Modelcatalog
One API to run leading open models for chat, embeddings, speech, image and video, served in the region you choose.
DeepSeekchat
DeepSeek V4.1 Flash
Released 16 Sept 2026
High-efficiency flash model from DeepSeek. Optimized for low-latency response and high-throughput reasoning.
ContextInput $0.30 / M tokens1049KCached $0.006 / M tokensMax output —Output $1.40 / M tokens
OpenAIchat
GPT-OSS 120B
Released 4 May 2026
OpenAI's flagship open-weight model. Apache-licensed weights and inference recipe; competitive with closed mid-tier models across reasoning benchmarks.
ContextInput $0.15 / M tokens—Cached $0.00 / M tokensMax output —Output $0.60 / M tokens
OpenAIchat
GPT-OSS 20B
Released 4 May 2026
OpenAI's compact open-weight release. Apache-licensed weights suited to self-hosted, latency-sensitive, and fine-tuning workloads.
ContextInput $0.05 / M tokens—Cached $0.00 / M tokensMax output —Output $0.20 / M tokens
Infinia Aitext to speech
chatterbox-multilingual-packs
Text to speech$15.00 per 1M chars
DeepSeekchat
deepseek-v4-flash-0731
ContextInput $0.14 / M tokens1049KCached $0.00 / M tokensMax output —Output $0.28 / M tokens
Microsoftchat
fara1.5-27b
ContextInput $0.27 / M tokens262KCached $0.00 / M tokensMax output —Output $0.76 / M tokens
Googlechat
gemma-4-31b-it
ContextInput $0.27 / M tokens262KCached $0.00 / M tokensMax output —Output $0.76 / M tokens
Zai Orgchat
glm-ocr
ContextInput $0.04 / M tokens131KCached $0.00 / M tokensMax output —Output $0.08 / M tokens
Tencentchat
hunyuanocr
ContextInput $0.14 / M tokens16KCached $0.00 / M tokensMax output —Output $0.57 / M tokens
Lightricksvideo
ltx-2.5
Video$0.05 per second
Infiniatechnologieschat
nia-1.0
ContextInput $1.40 / M tokens131KCached $0.26 / M tokensMax output —Output $4.40 / M tokens
Qwenspeech to text
qwen3-asr-1.7b
Speech to text$0.006 per minute
Qwenembedding
qwen3-embedding-8b
Embeddings$0.10 per 1M tokens
Qwenchat
qwen3-omni-30b-a3b-instruct
ContextInput $0.43 / M tokens66KCached $0.00 / M tokensMax output —Output $1.66 / M tokens
Vadimbelskytext to speech
qwen3.5-tts-emirati
Text to speech$15.00 per 1M chars
Qwenchat
qwen3.8-27b
ContextInput $0.42 / M tokens262KCached $0.00 / M tokensMax output —Output $3.00 / M tokens
Infiniatechnologieschat
saqr-27b
ContextInput $0.27 / M tokens262KCached $0.00 / M tokensMax output —Output $0.76 / M tokens
Stability AIimage
sd3.5-large
Image$0.04 per image
Artpark Iiscspeech to text
sravaani-1.0
Speech to text$0.006 per minute
Model pages, the playground and the API need a free account.Create one