Meta · Llama

Open-weight Llama models served through optimized Humiris inference routes.

Connect provider Official docs

AVAILABLE THROUGH HUMIRIS

8 production model routes

ToolsVisionOpen weightsLong contextCoding

MODELCONTEXTINPUT / 1MOUTPUT / 1M

Llama 4 Maverick

llama-4-maverick

1M$0.27$0.85Run

Large multimodal open-weight model for general workloads.

ToolsVisionOpen weightsLong context

Llama 4 Scout

llama-4-scout

512K$0.18$0.59Run

Efficient multimodal Llama route with broad context.

ToolsVisionOpen weightsLong context

Llama 3.3 70B Turbo

llama-3.3-70b-turbo

128K$0.88$0.88Run

Production-tuned open model for chat and agent workflows.

ToolsOpen weights

Llama 3.3 8B

llama-3.3-8b

128KRoute pricingRoute pricingRun

Fine-tunable compact Llama model for specialized private workloads.

ToolsOpen weights

Llama 3.2 90B Vision

llama-3.2-90b-vision

128KRoute pricingRoute pricingRun

Large open multimodal model for image and document understanding.

VisionToolsOpen weights

Llama 3.2 11B Vision

llama-3.2-11b-vision

128KRoute pricingRoute pricingRun

Efficient open vision model for private multimodal applications.

VisionToolsOpen weights

Llama 3.1 405B

llama-3.1-405b

128KRoute pricingRoute pricingRun

Large open-weight foundation model for demanding inference workloads.

ToolsOpen weightsCoding

Llama 3.1 8B Instant

llama-3.1-8b-instant

128K$0.050$0.080Run

Ultra-fast open route for simple high-volume tasks.

ToolsOpen weights

Pricing is shown in USD per one million tokens. Route availability and preview pricing can vary by region and account.

READY TO ROUTE

Use Llama with one Humiris key.

Get started