Create a Fireworks AI inference endpoint

PUT /_inference/{task_type}/{fireworksai_inference_id}

Auth

Create an inference endpoint to perform an inference task with the fireworksai service.

Required privileges

Cluster privileges manage_inference

Path parameters

task_type enum required: The type of the inference task that the model will perform.; Values: chat_completion completion text_embedding
fireworksai_inference_id string required: The unique identifier of the inference endpoint.

Query parameters

timeout string · default: 30s: Specifies the amount of time to wait for the inference endpoint to be created.

Request body

chunking_settings object: The chunking configuration object. Applies only to the text_embedding task type. Not applicable to the completion or chat_completion task types.; Reference
service enum required: The type of service supported for the specified task type. In this case, fireworksai.; Values: fireworksai
service_settings object required: Settings used to install the inference model. These settings are specific to the fireworksai service.
task_settings object: Settings to configure the inference task. Applies only to the completion or chat_completion task types. Not applicable to the text_embedding task type. These settings are specific to the task type you specified.

Response

application/json

chunking_settings object: The chunking configuration object. Applies only to the embedding, sparse_embedding and text_embedding task types. Not applicable to the rerank, completion, or chat_completion task types.
service string required: The service type
service_settings object required: Settings specific to the service
task_settings object: Task settings specific to the service and task type
inference_id string required: The inference Id
task_type enum required: The task type; Values: chat_completion completion text_embedding

Examples

Request Console 1 / 8 languages

Run PUT _inference/text_embedding/my-fireworks-embeddings to create an inference endpoint that performs a text_embedding task.

Console Kibana Dev Tools

PUT _inference/text_embedding/my-fireworks-embeddings
{
    "service": "fireworksai",
    "service_settings": {
        "api_key": "your-api-key",
        "model_id": "fireworks/qwen3-embedding-8b"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "my-fireworks-embeddings",
  inference_config: {
    service: "fireworksai",
    service_settings: {
      api_key: "your-api-key",
      model_id: "fireworks/qwen3-embedding-8b",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="my-fireworks-embeddings",
    inference_config={
        "service": "fireworksai",
        "service_settings": {
            "api_key": "your-api-key",
            "model_id": "fireworks/qwen3-embedding-8b"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/my-fireworks-embeddings" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "fireworks/qwen3-embedding-8b"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("my-fireworks-embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("fireworksai")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"your-api-key","model_id":"fireworks/qwen3-embedding-8b"}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "my-fireworks-embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "fireworksai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "your-api-key",
              "model_id": "fireworks/qwen3-embedding-8b"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "my-fireworks-embeddings",
    "body" => [
        "service" => "fireworksai",
        "service_settings" => [
            "api_key" => "your-api-key",
            "model_id" => "fireworks/qwen3-embedding-8b",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "my-fireworks-embeddings",
  body: {
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "fireworks/qwen3-embedding-8b"
    }
  }
)

Response

A successful response when creating a Fireworks AI text_embedding inference endpoint.

{
    "inference_id": "my-fireworks-embeddings",
    "task_type": "text_embedding",
    "service": "fireworksai",
    "service_settings": {
        "model_id": "fireworks/qwen3-embedding-8b",
        "url": "https://api.fireworks.ai/inference/v1/embeddings",
        "similarity": "cosine",
        "dimensions": 4096,
        "rate_limit": {
            "requests_per_minute": 6000
        }
    },
    "chunking_settings": {
        "strategy": "sentence",
        "max_chunk_size": 250,
        "sentence_overlap": 1
    }
}

Request Console 1 / 8 languages

Create a Fireworks AI text embedding endpoint with custom dimensions, similarity, and rate limit.

