EcoHash Inference
Vision Chat
Ask questions about an image with Qwen3-VL-8B-Instruct, or run text-only with gpt-oss-20b. Every reply reports time to first token, throughput, token counts and the exact cost of that request. Both models run on EcoHash's own GPUs behind one OpenAI-compatible endpoint.
Runs on the EcoHash demo key by default, with a small free allowance per visitor per day. Paste your own key to lift the limit — it is held for this browser session only, never stored, never logged, and never shown in the generated code below.
Qwen3-VL-8B-Instruct handles documents, charts, screenshots and photographs at $0.15 in / $0.50 out per 1M tokens.
gpt-oss-20b is a 21B mixture-of-experts model with 3.6B active parameters at $0.20 in / $0.28 out per 1M tokens — a typical reply in this demo costs well under one hundredth of a cent.
Replies are capped at 1024 tokens. This demo gives each visitor 5 free runs a day on the EcoHash demo key; paste your own key above to lift that.
- Qwen3-VL-8B-Instruct
- $0.15 in / $0.50 out per 1M tokens · Qwen/Qwen3-VL-8B-Instruct
- gpt-oss-20b
- $0.20 in / $0.28 out per 1M tokens · openai/gpt-oss-20b
Every model in this Space runs on EcoHash's own
NVIDIA RTX PRO 6000 Blackwell
fleet — no third-party resale — and is reachable through one OpenAI-compatible
endpoint at https://api.ecohash.com/v1. GPU instances from $1.89 per GPU-hour, billed per second.
Model catalog · Pricing · Docs · More demos · Create an account ($1 free credit)