THE MODEL, IN DETAIL / meta-llama

Llama-3.1-8B-Instruct

meta-llama/llama-3.1-8b-instructOpen weights

Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 8B instruct-tuned version is fast and efficient. It has demonstrated strong performance compared to...

OpenRouter

Source-linked model intelligenceCatalog added 23 Jul 2024Specifications observed 17 Oct 2026

GPQA Diamond

30.4%

Source-reported

Context window

131.1K

118K max output tokens

Input price

$0.05

USD / million input tokens

Output price

$0.08

USD / million output tokens

Inference providers

5 provider routes observed

Measured output speed

—

No model-level measurement

01 / PERFORMANCE

A clearer view of capability.

Read the score, understand the context, and explore where this model sits among its peers.

Performance fingerprint

Individual published accuracy scores · not a composite index

Performance meets price

GPQA Diamond · same published source and version

Qwenmoonshotaideepseek-aiopenaimeta-llama

In good company

GPQA Diamond · OpenEvals / Hugging Face

88.4

Qwen

87.6

moonshotai

86.6

Qwen

71.5

deepseek-ai

67.1

openai

65.8

Qwen

56.8

openai

38.9

LiquidAI

30.4

This model

Rank #26 in this published cohort. 27 models in the source cohort. Showing selected nearby models. Evaluation settings can differ.

Evidence, by task.

Coverage is not a capability score.

3published results
1 evaluation source

Reasoning2 evaluations

CodingAwaiting evidence

Mathematics1 evaluation

VisionAwaiting evidence

AgenticAwaiting evidence

Long contextAwaiting evidence

Documented features, task evaluations, and preference rankings describe different things. Missing coverage does not imply a model cannot perform a task.

Explore our methodology

02 / BENCHMARK EXPLORER

The numbers behind the model.

Original results, exact versions, and a direct path to the evidence behind every score.

3 published results

3 percentage-based evaluations. Each benchmark measures a different task; compare results within the same evaluation and protocol.

Published benchmark results for Llama-3.1-8B-Instruct
Version & metric	Source	Published
Published snapshot 2026-03-16Accuracy · Higher is better	OpenEvals / Hugging FaceSource-reported	15 Mar 2026
Published snapshot 2026-03-16Accuracy · Higher is better	OpenEvals / Hugging FaceSource-reported	15 Mar 2026
Published snapshot 2026-03-16Accuracy · Higher is better	OpenEvals / Hugging FaceSource-reported	15 Mar 2026

Artificial Analysis indices

Published in the OpenRouter catalog · source-defined index values

Coding Index5.4

Intelligence Index6.9

Catalog observation: 17 Oct 2026. Index versions and evaluation settings are not supplied in this feed. These are not Singularity composite scores.

Artificial Analysis

03 / COST & VALUE

Know what your workload costs.

Explore token prices, see where the spend goes, and model a workload of your own.

Input$0.05per million tokens

Output$0.08per million tokens

Cache read$0.025per million tokens

Cache write—per million tokens

Workload cost calculator

Change the numbers. See the trade-offs.

Pricing source

Input tokens / requestOutput tokens / requestRequests

Cached share of input0%

Token estimate only. Excludes cache writes, tools, and other provider fees. Actual token usage and provider limits vary.

Your estimated spend

1,000 requests · 11M tokens

Uncached input$0.5

Cached input$0

Output$0.08

Per request$0.0006

Without cache discount$0.58

Estimated cache savings$0

04 / INFERENCE NETWORK

One model. Different ways to run it.

Compare inference routes by price, context, quantization, and reported availability.

5 providers · 5 routes

Standard service tier only

Provider routes for Llama-3.1-8B-Instruct, observed 17 Oct 2026
Provider / route	Input / M	Output / M	Cache / M	Context	Output limit	Speed	Latency	Availability · 1d
DDeepInfraFP8	$0.02	$0.04	—	131.1K	16.4K	—	—	99.93%
NNovitaFP8	$0.02	$0.05	—	16.4K	14.7K	—	—	98.82%
GGroqQuantization not disclosed	$0.05	$0.08	$0.025	131.1K	118K	—	—	100%
CCloudflareFP8	$0.152	$0.287	—	32K	28.8K	—	—	98.92%
CCoreWeaveBF16	$0.22	$0.22	$0.22	131.1K	118K	—	—	100%

Snapshot observed 17 Oct 2026. Speed and latency are the reported 30-minute median when available. This is a dated snapshot, not live monitoring.

