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

CoreWeave

Categories
GPU clouds, Inference hosts
Owned by
CoreWeave, Inc. (Nasdaq: CRWV) — owns Weights & Biases
HQ
US
Website
https://wandb.ai/site/inference
Pricing page
https://wandb.ai/site/pricing/inference
Offers
GPU, bare metal, managed k8s, object storage
Fee model
per_token
Fees
Per-token pricing for W&B-hosted models; billed in addition to W&B Pro/Enterprise licences. Playground usage billed at the same token rates. Monthly spend budget configurable.
Free tier
no
OpenAI-compatible API
yes
Bring your own key
no
Notes
Serverless inference run on CoreWeave GPUs, sold under the Weights & Biases brand (listed as "CoreWeave" on OpenRouter).
Sources
https://wandb.ai/site/pricing/inference https://docs.wandb.ai/inference/models collected 2026-09-18

LLM prices (25 models, USD per 1M tokens)

ModelInputOutputCached inputContextSource
DeepSeek V3.1
deepseek-ai/DeepSeek-V3.1
$0.55$1.65161k src src2
DeepSeek V4 Flash 0423
deepseek-ai/DeepSeek-V4-Flash
$0.14$0.28$0.071.05M src src2
DeepSeek V4 Flash 0731
deepseek-ai/DeepSeek-V4-Flash-0731
$0.13$0.28$0.07262k src src2
DeepSeek V4 Pro 0423
deepseek-ai/DeepSeek-V4-Pro
$1.15$2.55$0.201.05M src src2
DeepSeek V4 Pro 0813
deepseek-ai/DeepSeek-V4-Pro-0813
$1.31$3.96$0.0441.05M src src2
Gemma 4 31B
google/gemma-4-31B-it
$0.10$0.34262k src src2
GLM 5 $1$3.20 src src2
GLM-5.2
zai-org/GLM-5.2
$0.76$2.42$0.141.05M src src2
GLM-5.3 Flash
zai-org/GLM-5.3-Flash
$0.15$0.50$0.051.05M src src2
gpt-oss-120b
openai/gpt-oss-120b
$0.03$0.17131k src src2
gpt-oss-20b
openai/gpt-oss-20b
$0.03$0.13131k src src2
IBM Granite 4.2 8B
ibm-granite/granite-4.2-8b
$0.10$0.15$0.05131k src src2
Kimi K2.6
moonshotai/Kimi-K2.6
$0.65$3.41$0.15262k src src2
Kimi K2.7 Code
moonshotai/Kimi-K2.7-Code
$0.71$3.50$0.15262k src src2
Llama 3.1 70B Instruct
meta-llama/Llama-3.1-70B-Instruct
$0.80$0.80131k src src2
Llama 3.1 8B Instruct
meta-llama/Llama-3.1-8B-Instruct
$0.22$0.22131k src src2
Llama 3.3 70B Instruct
meta-llama/Llama-3.3-70B-Instruct
$0.71$0.71128k src src2
MiniMax M3
MiniMaxAI/MiniMax-M3
$0.23$0.96$0.05262k src src2
NVIDIA Nemotron 3 Ultra (Preview)
nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B
$0.50$2.15$0.10262k src src2
NVIDIA Nemotron 3.5 Lightning 30B A3B
nvidia/NVIDIA-Nemotron-3.5-Lightning-30B-A3B
$0.07$0.20$0.04262k src src2
Qwen3-30B-A3B-Instruct-2507
Qwen/Qwen3-30B-A3B-Instruct-2507
$0.10$0.30262k src src2
Qwen3.5-35B-A3B
Qwen/Qwen3.5-35B-A3B
$0.25$1.25262k src src2
Qwen3.6 27B
Qwen/Qwen3.6-27B
$0.60$3.60$0.12262k src src2
Qwen3.6 35B A3B
Qwen/Qwen3.6-35B-A3B
$0.25$1.25262k src src2
Qwen3.8-27B
Qwen/Qwen3.8-27B
$0.40$3$0.15262k src src2

GPU rates

ProviderGPUGPUsVRAM/GPUBillingPer GPU-hrInstance /hrRegionSource
CoreWeaveL40 848 GBon demand $1.25$10North America src
CoreWeaveL40S 848 GBon demand $2.25$18North America src
CoreWeaveRTX PRO 6000 896 GBon demand $2.50$20North America src
CoreWeaveA100 80GB 880 GBon demand $2.70$21.60North America src
CoreWeaveH100 SXM 880 GBon demand $6.16$49.24North America src
CoreWeaveH200 8141 GBon demand $6.30$50.44North America src
CoreWeaveGH200 196 GBon demand $6.50$6.50North America src
CoreWeaveB200 8180 GBon demand $8.60$68.80North America src
CoreWeaveGB200 4186 GBon demand $10.50$42North America src