No KYC
No identity-document upload or KYC step in the current sign-in flow. Access and usage remain linked to your account.
Navigation
Model catalog
Model catalog
Choose the right balance of capability, context and cost.
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.
15 open-weight models. Publisher releases.
Published model sources verified 2026-09-04. Check service status for current availability. API model list ↗
| Model | Input / 1M | Output / 1M | Context | Type |
|---|---|---|---|---|
| Llama 3.1 8B | $0.03 | $0.05 | 128K* | Text |
| DeepSeek V4 Flash | $0.09 | $0.18 | 128K* | Text |
| Gemma 3 27B | $0.10 | $0.15 | 128K* | Text + images |
| Mistral Small 3 | $0.10 | $0.20 | 32K* | Text |
| Qwen3-Coder-Next | $0.12 | $0.80 | 128K* | Text |
| Hermes 4 70B | $0.13 | $0.40 | 128K* | Text |
| Mistral Small 4 | $0.15 | $0.60 | 128K* | Text + image |
| Qwen3 32B | $0.15 | $0.20 | 128K* | Text |
| Dolphin Mistral 24B Venice Edition | $0.20 | $0.90 | 128K* | Text + image |
| Qwen3 235B A22B | $0.20 | $0.60 | 128K* | Text |
| DeepSeek V3 | $0.25 | $0.85 | 128K* | Text |
| Llama 3.3 70B | $0.35 | $0.40 | 128K* | Text |
| DeepSeek R1 | $0.50 | $2.15 | 128K* | Text |
| Mixtral 8×22B | $0.60 | $0.60 | 64K* | Text |
| Llama 3.1 405B | $1.20 | $1.20 | 128K* | Text |
Choose by workload
L
Llama 3.1 8B
Fast classification, extraction and lightweight chat.
$0.03 / $0.05Llama 3.1 Community
DDeepSeek V4 Flash
A text model for long-context reasoning, coding and tool workflows, with a configured 1,048,576-token window.
$0.09 / $0.18MIT
GGemma 3 27B
Image understanding and multilingual conversation.
$0.10 / $0.15Gemma Terms of Use
MMistral Small 3
Efficient text tasks, function calling and European-language chat.
$0.10 / $0.20Apache 2.0
QQwen3-Coder-Next
A text-only coding model for codebase exploration and tool workflows, with a published 262,144-token native context.
$0.12 / $0.80Apache 2.0
HHermes 4 70B
Creative conversation, roleplay and reasoning with configurable instructions, published by Nous Research.
$0.13 / $0.40Meta Llama Community
MMistral Small 4
An official Mistral model combining text and image input, tool calling and configurable reasoning, with a published 262,144-token window.
$0.15 / $0.60Apache 2.0
QQwen3 32B
A balanced choice for code, multilingual chat and reasoning.
$0.15 / $0.20Apache 2.0
DDolphin Mistral 24B Venice Edition
Conversations and characters with application-controlled instructions, from Dolphin and Venice.
$0.20 / $0.90Apache 2.0
QQwen3 235B A22B
Strong general-purpose instruction following and tool use.
$0.20 / $0.60Apache 2.0
DDeepSeek V3
Code generation, complex instructions and structured tasks.
$0.25 / $0.85MIT
LLlama 3.3 70B
General-purpose assistants, summarization and tool use.
$0.35 / $0.40Llama 3.3 Community
DDeepSeek R1
Difficult reasoning, mathematics and code analysis.
$0.50 / $2.15MIT
MMixtral 8×22B
Multilingual generation and function-calling workflows.
$0.60 / $0.60Apache 2.0
LLlama 3.1 405B
Demanding general-purpose generation and complex instructions.
$1.20 / $1.20Llama 3.1 Community