model catalog

Production-ready models

Access frontier open-source LLMs through a single API. Pay per token, no subscription required.

New

DeepSeek V3.2

by DeepSeek
deepseek/deepseek-v3.2
Context 163K
Max Output 65K
Input / 1M $0.26
Output / 1M $0.38
Try it
New

Kimi K2.5

by Moonshot AI
moonshotai/kimi-k2.5
Context 262K
Max Output 262K
Input / 1M $0.45
Output / 1M $2.20
Try it
New

GLM-5

by Zhipu AI
z-ai/glm-5
Context 205K
Max Output 131K
Input / 1M $0.30
Output / 1M $2.55
Try it
New

MiniMax M2.5

by MiniMax
minimax/minimax-m2.5
Context 196K
Max Output 131K
Input / 1M $0.30
Output / 1M $1.10
Try it

Built for AI-powered coding

489 tokens/sec means your AI assistant thinks faster. Cursor autocomplete feels instant, Claude Code edits land quicker, and coding agents iterate in seconds instead of minutes.

4x faster than OpenAI
~90% cheaper than GPT-4o
Works with
Cursor Claude Code Cline Windsurf Kilo Code 20+ more
Output speed comparison
Avian (DeepSeek V3.2)489 tok/s
OpenAI (GPT-4o)120 tok/s
Anthropic (Claude 3.5)90 tok/s
Cost per 1M output tokens
Avian (DeepSeek V3.2)$0.38
OpenAI (GPT-4o)$10.00
Anthropic (Claude 3.5)$15.00
Set up in 60 seconds

OpenAI Compatible

Drop-in replacement for the OpenAI SDK. Change one line of code to switch.

No Rate Limits

Scale without restrictions. Send as many requests as you need.

NVIDIA B200 GPUs

Latest hardware for the fastest inference available today.

Start building with Avian

Get your API key in under a minute.

Get Started Free