model catalog

Production-ready models

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

New

DeepSeek V4.1 Flash

by DeepSeek
deepseek/deepseek-v4.1-flash
Context 1M
Max Output 384K
Input / 1M $0.1275
Output / 1M $0.51
Cache / 1M $0.00255
Try it
New

DeepSeek V4 Flash

by DeepSeek
deepseek/deepseek-v4-flash
Context 1M
Max Output 384K
Input / 1M $0.14
Output / 1M $0.28
Cache / 1M $0.0028
Try it
New

DeepSeek V4 Pro 0813

by DeepSeek
deepseek/deepseek-v4-pro-0813
Context 1M
Max Output 384K
Input / 1M $0.561
Output / 1M $1.683
Cache / 1M $0.0187
Try it
New

MiniMax M3

by MiniMax
minimax/minimax-m3
Context 512K
Max Output 500K
Input / 1M $0.255
Output / 1M $1.02
Cache / 1M $0.051
Try it
New

GLM-5.3

by Zhipu AI
z-ai/glm-5.3
Context 1M
Max Output 131K
Input / 1M $1.19
Output / 1M $3.74
Cache / 1M $0.221
Try it
New

GLM-5.3 Flash

by Zhipu AI
z-ai/glm-5.3-flash
Context 1M
Max Output 131K
Input / 1M $0.1275
Output / 1M $0.425
Cache / 1M $0.0255
Try it
New

Kimi K3

by Moonshot AI
moonshotai/kimi-k3
Context 1M
Max Output 922K
Input / 1M $2.55
Output / 1M $12.75
Cache / 1M $0.255
Try it
New

MiMo-V2.6 Flash

by Xiaomi
xiaomi/mimo-v2.6-flash
Context 1M
Max Output 131K
Input / 1M $0.14
Output / 1M $0.28
Cache / 1M $0.0028
Try it
New

MiMo-V2.6 Pro

by Xiaomi
xiaomi/mimo-v2.6-pro
Context 1M
Max Output 131K
Input / 1M $0.36975
Output / 1M $0.7395
Cache / 1M $0.00306
Try it
New

MiMo-V2.5 Pro

by Xiaomi
xiaomi/mimo-v2.5-pro
Context 1M
Max Output 131K
Input / 1M $0.36975
Output / 1M $0.7395
Cache / 1M $0.00306
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 V4.1 Flash)489 tok/s
OpenAI (GPT-4o)120 tok/s
Anthropic (Claude 3.5)90 tok/s
Cost per 1M output tokens
Avian (DeepSeek V4.1 Flash)$0.51
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