TokenOff
Open-Source Models

Chat Completions API

Call open-source models via the Chat Completions API.

Get Your API Key

Go to the API Keys page to create your API key.

API Base URL

https://tokenoff.com/api

Open-source models support the /v1/chat/completions endpoint, compatible with the OpenAI Chat Completions API.

curl

Blocking Call

curl https://tokenoff.com/api/v1/chat/completions \
  -H "Authorization: Bearer your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "deepseek-v4.1-flash",
      "messages": [
          {"role": "user", "content": "Hello"}
      ]
  }'

Output:

{"choices":[{"finish_reason":"stop","index":0,"message":{"content":"Hello! How can I help you today?","reasoning_content":"The user just said \"Hello\". This is aNew conversation start. I should respond warmly and briefly, inviting them to share what they need help with. No need for long response.","role":"assistant"}}],"created":1792046907,"id":"54878169-c5ad-4c6d-834d-92c70218d413","model":"deepseek-v4.1-flash","object":"chat.completion","usage":{"prompt_tokens":31,"completion_tokens":47,"total_tokens":78,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens_details":{"reasoning_tokens":37}}}

Streaming Response

curl https://tokenoff.com/api/v1/chat/completions \
  -H "Authorization: Bearer your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
      "model": "deepseek-v4.1-flash",
      "messages": [
          {"role": "user", "content": "Hello"}
      ],
      "stream": true
  }'

Output:

data: {"choices":[{"index":0,"delta":{"role":"assistant"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"We"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need answer greeting"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":". Need"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" be helpful"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":". \""}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"Hello\" from"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" user. We can respond"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" friendly"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" and"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" ask how"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" can help. No"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" need"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":" tools. Ensure concise"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","reasoning_content":"."}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","content":"Hello"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","content":"!"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","content":" How"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","content":" can"}}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk"}

data: {"choices":[{"index":0,"delta":{"role":"assistant","content":" I help you today?"},"finish_reason":"stop"}],"created":1792046963,"id":"bcea39b6-8aab-4ce6-b8e4-0ac4d83d5bcd","model":"deepseek-v4.1-flash","object":"chat.completion.chunk","usage":{"prompt_tokens":31,"completion_tokens":42,"total_tokens":73,"prompt_tokens_details":{"cached_tokens":0},"completion_tokens_details":{"reasoning_tokens":32}}}

data: [DONE]

Python

pip install openai

Blocking Call

from openai import OpenAI

client = OpenAI(
  api_key="your_api_key_here",
  base_url="https://tokenoff.com/api/v1",
)

response = client.chat.completions.create(
  model="deepseek-v4.1-flash",
  messages=[
      {"role": "user", "content": "Hello"}
  ],
)

print(response.choices[0].message.content)

Output:

Hello! How can I help you today?

Streaming Response

from openai import OpenAI

client = OpenAI(
  api_key="your_api_key_here",
  base_url="https://tokenoff.com/api/v1",
)

response = client.chat.completions.create(
  model="deepseek-v4.1-flash",
  messages=[
      {"role": "user", "content": "Hello"}
  ],
  stream=True,
)

for event in response:
  print(event)

Output:

ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content='We'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content=' need answer simple'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content=' greeting. Need maybe'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content=' say Hello'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content='! How can I'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content=' help you today'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content='? No more'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=None, function_call=None, refusal=None, role='assistant', tool_calls=None, reasoning_content='.'), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content='Hello', function_call=None, refusal=None, role='assistant', tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content='! How can I help you', function_call=None, refusal=None, role='assistant', tool_calls=None), finish_reason=None, index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=None)
ChatCompletionChunk(id='f9523770-4de8-4f08-9f78-8f12dc8f58f9', choices=[Choice(delta=ChoiceDelta(content=' today?', function_call=None, refusal=None, role='assistant', tool_calls=None), finish_reason='stop', index=0, logprobs=None)], created=1792047201, model='deepseek-v4.1-flash', object='chat.completion.chunk', service_tier=None, system_fingerprint=None, usage=CompletionUsage(completion_tokens=31, prompt_tokens=31, total_tokens=62, completion_tokens_details=CompletionTokensDetails(accepted_prediction_tokens=None, audio_tokens=None, reasoning_tokens=21, rejected_prediction_tokens=None), prompt_tokens_details=PromptTokensDetails(audio_tokens=None, cached_tokens=0)))

TypeScript

npm install openai

Blocking Call

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your_api_key_here",
  baseURL: "https://tokenoff.com/api/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [
      { role: "user", content: "Hello" },
  ],
});

console.log(response.choices[0]?.message.content);

Output:

Hello! How can I help you today?

Streaming Response

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "your_api_key_here",
  baseURL: "https://tokenoff.com/api/v1",
});

const response = await client.chat.completions.create({
  model: "deepseek-v4.1-flash",
  messages: [
      { role: "user", content: "Hello" },
  ],
  stream: true,
});

for await (const event of response) {
console.log(event);
}

Output:

{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object] } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk'
}
{
  choices: [ { index: 0, delta: [Object], finish_reason: 'stop' } ],
  created: 1792047343,
  id: 'e572794b-28d3-4f3c-a958-fba2ae2c7ae1',
  model: 'deepseek-v4.1-flash',
  object: 'chat.completion.chunk',
  usage: {
    prompt_tokens: 31,
    completion_tokens: 31,
    total_tokens: 62,
    prompt_tokens_details: { cached_tokens: 0 },
    completion_tokens_details: { reasoning_tokens: 22 }
  }
}

Supported Models

Contact Us

If you encounter any issues while using TokenOff: