Tessera Cloud
One flat fee. Five open-weight models. OpenAI-compatible.
Five open-weight models behind one OpenAI-compatible API. One flat monthly fee, no per-model upsell, no token meter. • Qwen 3.6-35B-A3B — chat, 32K context, direct & thinking modes • Whisper large-v3 + turbo — multilingual transcription • Kokoro 82M TTS — sub-200ms voice synthesis, 54 voices • Qwen3-Embedding-8B — 4,096-dim, multilingual • Qwen3-Reranker-4B — Cohere-compatible, drop-in from Cohere/Voyage/Jina Drop-in for the OpenAI SDK. EU / LATAM / US residency.
About Tessera Cloud
Five open-weight models behind one OpenAI-compatible API. One flat monthly fee, no per-model upsell, no token meter. • Qwen 3.6-35B-A3B — chat, 32K context, direct & thinking modes • Whisper large-v3 + turbo — multilingual transcription • Kokoro 82M TTS — sub-200ms voice synthesis, 54 voices • Qwen3-Embedding-8B — 4,096-dim, multilingual • Qwen3-Reranker-4B — Cohere-compatible, drop-in from Cohere/Voyage/Jina Drop-in for the OpenAI SDK. EU / LATAM / US residency.
Upvotes over time
Last 24 hoursTotal upvotes
9
Last 24h
—
Peak hour
—
No upvote activity in the last 24 hours.
2 comments
Got tired of token meters and US-only APIs, so I built mine: 5 open models, one flat monthly bill, EU/LATAM/US residency contracted. What would actually get you to switch from your current LLM cloud?
Is it like on mothly fee per 5 models? Wow!