Provider price comparison

USD per million tokens · input and output rates

InputOutput

DeepInfrafp8

$0.02

$0.04

Novitafp8

$0.02

$0.05

Groq

$0.05

$0.08

Cloudflarefp8

$0.152

$0.287

CoreWeavebf16

$0.22

Reported availability

Provider availability over the selected observation window

DeepInfra · FP899.93%

Novita · FP898.82%

Groq100%

Cloudflare · FP898.92%

CoreWeave · BF16100%

Output speed

Reported 30-minute p50 · tokens per second

No provider throughput measurements were returned in this snapshot.

Response latency

Reported 30-minute p50 · seconds

No provider latency measurements were returned in this snapshot.

Context by provider

Actual route limits can differ from the catalog maximum

DeepInfra · FP8131.1K

Novita · FP816.4K

Groq131.1K

Cloudflare · FP832K

CoreWeave · BF16131.1K

05 / CAPABILITIES & MODALITIES

What goes in. What comes out.

A map of documented interfaces and API features, separate from benchmark performance.

INPUT MODALITIES

Text

Llama-3.1-8B-InstructModel interface

OUTPUT MODALITIES

Text

Feature support

Listed catalog API parameters and documented pricing features

ReasoningNot listed

Tool callingSupported

Tool choiceSupported

Structured outputsSupported

Response formatSupported

Reasoning detailsNot listed

Seed controlSupported

Stop sequencesSupported

Prompt cachingSupported

TemperatureSupported

Room to work

Context capacity and completion limits

131.1Ktotal context tokens

Context window

118Kmax output

Output tokens share the total context budget. The maximum completion length is a separate limit, and individual provider routes may have smaller limits.

Catalog context: 131,072 tokens
Maximum output: 117,964 tokens
Top-provider context: 131,072 tokens

Features vary by route

Check the provider before depending on a specific API feature.

API feature support by provider
Provider route	Reasoning	Tools	Structured output	Response format	Implicit caching
DeepInfra · FP8	Not listed	Not listed	Not listed	Supported	Not listed
Novita · FP8	Not listed	Not listed	Not listed	Supported	Not listed
Groq	Not listed	Supported	Not listed	Supported	Supported
Cloudflare · FP8	Not listed	Not listed	Not listed	Supported	Not listed
CoreWeave · BF16	Not listed	Supported	Supported	Supported	Supported

06 / UNDER THE HOOD

The complete specification sheet.

Exact identities, model architecture, limits, and the defaults that shape a request.

Identity & architecture

Developer: meta-llama
Exact identity: meta-llama/Llama-3.1-8B-Instruct
Subject: Model
Access: Open weights
License: Not disclosed
Parameters: 8 billion
Tokenizer: Llama3
Instruction format: llama3

Reasoning & controls

Reasoning: Not listed
Mandatory reasoning: Not documented
Reasoning by default: Not documented
Published configuration: Not disclosed
Supported reasoning efforts: Not documented
Default reasoning effort: Not disclosed
API parameters: 17
Provider moderation: No
Quantization variants: fp8, bf16

Dates & limits

Catalog added: 23 Jul 2024
Knowledge cutoff: 2023-12-31
Catalog expiration: Not documented
Specifications observed: 17 Oct 2026
Providers observed: 17 Oct 2026
Request limits: Provider-specific / not supplied
Canonical catalog ID: meta-llama/llama-3.1-8b-instruct

API parameters & defaults

Availability is catalog-wide. Defaults can vary across providers.

frequency_penaltySupported · default not supplied

logit_biasSupported · default not supplied

logprobsSupported · default not supplied

max_tokensSupported · default not supplied

min_pSupported · default not supplied

presence_penaltySupported · default not supplied

repetition_penaltySupported · default not supplied

response_formatSupported · default not supplied

seedSupported · default not supplied

stopSupported · default not supplied

structured_outputsSupported · default not supplied

temperatureSupported · default not supplied

tool_choiceSupported · default not supplied

toolsSupported · default not supplied

top_kSupported · default not supplied

top_logprobsSupported · default not supplied

top_pSupported · default not supplied

07 / BUILD WITH THIS MODEL

From exploration to your first request.

