GPT-OSS-20B API pricing on EcoHash
Every EcoHash GPT-OSS-20B rate we track, compared against 11 providers serving the same model.
The cheapest GPT-OSS-20B input price we currently track is $0.018/1M on OpenRouter.
EcoHash GPT-OSS-20B rates
Prices per 1M tokens. Batch and cached-input rates are shown where the provider publishes them.
| Mode | Input | Output |
|---|---|---|
| Standard | $0.050/1M | $0.200/1M |
About GPT-OSS-20B
- Creator
- OpenAI
- Context
- 128K
- Modalities
- text
- Knowledge cutoff
- Jan 2025
- Open weights
- Yes
GPT-OSS-20B on other providers
About EcoHash
EcoHash rents NVIDIA RTX PRO 6000 Server Edition (Blackwell, 96 GB) GPUs as instances of 1, 2, 4 or 8 GPUs and multi-replica clusters, and serves open models for text, vision, image, speech and video through an OpenAI-compatible inference API. It also offers dedicated inference endpoints and managed LoRA/QLoRA fine-tuning. EcoHash Platform Technology LLC was founded in 2025 as the HPC and AI inference division of Cango Inc. (NYSE: CANG), a Bitcoin mining company.
Frequently Asked Questions
How much does GPT-OSS-20B cost on EcoHash?
EcoHash serves GPT-OSS-20B from $0.050 per 1M input tokens, across 1 tracked pricing mode. Prices are collected daily — see the table above for current input, output, and cached-input rates.
Is EcoHash the cheapest way to run GPT-OSS-20B?
EcoHash ranks #7 of 11 providers we track serving GPT-OSS-20B. The cheapest input price right now is on OpenRouter. Price is only one factor — throughput, latency, and context limits differ between providers.
Does EcoHash offer batch or cached pricing for GPT-OSS-20B?
We track 1 GPT-OSS-20B offering from EcoHash. Batch and cached-input rates appear in the table above when the provider publishes them; blank cells mean we have no current figure for that mode.