Console Kibana Dev Tools

PUT _inference/text_embedding/my-fireworks-embeddings
{
    "service": "fireworksai",
    "service_settings": {
        "api_key": "your-api-key",
        "model_id": "fireworks/qwen3-embedding-8b",
        "dimensions": 1024,
        "similarity": "cosine",
        "rate_limit": {
            "requests_per_minute": 6000
        }
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "text_embedding",
  inference_id: "my-fireworks-embeddings",
  inference_config: {
    service: "fireworksai",
    service_settings: {
      api_key: "your-api-key",
      model_id: "fireworks/qwen3-embedding-8b",
      dimensions: 1024,
      similarity: "cosine",
      rate_limit: {
        requests_per_minute: 6000,
      },
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="text_embedding",
    inference_id="my-fireworks-embeddings",
    inference_config={
        "service": "fireworksai",
        "service_settings": {
            "api_key": "your-api-key",
            "model_id": "fireworks/qwen3-embedding-8b",
            "dimensions": 1024,
            "similarity": "cosine",
            "rate_limit": {
                "requests_per_minute": 6000
            }
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/text_embedding/my-fireworks-embeddings" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "fireworks/qwen3-embedding-8b",
      "dimensions": 1024,
      "similarity": "cosine",
      "rate_limit": {
        "requests_per_minute": 6000
      }
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("my-fireworks-embeddings")
    .taskType(TaskType.TextEmbedding)
    .inferenceConfig(i -> i
        .service("fireworksai")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"your-api-key","model_id":"fireworks/qwen3-embedding-8b","dimensions":1024,"similarity":"cosine","rate_limit":{"requests_per_minute":6000}}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "my-fireworks-embeddings",
        TaskType = TaskType.TextEmbedding,
        InferenceConfig = new()
        {
            Service = "fireworksai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "your-api-key",
              "model_id": "fireworks/qwen3-embedding-8b",
              "dimensions": 1024,
              "similarity": "cosine",
              "rate_limit": {
                "requests_per_minute": 6000
              }
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "text_embedding",
    "inference_id" => "my-fireworks-embeddings",
    "body" => [
        "service" => "fireworksai",
        "service_settings" => [
            "api_key" => "your-api-key",
            "model_id" => "fireworks/qwen3-embedding-8b",
            "dimensions" => 1024,
            "similarity" => "cosine",
            "rate_limit" => [
                "requests_per_minute" => 6000,
            ],
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "text_embedding",
  inference_id: "my-fireworks-embeddings",
  body: {
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "fireworks/qwen3-embedding-8b",
      "dimensions": 1024,
      "similarity": "cosine",
      "rate_limit": {
        "requests_per_minute": 6000
      }
    }
  }
)

Response

A successful response when creating a Fireworks AI text_embedding inference endpoint.

{
    "inference_id": "my-fireworks-embeddings",
    "task_type": "text_embedding",
    "service": "fireworksai",
    "service_settings": {
        "model_id": "fireworks/qwen3-embedding-8b",
        "url": "https://api.fireworks.ai/inference/v1/embeddings",
        "similarity": "cosine",
        "dimensions": 4096,
        "rate_limit": {
            "requests_per_minute": 6000
        }
    },
    "chunking_settings": {
        "strategy": "sentence",
        "max_chunk_size": 250,
        "sentence_overlap": 1
    }
}

Request Console 1 / 8 languages

Run PUT _inference/chat_completion/my-fireworks-chat to create an inference endpoint that performs a chat_completion task.

Console Kibana Dev Tools

PUT _inference/chat_completion/my-fireworks-chat
{
    "service": "fireworksai",
    "service_settings": {
        "api_key": "your-api-key",
        "model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "chat_completion",
  inference_id: "my-fireworks-chat",
  inference_config: {
    service: "fireworksai",
    service_settings: {
      api_key: "your-api-key",
      model_id: "accounts/fireworks/models/deepseek-v3p1",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="chat_completion",
    inference_id="my-fireworks-chat",
    inference_config={
        "service": "fireworksai",
        "service_settings": {
            "api_key": "your-api-key",
            "model_id": "accounts/fireworks/models/deepseek-v3p1"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/chat_completion/my-fireworks-chat" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("my-fireworks-chat")
    .taskType(TaskType.ChatCompletion)
    .inferenceConfig(i -> i
        .service("fireworksai")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"your-api-key","model_id":"accounts/fireworks/models/deepseek-v3p1"}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "my-fireworks-chat",
        TaskType = TaskType.ChatCompletion,
        InferenceConfig = new()
        {
            Service = "fireworksai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "your-api-key",
              "model_id": "accounts/fireworks/models/deepseek-v3p1"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "chat_completion",
    "inference_id" => "my-fireworks-chat",
    "body" => [
        "service" => "fireworksai",
        "service_settings" => [
            "api_key" => "your-api-key",
            "model_id" => "accounts/fireworks/models/deepseek-v3p1",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "chat_completion",
  inference_id: "my-fireworks-chat",
  body: {
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
  }
)

Response

A successful response when creating a Fireworks AI text_embedding inference endpoint.

