{
"id": "chatcmpl-b6ea00c78f686daa",
"object": "chat.completion",
"created": 1791939594,
"model": "qwen3-coder-30b",
"choices": [
{
"index": 0,
"message": {
"role": "assistant",
"content": "READY",
"refusal": null,
"annotations": null,
"audio": null,
"function_call": null,
"reasoning": null
},
"logprobs": null,
"finish_reason": "stop",
"stop_reason": null,
"token_ids": null,
"routed_experts": null
}
],
"service_tier": null,
"system_fingerprint": "vllm-0.31.0-6fef36b3",
"usage": {
"prompt_tokens": 10,
"total_tokens": 12,
"completion_tokens": 2,
"prompt_tokens_details": null,
"completion_tokens_details": null
},
"prompt_logprobs": null,
"prompt_token_ids": null,
"prompt_text": null,
"kv_transfer_params": null,
"ec_transfer_params": null,
"metrics": null,
"credits": {
"deducted": 6,
"tokens": 12,
"remaining": 5019186
}
}
curl --location --request POST 'https://zylalabs.com/api/14252/openai-compatible+llm+chat+completions+api/35372/create+a+chat+completion' --header 'Authorization: Bearer YOUR_API_KEY'
--data-raw '{"model":"qwen3-coder-30b","messages":[{"role":"user","content":"Say READY"}],"max_tokens":16}'
{
"object": "list",
"data": [
{
"id": "synap-v1",
"object": "model",
"owned_by": "synap",
"nodes": 0,
"routing": "auto — routes inside the models we run on our own GPUs and picks the cheapest that can do the job (tools/code/reasoning), billed at the price of whichever model actually ran"
},
{
"id": "synap-v1-pro",
"object": "model",
"owned_by": "synap",
"nodes": 0,
"routing": "auto — adds the external models we offer to our own: the strongest model per job class (long context, reasoning, multilingual) rather than the cheapest"
},
{
"id": "team-planner",
"object": "model",
"owned_by": "linkrra-team-agent",
"served_by": "deepseek/deepseek-v4-pro",
"nodes": 0,
"pricing": {
"prompt_per_million": 2.2788,
"completion_per_million": 4.0512,
"currency": "USD",
"basis": "brokered"
},
"capability": "Reasoning, deep",
"tier": "premium",
"context_note": "DeepSeek's flagship, for problems that are genuinely hard.",
"secure": true,
"data_policy": "zero-retention (verified live via tools/verify-zdr.js)"
},
{
"id": "team-worker",
"object": "model",
"owned_by": "linkrra-team-agent",
"served_by": "qwen3-coder-30b",
"nodes": 0,
"pricing": {
"prompt_per_million": 0.0675,
"completion_per_million": 0.27,
"currency": "USD",
"basis": "brokered"
},
"capability": "Coding, everyday",
"tier": "standard",
"context_note": "Runs on our own GPUs. Your prompt never leaves our infrastructure.",
"secure": true,
"data_policy": "zero-retention by construction — served on Linkrra-operated fleet hardware; the request is never handed to a third-party inference provider"
},
{
"id": "gpt-oss-20b",
"object": "model",
"owned_by": "pearlpool-fleet",
"nodes": 1,
"pricing": {
"prompt_per_million": 0.017,
"completion_per_million": 0.085,
"currency": "USD",
"basis": "engine"
},
"capability": "Fast + cheap general model",
"tier": "standard",
"context_note": "Runs on our own GPUs. Your prompt never leaves our infrastructure.",
"secure": true,
"data_policy": "zero-retention by construction — served on Linkrra-operated fleet hardware; the request is never handed to a third-party inference provider",
"schema_version": "2.4",
"name": "OpenAI: gpt-oss-20b",
"input_modalities": [
{
"type": "text",
"supported_inputs": {
"max_context_length": {
"value": 32768,
"unit": "token"
}
},
"pricing": [
{
"type": "prompt",
"unit": "token",
"cost_usd": "0.000000017"
}
]
}
],
"output_modalities": [
{
"type": "text",
"max_length": {
"value": 32768,
"unit": "token"
},
"streaming": true,
"supported_parameters": {
"temperature": {
"type": "range",
"min": 0,
"max": 2
},
"top_p": {
"type": "range",
"min": 0,
"max": 1
},
"max_tokens": {
"type": "integer",
"min": 1,
"max": 32768,
"unit": "token"
},
"stop": {
"type": "array",
"max_items": 4
}
},
"pricing": [
{
"type": "completion",
"unit": "token",
"cost_usd": "0.000000085"
}
]
}
],
"is_ready": true,
"is_free": false,
"created": 1791849600,
"datacenters": [
{
"country_code": "KR"
}
]
},
{
"id": "qwen3-coder-30b",
"object": "model",
"owned_by": "pearlpool-fleet",
"nodes": 2,
"pricing": {
"prompt_per_million": 0.0675,
"completion_per_million": 0.27,
"currency": "USD",
"basis": "engine"
},
"capability": "Coding, everyday",
"tier": "standard",
"context_note": "Runs on our own GPUs. Your prompt never leaves our infrastructure.",
"secure": true,
"data_policy": "zero-retention by construction — served on Linkrra-operated fleet hardware; the request is never handed to a third-party inference provider",
"schema_version": "2.4",
"name": "Qwen: Qwen3 Coder 30B A3B Instruct",
"input_modalities": [
{
"type": "text",
"supported_inputs": {
"max_context_length": {
"value": 32768,
"unit": "token"
}
},
"pricing": [
{
"type": "prompt",
"unit": "token",
"cost_usd": "0.0000000675"
}
]
}
],
"output_modalities": [
{
"type": "text",
"max_length": {
"value": 32768,
"unit": "token"
},
"streaming": true,
"supported_parameters": {
"temperature": {
"type": "range",
"min": 0,
"max": 2
},
"top_p": {
"type": "range",
"min": 0,
"max": 1
},
"max_tokens": {
"type": "integer",
"min": 1,
"max": 32768,
"unit": "token"
},
"stop": {
"type": "array",
"max_items": 4
}
},
"pricing": [
{
"type": "completion",
"unit": "token",
"cost_usd": "0.00000027"
}
]
}
],
"is_ready": true,
"is_free": false,
"created": 1790985600,
"datacenters": [
{
"country_code": "KR"
}
]
},
{
"id": "glm-4.7-flash",
"object": "model",
"owned_by": "pearlpool-fleet",
"nodes": 1,
"pricing": {
"prompt_per_million": 0.055,
