Skip to content
Meta logo

Llama 3.1 8B Instruct

meta/llama-3.1-8b-instructPOST /v1/chat/completions

Small, extremely cheap open-weights model. The floor of the catalogue for simple classification work.

Tool callingStructured outputStreaming
Input / 1M
$0.0200
via DeepInfra
Output / 1M
$0.0400
via DeepInfra
Cached input / 1M
not published
Context
131K
max out 131K
Providers
3
failover available

3 providers serve this model

Multigrid picks between them on every request using your policy. Each price is what that route costs us, and we add no spread of our own to it.

ProviderUpstream model idIn / 1MOut / 1MBilling
DeepInfraCheapestmeta-llama/Meta-Llama-3.1-8B-Instruct-Turbo$0.0200$0.0400Credit
Groqllama-3.1-8b-instant$0.0500$0.0800Credit
OpenRoutermeta-llama/llama-3.1-8b-instruct$0.0500$0.0800Credit
No performance data published yet
Time to first token, throughput and uptime are measurements, and Multigrid has not served enough traffic through Llama 3.1 8B Instruct to publish honest ones. When it has, they will appear here per provider, taken from real requests. Nothing on this page is estimated: prices, context window and capabilities all come from the provider’s own documentation.

Call it

Same request shape as every other model in the catalogue.

example.ts
const res = await client.chat.completions.create({
  model: "meta/llama-3.1-8b-instruct",
  messages: [{ role: "user", content: "Hello" }],
  route: {
    // pin, exclude or order the providers below
    providers: ["deepinfra", "groq", "openrouter"],
    sort: "price",
  },
});

Send Llama 3.1 8B Instruct a real request

Signing up takes no card and commits you to nothing — you start at a zero balance, so nothing can be charged until you decide to add credit. The playground opens on Llama 3.1 8B Instruct and prices every answer as it arrives, at the rate shown above — what the route costs us, with nothing of ours added. Already have an account? The second button skips the form.

Llama 3.1 8B Instruct — API and pricing · Multigrid