Inference

Chat Completions

Send a conversation, get the next message. OpenAI's Chat Completions API: the OpenAI and OpenRouter SDKs call it unchanged. Set stream: true for server-sent events, which end with a usage chunk and data: [DONE].

POST/api/v1/chat/completionsTry it

Your key

Request

curl -X POST https://api.llm.buzz/api/v1/chat/completions \
  -H "Authorization: Bearer $LLM_BUZZ_KEY" \
  -H "Content-Type: application/json" \
  -d '{
  "model": "deepseek/deepseek-v4.1-flash",
  "messages": [
    {
      "role": "user",
      "content": "Say hello in one word."
    }
  ]
}'

import os
from openai import OpenAI

client = OpenAI(base_url="https://api.llm.buzz/api/v1", api_key=os.environ["LLM_BUZZ_KEY"])
reply = client.chat.completions.create(
    model="deepseek/deepseek-v4.1-flash",
    messages=[{"role": "user", "content": "Say hello in one word."}],
)
print(reply.choices[0].message.content)

import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.llm.buzz/api/v1", apiKey: process.env.LLM_BUZZ_KEY });
const reply = await client.chat.completions.create({
  model: "deepseek/deepseek-v4.1-flash",
  messages: [{ role: "user", content: "Say hello in one word." }],
});
console.log(reply.choices[0].message.content);

Response

{
  "id": "chatcmpl-...",
  "object": "chat.completion",
  "model": "deepseek/deepseek-v4.1-flash",
  "provider": "Prime Intellect",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Hello!"
      },
      "finish_reason": "stop",
      "native_finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 3,
    "total_tokens": 15,
    "cost": 0.0000072
  },
  "system_fingerprint": null
}

{
  "error": {
    "code": 400,
    "message": "...",
    "metadata": {
      "error_type": "invalid_request",
      "gateway_code": "invalid_request",
      "param": "messages"
    }
  }
}

{
  "error": {
    "code": 401,
    "message": "A valid gateway Bearer key is required. Send the virtual key as 'Authorization: Bearer <key>'.",
    "metadata": {
      "error_type": "authentication",
      "gateway_code": "invalid_key"
    }
  }
}

{
  "error": {
    "code": 402,
    "message": "...",
    "metadata": {
      "error_type": "payment_required",
      "gateway_code": "insufficient_credits"
    }
  }
}

{
  "error": {
    "code": 404,
    "message": "The requested model does not exist or is not granted to this key. GET /api/v1/models lists the model aliases available to this key.",
    "metadata": {
      "error_type": "not_found",
      "gateway_code": "model_not_found",
      "param": "model"
    }
  }
}

{
  "error": {
    "code": 409,
    "message": "...",
    "metadata": {
      "error_type": "invalid_request",
      "gateway_code": "idempotency_replay_unavailable",
      "param": "Idempotency-Key"
    }
  }
}

{
  "error": {
    "code": 429,
    "message": "...",
    "metadata": {
      "error_type": "rate_limit_exceeded",
      "gateway_code": "unavailable_route"
    }
  }
}

Authorization

An inference key, as Authorization: Bearer KEY.

Keys and limits

Parameters

Idempotency-Keystringheader
A retry with the same key and the same body never runs the request twice: it returns the first answer, or 409 idempotency_replay_unavailable when that answer is not stored where the retry arrived. Send the same key again only when the first call got no answer, or after an answer carrying x-gateway-admission-refused: true; after any other error answer send a new key. A retry without the key, or with a new one, runs and bills the request again. Reusing a key with a different body answers 409 idempotency_conflict.
x-session-idstringheader
Names the conversation, as session_id does, so its turns stay on the provider that holds its cache.

