Welcome

Open models behind OpenAI-compatible and ElevenLabs-compatible endpoints. Change the base URL. Keep your code.

Open models, served behind the APIs you already use. The official openai and elevenlabs SDKs work with one change: the base URL.

Quickstart

First chat completion with the OpenAI SDK in under a minute.

Voice

Text to speech, streaming, speech to text, cloning, and speech to speech. OpenAI and ElevenLabs shapes.

Real-time

Chat completions, completions, responses, and embeddings.

Realtime over WebSocket

Voice agents: the OpenAI Realtime API. Speech in, spoken answer out, one WebSocket.

Batch

OpenAI Files and Batches. 24h window or the Flex tier.

API Reference

Every route with request and response schemas.

One line to switch

Point the SDK at https://api.mserve.ai/openai/v1 and use an ms_ key. Everything else stays the same. https://api.mserve.ai/v1 works too.

from openai import OpenAI

client = OpenAI(base_url="https://api.mserve.ai/openai/v1", api_key="ms_your_key")

response = client.chat.completions.create(
    model="qwen3.8-27b",
    messages=[{"role": "user", "content": "Write one sentence about GPUs."}],
)
print(response.choices[0].message.content)

The same applies to voice with the ElevenLabs SDK at https://api.mserve.ai/elevenlabs:

from elevenlabs.client import ElevenLabs

client = ElevenLabs(base_url="https://api.mserve.ai/elevenlabs", api_key="ms_your_key")
audio = b"".join(client.text_to_speech.convert(voice_id="21m00Tcm4TlvDq8ikWAM", text="Every model. One API."))

Let your agent make the switch

Paste this into Claude Code, Cursor, Codex, or any coding agent with access to your repo. It reads these docs as Markdown and makes the change.

Prompt for your coding agent

Switch this codebase from OpenAI and ElevenLabs to mserve.ai. Keep the official SDKs.

1. Read https://docs.mserve.ai/llms.txt. For any page you need, append .md to its URL to get Markdown.
2. OpenAI SDK clients: set base_url to https://api.mserve.ai/openai/v1 and read the key from MSERVE_API_KEY.
   Model ids: chat and completions qwen3.8-27b, embeddings qwen3-embedding-0.6b, transcription whisper-large-v3, speech kokoro-82m. Full list: https://docs.mserve.ai/docs/pricing.md
3. ElevenLabs SDK clients: set base_url to https://api.mserve.ai/elevenlabs and read the key from MSERVE_API_KEY. Voice ids and model ids keep working.
4. Remove parameters listed as rejected in https://docs.mserve.ai/docs/resources/compatibility.md.
5. Run the test suite. Show me the diff before you commit.

Products

Product	Works with	Docs
Text to speech	OpenAI `audio.speech`, ElevenLabs `text_to_speech` incl. timestamps and WebSocket `stream-input`	Voice
Speech to text	OpenAI `audio.transcriptions` and `audio.translations`, ElevenLabs `speech_to_text`	Speech to Text
Voice cloning	ElevenLabs `voices.add`, edit, delete, samples	Custom Voices
Speech to speech	ElevenLabs `speech_to_speech` with preset or cloned targets	Speech to Speech
LLM	OpenAI chat completions, completions, responses, embeddings	Real-time
Realtime voice agents	OpenAI Realtime API over WebSocket	Realtime over WebSocket
Batch	OpenAI files and batches, 24h and Flex tiers	Batch
Keys, limits, billing	`GET /mserve/v1/key`, per-key limits, card top-ups	Authentication, Billing

Usage is billed per request against a prepaid balance. The API Reference lists every route with its request and response schema.

Prices

Full tables on Pricing.

Model	Model id	Input per 1M tokens	Output per 1M tokens
Qwen3.8 27B	`qwen3.8-27b`	$0.30	$2.50