API Documentation

Authenticate with a bearer token in the Authorization header:

Authorization: Bearer sk-sellapi-...

Create keys at /dashboard/keys. Keys are shown only once on creation.

Every user starts on the Free tier with 10,000 credits ($0.10). Free-tier users can call cheap models only (marked FREE on the models page).

Buy any credit pack to auto-upgrade to Pro: unlimited model access, higher rate limits.

POST /v1/chat/completions

OpenAI-compatible. Supports streaming, system messages, multimodal input, and tool calling.

Basic call

curl https://sellapi.dev/v1/chat/completions \
  -H "Authorization: Bearer sk-sellapi-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-4.6",
    "messages": [{ "role": "user", "content": "Hello!" }]
  }'

Streaming

Set stream: true for SSE token streaming:

const stream = await client.chat.completions.create({
  model: 'openai/gpt-5.4',
  messages: [{ role: 'user', content: 'Write a haiku' }],
  stream: true,
})

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? '')
}

Define tools in the OpenAI format. sellapi passes them through to the underlying model — works with all chat models that support function calling (Claude 4.x, GPT-5.x, Gemini 3.x, etc).

Step 1: First call with tools

const result = await client.chat.completions.create({
  model: 'anthropic/claude-sonnet-4.6',
  messages: [
    { role: 'user', content: "What's the weather in Berlin?" },
  ],
  tools: [{
    type: 'function',
    function: {
      name: 'get_weather',
      description: 'Get current weather for a city',
      parameters: {
        type: 'object',
        properties: {
          city: { type: 'string', description: 'City name' },
        },
        required: ['city'],
      },
    },
  }],
  tool_choice: 'auto',  // or 'required', 'none', or specific function
})

const toolCall = result.choices[0].message.tool_calls?.[0]
// { id, function: { name: 'get_weather', arguments: '{"city":"Berlin"}' } }

Step 2: Execute the tool and return result

const args = JSON.parse(toolCall.function.arguments)
const weather = await getWeatherFromYourAPI(args.city)

const followUp = await client.chat.completions.create({
  model: 'anthropic/claude-sonnet-4.6',
  messages: [
    { role: 'user', content: "What's the weather in Berlin?" },
    result.choices[0].message,           // assistant's tool_call
    {
      role: 'tool',
      tool_call_id: toolCall.id,
      content: JSON.stringify(weather),
    },
  ],
})

console.log(followUp.choices[0].message.content)

Each round-trip is a separate billed request. The credits charged appear in the x-sellapi-credits-charged response header.

POST /v1/embeddings

const res = await client.embeddings.create({
  model: 'openai/text-embedding-3-small',
  input: ['Hello world', 'Another text'],
})

console.log(res.data[0].embedding)  // [0.123, -0.456, ...]

Accepts string or string[]. Returns 1 embedding per input.

POST /v1/images/generations

curl https://sellapi.dev/v1/images/generations \
  -H "Authorization: Bearer sk-sellapi-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "google/imagen-4.0-generate-001",
    "prompt": "A sunset over the ocean",
    "n": 1
  }'

Returns { data: [{ b64_json: '...' }] }. Decode base64 to PNG/JPEG bytes.

GET /v1/models

Returns all available models with pricing and tier eligibility. Use this to dynamically populate model dropdowns in your app.

Every successful response includes:

• x-sellapi-credits-charged — credits deducted for this request
• x-sellapi-credits-balance — your remaining balance
• x-ratelimit-limit, x-ratelimit-remaining — rate limit info