{
    "inference_id": "my-fireworks-embeddings",
    "task_type": "text_embedding",
    "service": "fireworksai",
    "service_settings": {
        "model_id": "fireworks/qwen3-embedding-8b",
        "url": "https://api.fireworks.ai/inference/v1/embeddings",
        "similarity": "cosine",
        "dimensions": 4096,
        "rate_limit": {
            "requests_per_minute": 6000
        }
    },
    "chunking_settings": {
        "strategy": "sentence",
        "max_chunk_size": 250,
        "sentence_overlap": 1
    }
}

Request Console 1 / 8 languages

Run PUT _inference/completion/my-fireworks-completion to create an inference endpoint that performs a completion task.

Console Kibana Dev Tools

PUT _inference/completion/my-fireworks-completion
{
    "service": "fireworksai",
    "service_settings": {
        "api_key": "your-api-key",
        "model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
}

JavaScript Elasticsearch JavaScript Client

const response = await client.inference.put({
  task_type: "completion",
  inference_id: "my-fireworks-completion",
  inference_config: {
    service: "fireworksai",
    service_settings: {
      api_key: "your-api-key",
      model_id: "accounts/fireworks/models/deepseek-v3p1",
    },
  },
});

Python Elasticsearch Python Client

resp = client.inference.put(
    task_type="completion",
    inference_id="my-fireworks-completion",
    inference_config={
        "service": "fireworksai",
        "service_settings": {
            "api_key": "your-api-key",
            "model_id": "accounts/fireworks/models/deepseek-v3p1"
        }
    },
)

curl Shell

curl -X PUT "$ELASTICSEARCH_URL/_inference/completion/my-fireworks-completion" \
  -H "Authorization: ApiKey $ELASTIC_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
  }'

Java Elasticsearch Java Client

client.inference().put(p -> p
    .inferenceId("my-fireworks-completion")
    .taskType(TaskType.Completion)
    .inferenceConfig(i -> i
        .service("fireworksai")
        .serviceSettings(JsonData.fromJson("""
{"api_key":"your-api-key","model_id":"accounts/fireworks/models/deepseek-v3p1"}
"""))
    )
);

C# Elasticsearch .NET Client

var response = await client.Inference
    .PutAsync(new PutInferenceRequest()
    {
        InferenceId = "my-fireworks-completion",
        TaskType = TaskType.Completion,
        InferenceConfig = new()
        {
            Service = "fireworksai",
            ServiceSettings = JsonSerializer.Deserialize<JsonElement>("""
            {
              "api_key": "your-api-key",
              "model_id": "accounts/fireworks/models/deepseek-v3p1"
            }
            """)
        }
    });

PHP Elasticsearch PHP Client

$resp = $client->inference()->put([
    "task_type" => "completion",
    "inference_id" => "my-fireworks-completion",
    "body" => [
        "service" => "fireworksai",
        "service_settings" => [
            "api_key" => "your-api-key",
            "model_id" => "accounts/fireworks/models/deepseek-v3p1",
        ],
    ],
]);

Ruby Elasticsearch Ruby Client

response = client.inference.put(
  task_type: "completion",
  inference_id: "my-fireworks-completion",
  body: {
    "service": "fireworksai",
    "service_settings": {
      "api_key": "your-api-key",
      "model_id": "accounts/fireworks/models/deepseek-v3p1"
    }
  }
)

Response

A successful response when creating a Fireworks AI text_embedding inference endpoint.

{
    "inference_id": "my-fireworks-embeddings",
    "task_type": "text_embedding",
    "service": "fireworksai",
    "service_settings": {
        "model_id": "fireworks/qwen3-embedding-8b",
        "url": "https://api.fireworks.ai/inference/v1/embeddings",
        "similarity": "cosine",
        "dimensions": 4096,
        "rate_limit": {
            "requests_per_minute": 6000
        }
    },
    "chunking_settings": {
        "strategy": "sentence",
        "max_chunk_size": 250,
        "sentence_overlap": 1
    }
}