CloudTopHosts is operated by WiserWeb, which also sells WiserWebCloud (listed here). Tables are ordered by advertised price. Sponsored placements are labelled and never change that order. How this works
CloudTopHosts

gpt-oss-20b openai/gpt-oss-20b

Served by 19 providers. Cheapest: AkashML at $0.04 blended /1M tokens. The most expensive listing costs 5.6× as much for the same model.

Estimate my monthly bill →

ProviderTypeInput /1MOutput /1MCached inputBlendedContextNotesSource
AkashML
openai/gpt-oss-20b
Inference hosts $0.02$0.10$0.04 128k Limited Trial. src src2
2026-09-18
CoreWeave
openai/gpt-oss-20b
Inference hosts $0.03$0.13$0.055 131k Context from docs model table (rounded, e.g. "262k"). src src2
2026-09-18
OpenRouter
openai/gpt-oss-20b
LLM routers $0.03$0.13$0.03$0.055 131k api modality text->text src
2026-09-18
DeepInfra
openai/gpt-oss-20b
Inference hosts $0.03$0.14$0.058 131k bf16 src src2
2026-09-18
Featherless
openai/gpt-oss-20b
Inference hosts $0.04$0.15$0.068 131k Developer-plan per-token rate; model_class gpt-oss-20b; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) src src2 src3
2026-09-18
GMI Cloud Inference Engine
openai/gpt-oss-20b
Inference hosts $0.04$0.15$0.068 from GMI console public pricing API (console is client-rendered; docs say prices live in console Model Hub) src src2
2026-09-18
Novita AI
openai/gpt-oss-20b
Inference hosts $0.04$0.15$0.068 131k src src2
2026-09-18
SiliconFlow
openai/gpt-oss-20b
Inference hosts $0.04$0.18$0.075 context shown on pricing page as "131K" src
2026-09-18
OVHcloud AI Endpoints
gpt-oss-20b
Inference hosts $0.046$0.172$0.077 fp4 list price EUR 0.04/M in, EUR 0.15/M out; context shown on catalog as "131K" (rounded); converted at ECB EURUSD 1.1481 2026-09-17 (latest ECB reference rate) src
2026-09-18
Parasail Inference hosts $0.04$0.20$0.02$0.08 src
2026-09-18
Nscale Serverless Inference
openai/gpt-oss-20b
Inference hosts $0.05$0.20$0.088 131k price as listed by Hugging Face Inference Providers router for provider "nscale" (HF states it passes provider prices through with no markup); Nscale publishes model prices only in its console / authenticated /v1/models src
2026-09-18
Google Vertex AI (Gemini Enterprise Agent Platform) Hyperscaler AI platforms $0.07$0.25$0.007$0.115 batch −50% Managed MaaS API. Batch $0.035/$0.125. src
2026-09-18
Amazon Bedrock
openai.gpt-oss-20b-1:0
Hyperscaler AI platforms $0.07$0.30$0.128 128k batch −50% src src2
2026-09-18
Oracle OCI Generative AI
openai.gpt-oss-20b
Hyperscaler AI platforms $0.07$0.30$0.128 Parts B112006/B112007. provider_model_id not verified on the price list. src src2
2026-09-18
Requesty
fireworks/gpt-oss-20b
LLM routers $0.07$0.30$0.035$0.128 131k upstream route fireworks; geo global; 1 other upstream routes listed (input $0.1-$0.1/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included src
2026-09-18
Groq
openai/gpt-oss-20b
Inference hosts $0.075$0.30$0.131 131k batch −50% Cached input 50% discount; ~1000 tok/s src
2026-09-18
DigitalOcean
openai-gpt-oss-20b
Inference hosts $0.05$0.45$0.15 128k src src2
2026-09-18
Replicate
openai/gpt-oss-20b
Inference hosts $0.09$0.36$0.158 src
2026-09-18
Cloudflare Workers AI
@cf/openai/gpt-oss-20b
Inference hosts $0.20$0.30$0.225 Billed in neurons ($0.011/1k neurons); USD per-M-token equivalent as published by Cloudflare src
2026-09-18

✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.