Baseten Model APIs
$0.01/call
OpenAI-compatible inference API for high-performance LLMs. Drop-in replacement for OpenAI SDK - just change base_url and api_key. **Supported Models:** | Model | Slug | Context | |-------|------|--------| | DeepSeek V3 0324 | `deepseek-ai/DeepSeek-V3-0324` | 164k | | DeepSeek V3.1 | `deepseek-ai/DeepSeek-V3.1` | 164k | | GLM 4.6 (Zhipu) | `zai-org/GLM-4.6` | 200k | | GLM 4.7 (Zhipu) | `zai-org/GLM-4.7` | 200k | | Kimi K2 0905 | `moonshotai/Kimi-K2-Instruct-0905` | 128k | | Kimi K2 Thinking | `moonshotai/Kimi-K2-Thinking` | 262k | | Kimi K2.5 | `moonshotai/Kimi-K2.5` | 262k | | OpenAI GPT OSS 120B | `openai/gpt-oss-120b` | 128k | **Features:** Chat completions, streaming, tool calling, structured outputs, reasoning modes. **Pricing:** ~$0.60/1M tokens (varies by model)
Connect Baseten Model APIs tools
Cursor
Claude Code
Claude Desktop
Windsurf
VS Code
Cline
Roo Code
ChatGPT
Gemini CLI
Amazon Q
Goose
Augment
n8n
API / cURL
AI SDK
TypeScript SDK
{
"mcpServers": {
"baseten": {
"url": "https://baseten.mcp.xpay.sh/mcp?key=YOUR_API_KEY"
}
}
}Or connect all tools
Access all tools (including Baseten Model APIs) through a single MCP connection.
{
"mcpServers": {
"xpay": {
"url": "https://mcp.xpay.sh/mcp?key=YOUR_API_KEY"
}
}
}Agent Discovery
Machine-readable catalogs for LLM agents and automation.
curl https://xpay.tools/llms.txt
curl https://xpay.tools/agents.txt
curl https://xpay.tools/skill.md
Pricing
Pay per tool call. No subscriptions.
1 Baseten Model APIs tool availableFrequently Asked Questions
Baseten Model APIs is an API provider available on xpay with 1 tool. OpenAI-compatible inference API for high-performance LLMs. Drop-in replacement for OpenAI SDK - just change base_url and api_key. **Supported Models:** | Model | Slug | Context | |-------|------|--------| | DeepSeek V3 0324 | `deepseek-ai/DeepSeek-V3-0324` | 164k | | DeepSeek V3.1 | `deepseek-ai/DeepSeek-V3.1` | 164k | | GLM 4.6 (Zhipu) | `zai-org/GLM-4.6` | 200k | | GLM 4.7 (Zhipu) | `zai-org/GLM-4.7` | 200k | | Kimi K2 0905 | `moonshotai/Kimi-K2-Instruct-0905` | 128k | | Kimi K2 Thinking | `moonshotai/Kimi-K2-Thinking` | 262k | | Kimi K2.5 | `moonshotai/Kimi-K2.5` | 262k | | OpenAI GPT OSS 120B | `openai/gpt-oss-120b` | 128k | **Features:** Chat completions, streaming, tool calling, structured outputs, reasoning modes. **Pricing:** ~$0.60/1M tokens (varies by model) All tools are pay-per-call with no monthly fees.
Baseten Model APIs tools are priced at $0.01/call. You only pay when you use a tool — there are no subscriptions or monthly fees. New accounts get $5 in free credits to try any tool.
Add xpay's MCP server to your AI client (Claude Code, Cursor, VS Code, Windsurf, or Cline) with the endpoint: https://mcp.xpay.sh/mcp?key=YOUR_API_KEY. Once connected, use xpay_discover to find Baseten Model APIs tools, then xpay_run to execute them. For Claude Code: claude mcp add --transport http xpay "https://mcp.xpay.sh/mcp?key=YOUR_API_KEY"
Baseten Model APIs provides 1 tool: baseten chat completions. Each tool can be called independently and has its own pricing.
No. With xpay, one API key gives you access to all 1 Baseten Model APIs tools plus 1000+ tools from 80+ other providers. You don't need to sign up for Baseten Model APIs's API directly — xpay handles authentication, billing, and rate limiting.
Yes. Every new xpay account gets $5 in free credits. You can use these credits to try any Baseten Model APIs tool — no credit card required. Sign up at xpay.tools to get started.