LLM ReferenceLLM Reference
Replicate API

Falcon 40B on Replicate API

Falcon · Technology Innovation Institute (TII)

Serverless

Last refreshed 2026-04-19. Next refresh: weekly.

Why use Falcon 40B on Replicate API?

Replicate API offers Falcon 40B with pay-as-you-go pricing at $0.65/1M input tokens. Replicate is a cloud-based platform that enables users to run machine learning models easily and efficiently.

Compare Falcon 40B across 4 providers to find the best fit for your use case
Input / 1M
$0.65
Output / 1M
$2.75
Cache
Not sourced
Batch
Not sourced

Setup recipe

Python + curl
Install
pip install replicate
Auth
export REPLICATE_API_TOKEN=...
Call
import replicate
output = replicate.run(
    "falcon-40b",
    input={"prompt": "Hello"}
Model ID
falcon-40b

Request example

import replicate

# reads REPLICATE_API_TOKEN from env
# falcon-40b format: "owner/model-name" (latest version) or "owner/model-name:version-hash"
output = replicate.run(
    "falcon-40b",
    input={"prompt": "Hello"}
)
# Output is a list or generator depending on the model
print("".join(output))

Gotchas

  • Replicate uses "owner/model-name" format (e.g. "meta/meta-llama-3-8b-instruct") for the latest version, or "owner/model-name:version-sha" to pin to a specific version. The REST endpoint splits owner and model-name into the path: /v1/models/{owner}/{model-name}/predictions.
  • The examples expect REPLICATE_API_TOKEN; rename it only if your application config maps the new variable.

Compare Falcon 40B Across Providers

ProviderInput (per 1M)Output (per 1M)
Microsoft Foundry$1.54$1.77
GCP Vertex AI
Alibaba Cloud PAI-EAS
Replicate API$0.65$2.75

Pricing

TypePrice (per 1M)
Input tokens$0.65
Output tokens$2.75

Capabilities

Structured Outputs

About Falcon 40B

Falcon 40B is a leading open-source large language model developed by the Technology Innovation Institute in Abu Dhabi, featuring a causal decoder-only architecture with 40 billion parameters. It stands out with its use of rotary positional embeddings, multi-query attention, and FlashAttention, enhancing its contextual understanding and processing efficiency. Trained on 1 trillion tokens using the enriched RefinedWeb dataset, Falcon 40B excels in various natural language processing tasks, ranging from text generation to language translation and question answering. It supports multiple languages and is open under the Apache 2.0 license, promoting both research and commercial use. The model efficiently utilizes standard hardware, requiring around 85-100 GB of memory for inference, setting a benchmark for performance and scalability in its category.

FAQ

What does Falcon 40B cost on Replicate API?

On Replicate API, Falcon 40B costs $0.65 per 1M input tokens and $2.75 per 1M output tokens.

How does Replicate API compare to other Falcon 40B providers?

Falcon 40B is available from 4 providers. The cheapest input pricing is $0.65/1M tokens from Replicate API.

Who created Falcon 40B?

Falcon 40B was created by Technology Innovation Institute (TII) as part of the Falcon model family.

Is Falcon 40B open source?

Falcon 40B is open source under Apache 2.0 according to the seed data.

Get Started

Model Specs

Released2023-11-28
Parameters40B
ArchitectureDecoder Only