Body application/json

modelstringrequired
A model's name from GET /api/v1/models, such as deepseek/deepseek-v4.1-flash. A suffix changes one request: :floor tries the cheapest provider first and :nitro the fastest. On Chat Completions and Responses :online asks for a web search, which llm.buzz does not run today: the request is served without one and x-sgr-ignored-parameters names web_search->dropped(search_unavailable), or for an organization whose requests llm.buzz keeps in the EU it answers 400 web_search_unavailable_in_region. On Messages :online does nothing and is named as model:online.
messagesobject[]required
The conversation, as OpenAI's message objects: system, user, assistant and tool roles. A user message may carry image_url parts for models that read images, and a text part may carry prompt_cache_breakpoint, OpenAI's explicit cache mark.
streambooleandefault false
Stream the answer as server-sent events.
max_tokensinteger
The most tokens the answer may use. Also bounds what the request holds of your balance while it runs.
temperaturenumber
Sampling temperature. A model that takes none drops it and names it in x-sgr-ignored-parameters.
toolsobject[]
Functions the model can call, in OpenAI's shape. {"type": "openrouter:tool_search"} declares a tool search, and a tool with defer_loading: true beside function waits for it.
tool_choicestring or object
auto, none, required, or an object naming one function.
response_formatobject
{"type": "json_schema", ...} asks for an answer in a JSON schema; {"type": "json_object"} for any JSON object.
reasoningobject
Reasoning controls, translated for each provider.
Show 4 child fields
- effortstring
  How hard the model thinks. An effort the model does not take becomes the nearest one it does, named in x-sgr-ignored-parameters.
- max_tokensinteger
  A reasoning budget in tokens.
- enabledboolean
  Turn reasoning on or off.
- excludeboolean
  Keep the reasoning text out of the answer while the model still reasons.
include_reasoningboolean
OpenRouter's older switch: true is reasoning: {}, false is reasoning: {exclude: true}.
providerobject
Steers one request across the model's providers. With the OpenAI SDK, send it in extra_body. Every field accepts null. A name matches a provider's display name, its tag or the tag's first part, ignoring case: llm.buzz or llm-buzz names llm.buzz's own provider, and llm-buzz/eu only its capacity in the EU.
Show 7 child fields
- orderstring[]
  Try these providers first, in this order, then the others. At most 64 names.
- onlystring[]
  Use only these providers.
- ignorestring[]
  Never use these providers.
- allow_fallbacksboolean
  false stops moving to other providers.
- sortstring
  The order to try providers in. Ignored when order is set.
  
  pricethroughputlatencysmart
- zdrboolean
  true keeps the request on providers that declare 0 days of retention.
- data_collectionstring
  deny keeps the request on providers that declare no training and 0 days of retention.
  
  allowdeny
session_idstring
A name for the conversation, 1 to 256 characters, so its turns stay on the provider that holds its cache.
cache_controlobject
Anthropic's prompt-cache marker, {"type": "ephemeral"} with an optional ttl of "5m" or "1h". llm.buzz passes it on and never adds one. Claude models cache only where a request marks it.
prompt_cache_optionsobject
OpenAI's explicit caching, for GPT-5.6 and later models: mode implicit (OpenAI's default) or explicit (OpenAI writes the cache only at a prompt_cache_breakpoint), and ttl 30m.
prompt_cache_retentionstring
OpenAI's cache retention. 24h with provider.zdr, provider.data_collection: "deny" or your organization's no-retention policy is a 400 invalid_request.

in_memory24h
web_search_optionsobject
Asks for a web search, as the :online suffix does. llm.buzz runs none today: the request is served without a search, nothing is billed for one, and x-sgr-ignored-parameters names it as web_search->dropped(search_unavailable). An organization whose requests llm.buzz keeps in the EU gets 400 web_search_unavailable_in_region instead.

Response 200

The answer. provider names the provider that answered, and usage.cost is the request's cost in US dollars when every part of it is known.

idstring
The completion's ID.
modelstring
The model that answered.
providerstring
The display name of the provider that answered, after any failover: llm.buzz for llm.buzz's own provider.
choicesobject[]
The answer. message.reasoning carries readable reasoning when the model returns it, and message.images the images a model that makes images returns.
usageobject
Token counts; cache reads in prompt_tokens_details.cached_tokens and writes in its cache_write_tokens (cache_write_1h_tokens for the one-hour part, when the provider reports it); and cost in US dollars. Omitted when the provider reported no counts.
x-sgr-ignored-parametersstring[]
Fields llm.buzz dropped instead of failing the request, such as temperature->dropped(unsupported_by_provider).

Errors

400
A field is missing or malformed (invalid_request, with metadata.param), or the model cannot do what the request asks (unsupported_capability).
401
No key, or the key is unknown, expired, revoked or disabled.
402
Your balance is spent and the model is not free, or the request could cost more than your balance.
404
No model has this name, or your key may not call it.
409
The Idempotency-Key was used before. idempotency_replay_unavailable: the first request was accepted, and its answer is not stored where this retry arrived, so it was not run again; retry with the same key after a short backoff first, when the first call got no answer, and send a new key to run the request again (it is billed again) or after an error answer. idempotency_conflict: the key came with a different body; use a new key for each distinct request. Neither runs the request again.
429
Providers are throttling, or the model is at capacity (unavailable_route): retry after Retry-After seconds. Or a free offer's allowance is used (free_allowance_exceeded): your organization's tokens, or your key's requests per minute. Choose a paid model, or for the per-minute limit retry after Retry-After seconds.

Every error code