Skip to content
Agents tracked: 302 Downloads (7d): 239M down 5.7% GitHub stars: 6.4M VS Code installs: 151M Releases (7d): 342 Agent status: 5 with issues Updated Oct 9, 2026

Friendli by FriendliAI

API for running frontier model inference with text, vision, and speech-to-text capabilities.

Model hosting and inference

Price
see pricing
list price
Free tier
No
SDK downloads
—
no official SDK package
Status
—
no public status page

Pricing

Free tier—
Cheapest paid plan—
Usage pricePay per token for text/vision models, per audio minute for STT
Good to knowAdded automatically: integrations in LlamaIndex. Prices read from the official pricing page.

From the official pricing page, checked Oct 9, 2026. Prices change: confirm before you buy.

Use it from an agent

MCP serverNone found

Alternatives to Friendli

All model hosting and inference

APIFreePrice SDK downloads / wkGitHub starsMCP
Fireworks
Serverless inference API with per-token pricing for running open and proprietary models.
— per token for inference; per GPU second for on-demand deployments — —
Replicate
Run and deploy machine learning models with pay-per-use pricing for inference.
— Varies by model and hardware; examples: $0.04/output image,... — —
AI21
API access to foundation models for text generation and chat tasks.
$10 credits for 7 days Free plan
then $0.2 per 1M input tokens, $0.4 per 1M output tokens...
— —
Baseten
Deploy and run custom, fine-tuned, and open-source AI models with GPU compute.
Free credits for new accounts Free plan
then Price per 1M tokens for Model APIs; price per minute for...
— —
DeepInfra
API for running various AI models including text generation, embeddings, image generation, and speech recognition.
— Per token pricing varies by model; e.g., $0.06 per 1M input tokens... — —
Together AI
API for inference on open-source and third-party language models, vision, audio, video, and embeddings.
— varies by model and task; e.g., $0.30 per 1M input tokens (MiniMax... — —
Is Friendli right for you? Ask AgentGid →