FR
Friendli AI
Serverless
Fast serverless and dedicated AI inference. Korean provider with competitive pricing on open-source models and prompt caching support.
Features
OpenAI Compatible
Streaming
Batching
Fine-tuning
Embeddings
Vision
Audio
Function Calling
JSON Mode
Compliance
SOC 2
HIPAA
GDPR
Pricing Model
per token Free tier: Up to 50K inference credit for new users
Details
Models 13
API Base
https://api.friendli.ai/v1 Audio / MusicLLM Inference
Model Catalog (13)
| Model | Type | Input $/1M | Output $/1M | Context | Speed | Status |
|---|---|---|---|---|---|---|
| DeepSeek V3.2 DeepSeek · 671B MoE (37B active) | llm | $0.500 | $1.50 | — | — | |
| GLM 4.7 Zhipu AI | llm | $0.600 | $2.20 | — | — | |
| GLM 5 Zhipu AI · 744B | llm | $1.00 | $3.20 | — | — | |
| GLM 5.1 Z.ai · 744B MoE (40B active) | llm | $1.40 | $4.40 | — | — | |
| GLM 5.2 Z.ai | llm | $1.40 | $4.40 | — | — | |
| GLM 5.3 Z.ai | llm | $1.40 | $4.40 | 1.0M | — | |
| GLM 5.3 Flash Z.ai | llm | $0.150 | $0.500 | 1.0M | — | |
| Gemma 4 31B Google · 27B | llm | $0.140 | $0.400 | 262k | — | |
| Kimi K2.5 Moonshot AI · 1T MoE (32B active) | llm | $0.600 | $3.00 | — | — | |
| Llama 3.3 70B Meta · 70B | llm | $0.600 | $0.600 | — | — | |
| MiniMax M2.5 MiniMax | llm | $0.300 | $1.20 | — | — | |
| Qwen 3 235B Alibaba · 235B MoE | llm | $0.200 | $0.800 | — | — | |
| Whisper Large V3 OpenAI · 1.5B | speech to_text | $0.0000/sec | — | — | — |
Friendli AI API FAQ
Is the Friendli AI API free?
Yes, Friendli AI has a free tier: Up to 50K inference credit for new users. Paid usage is billed per model.
What is the cheapest Friendli AI model?
Gemma 4 31B at $0.14 in / $0.40 out per 1M tokens, based on the 13 models we track for Friendli AI.
How many models does Friendli AI offer?
We track 13 Friendli AI models: 12 LLM, 1 speech-to-text.
Is the Friendli AI API OpenAI-compatible?
Yes. Friendli AI exposes an OpenAI-compatible endpoint, so you can use the OpenAI SDKs by changing the base URL and API key.