Responses

Create Responses

POST/v1/responses

Creates a model response. Provide text or image inputs to generate text or JSON outputs. Compatible with OpenAI Create Response API

---

Request

Text input Request

curl -X POST https://api.ig1.ai/v1/responses \
  -H "Authorization: Bearer <YOUR_API_KEY>" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen35-397b-a17b-instruct-general",    
    "input": "Write me a nice poem about DevOps."

  }'

Other option

curl -X POST https://api.ig1.ai/v1/responses \
  -H "Authorization: Bearer $IG1AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen35-397b-a17b-instruct-general",
    "input": [
      { "role": "user", "content": "Write me a nice poem about DevOps." }
    ]
  }'

Image input request

curl -X POST https://api.ig1.ai/v1/responses \
  -H "Authorization: Bearer $IG1AI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen35-397b-a17b-instruct-general",
    "input": [
      { 
        "role": "user",
        "content": [
          {"type": "input_text", "text": "Describe this image"},
          {
            "type": "input_image",
            "image_url": "data:image/png;base64,<BASE64_ENCODED_IMAGE_DATA>"
          }
        ]
      }
    ]
  }'

Request body

Parameter	Type	Required	Description
model	string	✅	Model ID (see LLM Models)
input	string or array	✅	String or Array of input objects (role + content)
stream	boolean		Enable streaming (true/false)
temperature	float		Sampling temperature
top_p	float		Nucleus sampling
max_tokens	integer		Maximum tokens to generate

Extra sampling parameters

The following additional sampling parameters are supported:

Parameter	Type	Description
use_beam_search	bool	Enables beam search over sampling.
top_k	int	Limits sampling to top K tokens (1 to Vocabulary_size).
min_p	float	Minimum probability relative to top token (0.0 to 1.0).
repetition_penalty	float	Penalizes repeated tokens (from 1.0).
length_penalty	float	Adjusts sequence length in beam search (from 0.0 to 2.0+).
stop_token_ids	list[int]	Tokens that trigger generation end (e.g., []).
include_stop_str_in_output	bool	Keeps stop strings in final text.
ignore_eos	bool	Forces generation past EOS token.
min_tokens	int	Minimum tokens to generate (0 to max_tokens).
skip_special_tokens	bool	Removes special tokens from output.
spaces_between_special_tokens	bool	Adds spacing between special tokens.
truncate_prompt_tokens	int	Limits prompt length by truncating (from 1 to max_context).
prompt_logprobs	int	Returns logprobs for prompt tokens (e.g., null).
allowed_token_ids	list[int]	Restricts output to specific tokens (typical values: 0 to 5).
bad_words	list[string]	Prohibits specific words in output.

---

Response

Text Response

{
  "background": false,
  "created_at": 1775114826,
  "id": "resp_826146982537",
  "incomplete_details": null,
  "input_messages": null,
  "instructions": null,
  "max_output_tokens": null,
  "max_tool_calls": null,
  "metadata": null,
  "model": "qwen35-397b-a17b-instruct-general",
  "object": "response",
  "output": [
    {
      "content": [
        {
          "annotations": [],
          "logprobs": null,
          "text": "In a meadow bathed in moonlight...",
          "type": "output_text"
        }
      ],
      "id": "msg_826146964620",
      "phase": null,
      "role": "assistant",
      "status": "completed",
      "type": "message"
    }
  ],
  "output_messages": null,
  "output_text": "In a meadow bathed in moonlight,...",
  "parallel_tool_calls": true,
  "previous_response_id": null,
  "prompt": null,
  "reasoning": null,
  "service_tier": "auto",
  "status": "completed",
  "temperature": null,
  "text": null,
  "tool_choice": "auto",
  "tools": [],
  "top_logprobs": null,
  "top_p": null,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 23,
    "input_tokens_details": {
      "cached_tokens": 0,
      "cached_tokens_per_turn": [],
      "input_tokens_per_turn": []
    },
    "output_tokens": 70,
    "output_tokens_details": {
      "output_tokens_per_turn": [],
      "reasoning_tokens": 0,
      "tool_output_tokens": 0,
      "tool_output_tokens_per_turn": []
    },
    "total_tokens": 93
  },
  "user": null
}

Image Response

{
  "id": "resp-beb77eb36e222299",
  "object": "responses",
  "created": 1773745771,
  "model": "qwen35-397b-a17b-instruct-general",
  "output": [
    {
      "type": "message",
      "id": "msg-XXXXXX",
      "role": "assistant"
      "content": {
        "type": "output_text",
        "text": "The image represents a portrait ...",
        "annotations": []
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "input_tokens": 128,
    "input_tokens_details": {
      "cached_tokens": 0
    },
    "output_tokens": 358,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 486
  }
}

---

Unsupported OpenAI endpoints

warning

IG1 AI does not store any chat history or data. That is why following endpoints are not supported:

• Retrieve a Response: GET/v1/responses/{response_id},
• Delete a response: DELETE/v1/responses/{id},
• List input items: GET/v1/responses/{response_id}/input_items
• Count input tokens: POST/v1/responses/input_tokens
• Cancel a response: POST/v1/responses/{id}/cancel
• Compact a response: POST/v1/responses/compact