Skip to main content
POST
https://api.firmware.ai
/
v1
/
chat
/
completions
Chat completions
curl --request POST \
  --url https://api.firmware.ai/v1/chat/completions \
  --header 'Content-Type: application/json' \
  --data '
{
  "model": "<string>",
  "messages": [
    {}
  ],
  "stream": true,
  "temperature": 123,
  "max_tokens": 123,
  "tools": [
    {}
  ],
  "tool_choice": {},
  "mcp_servers": [
    {}
  ],
  "thinking": {},
  "reasoning_effort": "<string>",
  "generation_config": {},
  "safety_settings": [
    {}
  ]
}
'
{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 8,
    "total_tokens": 20
  }
}
Create a chat completion. Supports streaming, tool calling, and MCP server integration across all providers.

​
Request body

​
model
string
required
Model ID to use for completion. See available models for the full list.
​
messages
array
required
Conversation history as an array of message objects.
[
  { "role": "system", "content": "You are a helpful assistant." },
  { "role": "user", "content": "Hello!" }
]
​
stream
boolean
default:"false"
Enable Server-Sent Events streaming for the response.
​
temperature
number
Sampling temperature between 0 and 2. Higher values make output more random.
​
max_tokens
integer
Maximum tokens to generate in the completion.
​
tools
array
List of tools the model may call. Supports OpenAI function tools.
[
  {
    "type": "function",
    "function": {
      "name": "get_weather",
      "description": "Get current weather for a location",
      "parameters": {
        "type": "object",
        "properties": {
          "location": { "type": "string" }
        },
        "required": ["location"]
      }
    }
  }
]
​
tool_choice
string | object
Controls tool calling. Options: auto, none, required, or a specific tool.
​
mcp_servers
array
MCP server addresses for server-side tool execution.
["dedalus-labs/brave-search", "dedalus-labs/github-api"]
​
thinking
object
Extended thinking configuration for Anthropic models.
{ "type": "enabled", "budget_tokens": 2048 }
​
reasoning_effort
string
Constrains effort on reasoning for supported reasoning models. Higher values use more compute, improving quality at the cost of latency and tokens.Options: low, medium, high
"medium"
​
generation_config
object
Google generationConfig object. Merged with auto-generated config. Use for Google-specific params like candidateCount or responseMimeType.
{
  "candidateCount": 2,
  "responseMimeType": "application/json"
}
​
safety_settings
array
Google safety settings for harm categories and thresholds.
[
  {
    "category": "HARM_CATEGORY_HARASSMENT",
    "threshold": "BLOCK_NONE"
  }
]

​
Response

​
id
string
Unique identifier for the completion.
​
object
string
Always chat.completion.
​
created
integer
Unix timestamp of when the completion was created.
​
model
string
The model used for the completion.
​
choices
array
Array of completion choices.
​
usage
object
Token usage statistics.
​
tools_executed
array
List of MCP tools executed server-side, if any.

​
Examples

curl https://api.firmware.ai/v1/chat/completions \
  -H "Authorization: Bearer $FIRMWARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "gpt-4o",
    "messages": [
      {"role": "user", "content": "What is the capital of France?"}
    ]
  }'

{
  "id": "chatcmpl-123",
  "object": "chat.completion",
  "created": 1677652288,
  "model": "gpt-4o",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The capital of France is Paris."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 12,
    "completion_tokens": 8,
    "total_tokens": 20
  }
}