·meta-llama/llama-3.1-8b-instruct

Llama 3.1 8B Instruct is a language model published by Meta. 5 OpenRouter endpoints are published in the latest snapshot. It accepts text input and returns text. The published context limit is 131K tokens. The catalogue declares support for tool use, structured outputs.

ModelCap Index · Current board
24.5#89
Measured · 85% support · score interval 24.5–30.9
Market Gravity
44.6
Secondary market signal
Input
$0.05
per 1M tokens
Output
$0.08
per 1M tokens
Context
131K
tokens
Providers
5
endpoints
Gateway spend
—
latest · Vercel share

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
DeepInfrafp8Cheapest$0.02$0.04131Kfp8100.0%
Novitafp8$0.02$0.0516Kfp899.74%
Groq$0.05$0.08131K—99.61%
CoreWeavebf16$0.22$0.22128Kbf16100.0%
Cloudflarefp8$0.152$0.28732Kfp8100.0%

Hugging Face Inference Providers

Exact repository identity

Provider economics and telemetry published by the Hugging Face Router. These are operational signals, not benchmark results.

ProviderInputOutputContextTTFTThroughputFeatures
deepinfra
live
$0.02$0.05131K342 ms19.7 tok/stools
novita
live
$0.02$0.0516K567 ms159.9 tok/s—
nscale
live
$0.06$0.06131K553 ms147.4 tok/sstructured

Reported evaluation leads (10)

Excluded from score

Structured rows reported in this exact model repository at the pinned revision below. They are useful research leads, but remain quarantined until dataset revision, harness, configuration and identity pass ModelCap’s independent admission review.

Dataset / taskMetricValueRevisionProvenance
Idavidrein/gpqa
diamond
—30.4
Unpinned
not published
Reported
Quarantined
LEXam-Benchmark/LEXam
open_question
—10
Unpinned
not published
Reported
Quarantined
LEXam-Benchmark/LEXam
mcq_4_choices
—24.04
Unpinned
not published
Reported
Quarantined
openai/gsm8k
gsm8k
—84.5
Unpinned
not published
Reported
Quarantined
thamilvendhan/signalbench
src
—0.6333
Unpinned
not published
Reported
Quarantined
thamilvendhan/signalbench
time
—0.8333
Unpinned
not published
Reported
Quarantined
thamilvendhan/signalbench
access_deny
—0.5
Unpinned
not published
Reported
Quarantined
thamilvendhan/signalbench
memory_label
—0.6667
Unpinned
not published
Reported
Quarantined
thamilvendhan/signalbench
injection
—0.75
Unpinned
not published
Reported
Quarantined
thamilvendhan/signalbench
bot_policy
—0.4167
Unpinned
not published
Reported
Quarantined

ModelCap Index · Current board

Methodology
24.5
Measured · 3 public benchmark observations across 3 boards
Current board
#89
Public rank basis
Measured (measured)
Index support
85.0% · strong
Index interval
24.5–30.9
Rank posterior
Not available
Top 5 / Top 10 probability
Not available / Not available
Posterior as of
Snapshot timestamp unavailable
Identity binding
Exact catalogue product · meta-llama/meta-llama/llama-3.1-8b-instruct · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata meta-llama/Meta-Llama-3.1-8B-Instruct@0e9e39f249a16976918f6564b8830bc894c89659 (not the evaluation revision)
Direct benchmark observations
3
Breadth-adjusted BES point estimate
27.7
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
27.7
Evidence status
confirmed · 94% mass
General preference
27.9
Coding
28.8
Agents & tools
23.1
Reasoning
—
Evidence breadth
97%
Evidence coverage
85%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
24.0
Liquidity (providers × uptime)
94.5
Open reach (HF downloads)
—
Surface (context / tools / modalities)
45.2
Freshness
5.8
  • · OpenRouter popularity #76
  • · 5 live providers
  • · Catalogue: context 131072, tools
  • · First seen 2024-07-23

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

BES evidence selected · measured input only

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Deployment readiness

Metadata index
88.7
strong · 93% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
68.3
Deployability
100.0
Evaluation provenance
75.4

Missing: accessLegalClarity.resolvable-license-terms, evaluationProvenance.evaluation-dataset-revisions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
44.6
OpenRouter weekly popularity
#76 of 298

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

Status
Ranked
Source
Arena
Official rank
#312 of 385
Rating
1211.4
95% confidence interval
1207–1216
Votes
50K
Source snapshot
6 Aug 2026, 13:00 UTC
Category
overall
Identity match confidence
100%

Market Gravity breakdown

Usage55%
24.0

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
94.5

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
50.0

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
5.8

Time since first public availability, on a six-month half-life.

Specification

Context window
131K tokens
Max output
131K tokens
Inputs
Text
Outputs
Text
Tokenizer
Llama3
Cached input tokens
$0.025 / 1M
First seen on OpenRouter
23 Jul 2024
Knowledge cutoff
2023-12-31

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Gated access. The weights are hosted behind an access request or acceptance step. Review the publisher's access requirements and license before use or redistribution.

Access
Gated access
Licence
llama3.1
Pinned revision
0e9e39f249a1
Parameters
8.0B
Architecture
LlamaForCausalLM
Model type
llama
Hugging Face downloads (30d)
7.7M
Downloads (all time)
175.8M
Likes
7K
Repository
meta-llama/Meta-Llama-3.1-8B-Instruct
Repository updated
25 Sept 2024, 17:00 UTC
Base lineage
meta-llama/Llama-3.1-8Bmeta-llama/Meta-Llama-3.1-8B