Use the documented catalog identifier and keep your API key in an environment variable.

Make an API request

const response = await fetch(
  "https://openrouter.ai/api/v1/chat/completions",
  {
    method: "POST",
    headers: {
      Authorization: `Bearer ${process.env.OPENROUTER_API_KEY}`,
      "Content-Type": "application/json",
    },
    body: JSON.stringify({
      "model": "meta-llama/llama-3.1-8b-instruct",
      "messages": [
        {
          "role": "user",
          "content": "Explain the trade-offs in this design."
        }
      ]
    }),
  },
);
if (!response.ok) throw new Error(`HTTP ${response.status}`);
const data = await response.json();
console.log(data.choices[0].message.content);

08 / PROVENANCE & HISTORY

Every number has a story.

Follow the source, check the observation date, and distinguish published results from model specifications.

The source register

Direct links to the underlying records

OpenRouter model catalog

Architecture, modalities, parameters, and starting prices

Observed 17 Oct 2026

OpenRouter provider routes

Provider limits, prices, availability, and reported measurements

Observed 17 Oct 2026

OpenEvals / Hugging Face

Source-reported · Published snapshot 2026-03-16

Observed 13 Oct 2026

The observation trail

Recorded events, in chronological order

23 Jul 2024Added to the model catalog

Catalog creation date, as recorded by OpenRouter.

15 Mar 2026GPQA Diamond result published

30.4% · OpenEvals / Hugging Face

15 Mar 2026GSM8K result published

84.5% · OpenEvals / Hugging Face

15 Mar 2026MMLU-Pro result published

48.3% · OpenEvals / Hugging Face

17 Oct 2026Model specifications observed

Catalog pricing, limits, and supported parameters captured.

17 Oct 2026Provider routes observed

5 inference routes in this snapshot.

Observation dates describe when data was captured. They do not represent newly run evaluations or continuous performance monitoring.

Published observation ledger

Historical evidence, with source and version preserved.

Published observation history for Llama-3.1-8B-Instruct
Observed	Benchmark	Version	Source	Verification
13 Oct 2026	GPQA Diamond	Published snapshot 2026-03-16	OpenEvals / Hugging Face	Source-reported
13 Oct 2026	MMLU-Pro	Published snapshot 2026-03-16	OpenEvals / Hugging Face	Source-reported
13 Oct 2026	GSM8K	Published snapshot 2026-03-16	OpenEvals / Hugging Face	Source-reported

09 / A FEW MORE DETAILS

Questions worth asking.

Quick answers, drawn from this model’s connected specifications.

How much does Llama-3.1-8B-Instruct cost?

Catalog starting rates are $0.05 per million input tokens and $0.08 per million output tokens. Cache-read pricing is $0.025 per million tokens. Compare provider routes and service tiers above for their specific prices.

How much context can it handle?

131,072 tokens in the catalog context window. The catalog lists a maximum of 117,964 completion tokens. Provider limits can differ.

Does it support tools and structured output?

Tool calling: listed as supported. Structured outputs: listed as supported. See the provider feature matrix for route-specific differences.

How should I interpret these benchmark results?

Read the benchmark name, exact version, metric, source, and model configuration together. Different evaluation settings can change the result. Preference ratings and source-defined composite indices remain separate from task accuracy.

Are these prices and provider measurements live?

This page uses dated source snapshots. Catalog data was observed on 17 Oct 2026. Provider routes were observed on 17 Oct 2026. Missing measurements are not estimated or treated as zero.

Source-backed evidence. Different tasks. A clearer picture.

About Methodology Benchmark dashboard