Verda Inference
Serves frontier open-weight models such as Kimi K3.1 Pro and DeepSeek V4.1 Flash, with 1M-token context, through one OpenAI-compatible API billed per token.
Find alternatives to Verda Inference
What it does
- Model inference
- Model hosting
Sources
- Pricing
-
Pricing source read 2026-11-16: "Frontier open-weight models through one OpenAI compatible API, billed per token. Prices are per 1M tokens."; "Kimi K3.1 Pro 1M $2.00 $0.20 $10.00".
- Description
-
Official documentation · 16 Nov 2026
Product page text fetched 2026-11-16; page quote: "Verda Inference is now in preview."; "Frontier open-weight models per token, through one OpenAI compatible API"; "Kimi K3.1 Pro Available".
- What it does
-
Official documentation · 16 Nov 2026
Product page text fetched 2026-11-16; page quote: "Verda Inference is now in preview."; "Frontier open-weight models per token, through one OpenAI compatible API"; "Kimi K3.1 Pro Available".
- Sold within
-
Sold on its own: the pricing page publishes a per-token rate card for the inference preview, and the same console sign-up serves it. Page quote: "Frontier open-weight models through one OpenAI compatible API, billed per token. Prices are per 1M tokens."; "Kimi K3.1 Pro 1M $2.00 $0.20 $10.00".
- Name
-
Official documentation · 16 Nov 2026
Product page text fetched 2026-11-16; page quote: "Verda Inference is now in preview."; "Frontier open-weight models per token, through one OpenAI compatible API"; "Kimi K3.1 Pro Available".
- URL
-
Official documentation · 16 Nov 2026
Product page text fetched 2026-11-16; page quote: "Verda Inference is now in preview."; "Frontier open-weight models per token, through one OpenAI compatible API"; "Kimi K3.1 Pro Available".
- Deployment
-
Official documentation · 16 Nov 2026
Product page text fetched 2026-11-16; page quote: "Verda Inference is now in preview."; "Frontier open-weight models per token, through one OpenAI compatible API"; "Kimi K3.1 Pro Available". The pages read describe a vendor-run web service and no other deployment model, so saas is the value written.
- Interfaces
-
Official documentation · 16 Nov 2026
Page quote: "Quickstart Make your first call in minutes with an OpenAI client".
Also from Verda
-
Verda Cloud Infrastructure service
Verda Cloud rents NVIDIA GPU instances and InfiniBand clusters by the hour, runs auto-scaling serverless GPU containers for inference and batch jobs, and serves open-weight models per token through an OpenAI-compatible API.
Something wrong here? Send a correction — quote this product id: verda-inference.