MetaCertifiedReleased 07/23/2024

Llama 3.1 8B Instruct

An update to Meta Llama 3 8B Instruct that includes an expanded 128K context length, multilinguality and improved reasoning capabilities.

View API reference ↓
Input / output priceFrom$0.020 / $0.050per 1M
24h uptime100.00%
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "meta/llama-3.1-8b",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Providers

Dispatch routes requests across these providers and fails over between them without changing the model. Restrict or order providers with team Directives. Prices are gateway list prices before the platform fee.

ProviderContextMax outputLatencyThroughputInputOutputCacheCapabilitiesZDRNo trainingRegionsStatus
Amazon Bedrock128K8K0.2 s301 tps$0.22$0.22Read —Write —2 featuresYesYesGlobalCertified
novita16K16K0.5 s—$0.020$0.050Read —Write —3 featuresNoNoGlobalCertified

Uptime

24 hours

Request success rate per provider.

Amazon Bedrock100.00%
novita100.00%

Throughput

last hour

P50 output tokens per second.

Amazon Bedrock301 tps
novita—

Latency

last hour

P50 time to first token.

Amazon Bedrock0.2 s
novita0.5 s

Getting started

Create a key on the API Keys page and set it as IB_API_KEY. See the quickstart.

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.inferencebureau.com/v1",
  apiKey: process.env.IB_API_KEY,
});

const res = await client.chat.completions.create({
  model: "meta/llama-3.1-8b",
  messages: [{ role: "user", content: "Why is the sky blue?" }],
});

console.log(res.choices[0].message.content);

Top-level parameters

Standard Chat Completions parameters work as documented. These have model-specific behavior.

ParameterTypeRequiredDescription
modelstringYesModel ID in the form creator/model, e.g. meta/llama-3.1-8b. Must be allowed by your team's Directives.
max_tokensnumberNoHard cap on generated tokens, and the basis for the balance reserved per request. Llama 3.1 8B Instruct supports up to 8,192 output tokens.
toolsTool[]NoFunction definitions the model can call. Tool calls are returned in choices[].message.tool_calls.
Supportedmax_tokenstemperaturestoptoolstool_choiceresponse_formatstructured_outputs

Input limits

InputSourcesLimits
Text—Prompt and response share the 128K-token context window

More models by Meta

ModelContextInputOutputCacheRelease
meta/muse-ember1.05M$0.100$0.50Read $0.0040Write —11/09/2026
meta/muse-spark-open1.05M$1.25$4.25Read $0.15Write —10/15/2026
meta/muse-wonder-1.01.05M$4.00$20.00Read $0.20Write —10/12/2026
meta/muse-spark-1.31.05M$1.25$4.25Read $0.15Write —09/02/2026
meta/muse-spark-1.3-contributor1.05M$0.100$0.20Read $0.0020Write —09/02/2026
meta/muse-glimmer-30b131K$0.35$1.50Read $0.040Write —08/10/2026
meta/muse-spark-1.21.05M$1.25$4.25Read $0.15Write —08/05/2026
meta/muse-spark-1.2-contributor1.05M$0.100$0.20Read $0.0020Write —08/05/2026
meta/muse-spark-1.11.05M$1.25$4.25Read $0.15Write —07/09/2026
meta/llama-4-maverick128K$0.24$0.97Read —Write —04/05/2025