modelhub.help

Yi-Coder

01.AIOpen-weight

128K context · 9B params · Apache-2.0

01-ai/yi-coder

Yi-Coder is 01.AI's open-source code model series (9B / 1.5B / 34B) with 128K context, strong multilingual code generation, test-case synthesis and bug diagnosis. Served here via SiliconFlow.

Cheapest blended: ¥0.27 / 1M tokens on SiliconFlowGet custom quote

Reachability & verification

Live reachability

Probing…

Target (01.AI): https://api.siliconflow.cn/v1

Live reachability probe

Measured in real time from the ModelHub gateway egress to this model's API endpoint. Green means reachable right now. Overseas reference latencies are estimates; the live probe is the proof of current reachability.

Pricing across providers

1

Prices are shown in each provider's billing currency — ¥ (CNY) for Chinese providers, $ (USD) for overseas gateways.

ProviderInput /1MOutput /1MBlendedCtxp50 latencyAPIVerified
SiliconFlow01-ai/Yi-Coder-9B¥0.2¥0.4¥0.27128K OAI43d ago

Works with

CursorClineAiderContinueOpenCodeOpen WebUI

Any OpenAI-compatible client works — point the base URL at the provider endpoint.

Capabilities

codechat

Languages: en, zh, +50 langs

Code samples

Python
from openai import OpenAI

client = OpenAI(
    base_url="https://api.siliconflow.cn/v1",
    api_key="YOUR_API_KEY",
)

resp = client.chat.completions.create(
    model="01-ai/Yi-Coder-9B",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(resp.choices[0].message.content)
cURL
curl https://api.siliconflow.cn/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "01-ai/Yi-Coder-9B",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Node.js
import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.siliconflow.cn/v1",
  apiKey: "YOUR_API_KEY",
});

const resp = await client.chat.completions.create({
  model: "01-ai/Yi-Coder-9B",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(resp.choices[0].message.content);

Technical specs

Context

128K

Max output

Parameters

9B

Release

2024-09

Training cutoff

License

Apache-2.0

Similar models

Frequently asked questions

How much does Yi-Coder cost?

The cheapest tracked blended price is ¥0.27 per 1M tokens on SiliconFlow. See the pricing matrix above for input/output splits per provider.

Can I use Yi-Coder from outside China?

Availability depends on the hosting provider. Use our Path Planner on the 01.AI page to map a verified official-vs-brokered access path, including payment and KYC constraints.

Is Yi-Coder open source?

Yes — Yi-Coder is open-weight under the Apache-2.0 license. You can self-host it or use any listed inference provider.

Is Yi-Coder OpenAI-compatible?

Yes — at least one tracked provider exposes an OpenAI-compatible endpoint, so Cursor, Cline, Aider and similar clients work with just a base-URL change.

What is the maximum context window?

Yi-Coder supports up to 128K tokens of context with a maximum output of — tokens.

Need verified access to Yi-Coder?

We broker vetted intros to 01.AI — payment, KYC and endpoint verification handled.

Request a brokerage intro