"completion_per_million": 0.38,
"currency": "USD",
"basis": "engine"
},
"capability": "Fast general model",
"tier": "standard",
"context_note": "Runs on our own GPUs. Your prompt never leaves our infrastructure.",
"secure": true,
"data_policy": "zero-retention by construction — served on Linkrra-operated fleet hardware; the request is never handed to a third-party inference provider",
"schema_version": "2.4",
"name": "Z.AI: GLM 4.7 Flash",
"input_modalities": [
{
"type": "text",
"supported_inputs": {
"max_context_length": {
"value": 6144,
"unit": "token"
}
},
"pricing": [
{
"type": "prompt",
"unit": "token",
"cost_usd": "0.000000055"
}
]
}
],
"output_modalities": [
{
"type": "text",
"max_length": {
"value": 6144,
"unit": "token"
},
"streaming": true
}
]
}
],
"_note": "Response truncated for documentation purposes"
}
curl --location --request GET 'https://zylalabs.com/api/14252/openai-compatible+llm+chat+completions+api/35373/list+available+models' --header 'Authorization: Bearer YOUR_API_KEY'
After signing up, every developer is assigned a personal API access key, a unique combination of letters and digits provided to access to our API endpoint. To authenticate with the OpenAI-Compatible LLM Chat Completions API simply include your bearer token in the Authorization header.
| Header | Description |
|---|---|
Authorization
|
Required
Should be Bearer access_key. See "Your API Access Key" above when you are subscribed.
|
No long-term commitment. Upgrade, downgrade, or cancel anytime. Free Trial includes up to 50 requests.
The POST Create a chat completion endpoint returns a chat completion object, including the model used, generated message content, and usage statistics. The GET List available models endpoint returns a list of models, detailing their IDs, context lengths, and routing information.
Key fields in the chat completion response include "id," "model," "choices" (with message content), and "usage" (detailing token counts). In the models list response, important fields include "id," "owned_by," and "routing."
The chat completion response is structured as a JSON object with nested fields for choices and usage. The models list response is an array of model objects, each containing specific attributes like ID and routing details.
The POST Create a chat completion endpoint accepts parameters such as "model," "messages," and "stream." Users can customize requests by specifying the model ID and providing a sequence of messages for context.
Typical use cases include building chatbots, generating conversational agents, and enhancing customer support systems. The API can be used to create interactive applications that require natural language understanding and generation.
Users can extract the "content" field from the "choices" array to display the generated message. The "usage" field helps track token consumption, which is useful for optimizing requests and managing costs.
Data accuracy is maintained through the use of advanced models trained on diverse datasets. The API operates on Linkrra's hardware, ensuring consistent performance and reliability in generating responses.
If the response contains empty or partial results, users should check the "choices" array for available messages. Implementing error handling can help manage unexpected outputs and ensure a smooth user experience.
To obtain your API key, first sign in to your account and navigate to the API you want to use. From the API's Pricing section, choose a plan and complete the subscription process. Once subscribed, return to the API page and you will see your API Access Key displayed at the top of the documentation page. You can use this key to authenticate your requests.
You can’t switch APIs during the free trial. If you subscribe to a different API, your trial will end and the new subscription will start as a paid plan.
The free trial lasts for 7 days and allows you to make up to 50 API requests.
No, the free trial is available only once, so we recommend using it on the API that interests you the most. Most of our APIs offer a free trial, but some may not include this option.
Yes. If the API offers a free trial, you will see a "Free 7-Day Trial" option in its Pricing section. The trial lasts for 7 days and allows up to 50 API requests, enabling you to evaluate the API before subscribing to a paid plan.
Zyla API Hub is like a big store for APIs, where you can find thousands of them all in one place. We also offer dedicated support and real-time monitoring of all APIs. Once you sign up, you can pick and choose which APIs you want to use. Just remember, each API needs its own subscription. But if you subscribe to multiple ones, you'll use the same key for all of them, making things easier for you.
You can monitor your API usage through the response headers included with every request:
x-zyla-api-calls-monthly-used: Shows the total number of API requests you have used during the current billing period.
x-zyla-api-calls-monthly-remaining: Shows the number of API requests you have remaining for the current billing period.
Yes, you can cancel your subscription at any time. Simply go to the Pricing section of the API you're subscribed to and click the "Unsubscribe" button.
Please note that upgrades, downgrades, and cancellations take effect immediately. Once your subscription is canceled, access to the service will end immediately, regardless of any remaining API calls in your quota.
Please have a look at our Refund Policy: https://zylalabs.com/terms#refund