---
name: "xpay-baseten"
description: "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)"
version: "1.0.0"
provider: "Baseten Model APIs"
tools: 1
---

# Baseten Model APIs

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)

## Baseten Model APIs

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)

### Available Tools

- **baseten_chat_completions**: Create a chat completion using OpenAI-compatible API.

**Supported Models:**
- `deepseek-ai/DeepSeek-V3-0324` - DeepSeek V3 0324 (164k context) 🧠
- `deepseek-ai/DeepSeek-V3.1` - DeepSeek V3.1 (164k context) 🧠
- `zai-org/GLM-4.6` - GLM 4.6 (200k context) 🧠
- `zai-org/GLM-4.7` - GLM 4.7 (200k context) 🧠
- `moonshotai/Kimi-K2-Instruct-0905` - Kimi K2 0905 (128k context)
- `moonshotai/Kimi-K2-Thinking` - Kimi K2 Thinking (262k context) 🧠 always-on
- `moonshotai/Kimi-K2.5` - Kimi K2.5 (262k context)
- `openai/gpt-oss-120b` - OpenAI GPT OSS 120B (128k context)

🧠 = Reasoning model. Use `reasoning_effort` param (low/medium/high) to control thinking depth. Response includes `reasoning_content` field with chain-of-thought.

Supports streaming, tool calling, structured outputs. — $0.01/call

### Quick Start

```json
{
  "mcpServers": {
    "baseten": {
      "url": "https://baseten.mcp.xpay.sh/mcp?key=YOUR_XPAY_KEY"
    }
  }
}
```

### Pricing

Pay per tool call from your XPay wallet. No subscriptions, no minimums.

Get an API key at [xpay.tools](https://xpay.tools).


**Tools:** 1
**Category:** General

## When to Use

Use Baseten Model APIs tools when you need to 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 available through xpay✦'s single MCP connection.

## MCP Connection

```json
{
  "mcpServers": {
    "xpay": {
      "url": "https://mcp.xpay.sh/mcp?key=YOUR_API_KEY"
    }
  }
}
```

For Claude Code:
```bash
claude mcp add --transport http xpay "https://mcp.xpay.sh/mcp?key=YOUR_API_KEY"
```

## Available Tools

- **Baseten Chat Completions** — Create a chat completion using OpenAI-compatible API.

**Supported Models:**
- `deepseek-ai/DeepSeek-V3-0324` - DeepSeek V3 0324 (164k context) 🧠
- `deepseek-ai/DeepSeek-V3.1` - DeepSeek V3.1 (164k context) 🧠
- `zai-org/GLM-4.6` - GLM 4.6 (200k context) 🧠
- `zai-org/GLM-4.7` - GLM 4.7 (200k context) 🧠
- `moonshotai/Kimi-K2-Instruct-0905` - Kimi K2 0905 (128k context)
- `moonshotai/Kimi-K2-Thinking` - Kimi K2 Thinking (262k context) 🧠 always-on
- `moonshotai/Kimi-K2.5` - Kimi K2.5 (262k context)
- `openai/gpt-oss-120b` - OpenAI GPT OSS 120B (128k context)

🧠 = Reasoning model. Use `reasoning_effort` param (low/medium/high) to control thinking depth. Response includes `reasoning_content` field with chain-of-thought.

Supports streaming, tool calling, structured outputs. — $0.01/call — [SKILL.md](https://xpay.tools/skills/baseten/baseten-chat-completions/SKILL.md)

## How to Execute

1. **`xpay_discover`** — Search for tools: `xpay_discover("baseten")`
2. **`xpay_details`** — Get input schema: `xpay_details("baseten/TOOL_NAME")`
3. **`xpay_run`** — Execute: `xpay_run("baseten/TOOL_NAME", { ...inputs })`
4. **`xpay_balance`** — Check credits

## Links

- Provider page: https://xpay.tools/baseten/
- All providers: https://xpay.tools/explore
- Docs: https://docs.xpay.sh