weightsapi.INFERENCEConsole
Navigation
Transparent by the token.

Transparent by the token.

Compare pay-as-you-go token rates and prepaid monthly GPU rentals.

No KYC

No identity-document upload or KYC step in the current sign-in flow. Access and usage remain linked to your account.

No added content filters

WeightsAPI adds no content filter at the gateway. A model’s own training can still lead it to refuse a request.

Add credit before your first request

Minimum top-up: $100. Playground and API use the same prepaid balance.

Top up from $100

Estimate your monthly usage

80% input · 20% output. Uncached standard text rates.

WEIGHTSAPI / MONTH$16.00

Named price baselines checked 2026-09-04. Same token volumes, not equivalent output quality. Excludes caching, tools and taxes.

Pay-as-you-go models

USD / 1 million tokens
ModelInput / 1MOutput / 1MContextType
LLlama 3.1 8B$0.03$0.05128K*Text
DDeepSeek V4 Flash$0.09$0.18128K*Text
GGemma 3 27B$0.10$0.15128K*Text + images
MMistral Small 3$0.10$0.2032K*Text
QQwen3-Coder-Next$0.12$0.80128K*Text
HHermes 4 70B$0.13$0.40128K*Text
MMistral Small 4$0.15$0.60128K*Text + image
QQwen3 32B$0.15$0.20128K*Text
DDolphin Mistral 24B Venice Edition$0.20$0.90128K*Text + image
QQwen3 235B A22B$0.20$0.60128K*Text
DDeepSeek V3$0.25$0.85128K*Text
LLlama 3.3 70B$0.35$0.40128K*Text
DDeepSeek R1$0.50$2.15128K*Text
MMixtral 8×22B$0.60$0.6064K*Text
LLlama 3.1 405B$1.20$1.20128K*Text

*Service context windows. Qwen3 32B requires YaRN above its 32K native window. See each model’s configuration requirements and current service status.

Beyond chat

Embeddings$0.008 / 1M tokens
RerankingPrice to be confirmed
Audio transcription$0.003 / minute
Image generation$0.02 / image
Batch API

Batch processing is currently unavailable. Use synchronous requests for your jobs.

Your model. Your machine.

Dedicated GPUs

Monthly prepaid rental. Capacity and model compatibility are confirmed before activation.

L40S

48 GB · GPU memory

$520 / per monthRent this GPU

A100

80 GB · GPU memory

$990 / per monthRent this GPU

H100 SXM

80 GB · GPU memory

$1,690 / per monthRent this GPU

H200

141 GB · GPU memory

$2,290 / per monthRent this GPU

2 × H100

160 GB · GPU memory

$3,210 / per monthRent this GPU

8 × H100

640 GB · GPU memory

$12,170 / per monthRent this GPU
Crypto payments

XMR (10 confirmations) · BTC (1 confirmations) · USDT (19 confirmations) · TRX (19 confirmations) · USDT (12 confirmations) · USDC (12 confirmations) · ETH (12 confirmations) · SOL (32 confirmations) · LTC (6 confirmations). Every account top-up has a USD 100 minimum. No platform deposit fee. Network fees still apply.