Skip to content
OpenAI logo

GPT-6.1 Terra

Text Generation • OpenAI

View as MarkdownAgent setup

Model ID

Use with the Workers AI binding, the AI Gateway REST API, or the Unified API.

Calling the provider directly? Use the provider's model name instead, including with provider-native endpoints or the provider's own SDK. For example, Anthropic's name for anthropic/claude-opus-4.8 is claude-opus-4-8.

  • Third-party
  • Zero data retention

GPT-6.1 Terra is OpenAI's fast, efficient model for visual reasoning, precise computer use, and clear, natural writing. Use it to match product photos to catalog entries, interpret technical drawings, act on application screens, or draft and revise text. Tool calling requires the Responses API.

Model Info
Context Window ↗1,050,000 tokens
Terms and Licenselink ↗
More informationlink ↗
Zero data retentionYes
Request formatsResponses, Chat Completions
Pricing
  • Short-context input (per 1M)$1.00
  • Short-context cached input (per 1M)$0.05
  • Short-context cache write (per 1M)$1.25
  • Short-context output (per 1M)$5.00
  • Long-context input (per 1M)$2.00
  • Long-context cached input (per 1M)$0.10
  • Long-context cache write (per 1M)$2.50
  • Long-context output (per 1M)$7.50

Usage

const response = await env.AI.run(
  'openai/gpt-6.1-terra',
  {
    input:
      'Match this product to the best catalog entry: a blue insulated stainless-steel bottle with a screw cap and a 750 ml capacity. Catalog: A: blue plastic sports bottle, 750 ml; B: blue insulated stainless-steel bottle, 750 ml; C: silver insulated stainless-steel bottle, 500 ml. Return the entry letter and one sentence explaining the match.',
    max_output_tokens: 512,
    reasoning: { effort: 'high' },
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/responses \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-6.1-terra",
  "input": "Match this product to the best catalog entry: a blue insulated stainless-steel bottle with a screw cap and a 750 ml capacity. Catalog: A: blue plastic sports bottle, 750 ml; B: blue insulated stainless-steel bottle, 750 ml; C: silver insulated stainless-steel bottle, 500 ml. Return the entry letter and one sentence explaining the match.",
  "max_output_tokens": 512,
  "reasoning": {
    "effort": "high"
  }
}'
**B** — it matches the blue color, insulated stainless-steel construction, and 750 ml capacity.
{
  "id": "resp_0acdd97eb3c98a2b006adf9b32809487d18cea64c95e19ba89",
  "object": "response",
  "created_at": 1793039154,
  "status": "completed",
  "access_programs": {
    "cyber": "standard"
  },
  "background": false,
  "billing": {
    "payer": "developer"
  },
  "completed_at": 1793039155,
  "error": null,
  "frequency_penalty": 0,
  "incomplete_details": null,
  "instructions": null,
  "max_output_tokens": 512,
  "max_tool_calls": null,
  "model": "gpt-6.1-terra",
  "moderation": null,
  "output": [
    {
      "id": "msg_0acdd97eb3c98a2b006adf9b331a5087d1ac4b592c306e418f",
      "type": "message",
      "status": "completed",
      "content": [
        {
          "type": "output_text",
          "annotations": [],
          "logprobs": [],
          "text": "**B** — it matches the blue color, insulated stainless-steel construction, and 750 ml capacity."
        }
      ],
      "phase": "final_answer",
      "role": "assistant"
    }
  ],
  "parallel_tool_calls": true,
  "presence_penalty": 0,
  "previous_response_id": null,
  "prompt_cache_key": null,
  "prompt_cache_retention": "24h",
  "reasoning": {
    "context": "all_turns",
    "effort": "high",
    "mode": "standard",
    "summary": null
  },
  "safety_identifier": null,
  "service_tier": "default",
  "store": true,
  "temperature": 1,
  "text": {
    "format": {
      "type": "text"
    },
    "verbosity": "medium"
  },
  "tool_choice": "auto",
  "tool_usage": {
    "image_gen": {
      "input_tokens": 0,
      "input_tokens_details": {
        "image_tokens": 0,
        "text_tokens": 0
      },
      "output_tokens": 0,
      "output_tokens_details": {
        "image_tokens": 0,
        "text_tokens": 0
      },
      "total_tokens": 0
    },
    "web_search": {
      "num_requests": 0
    }
  },
  "tools": [],
  "top_logprobs": 0,
  "top_p": 0.98,
  "truncation": "disabled",
  "usage": {
    "input_tokens": 83,
    "input_tokens_details": {
      "cache_write_tokens": 0,
      "cached_tokens": 0
    },
    "output_tokens": 26,
    "output_tokens_details": {
      "reasoning_tokens": 0
    },
    "total_tokens": 109
  },
  "user": null,
  "metadata": {}
}

Examples

Clear Writing — Revise customer-facing text through Chat Completions
const response = await env.AI.run(
  'openai/gpt-6.1-terra',
  {
    messages: [
      {
        role: 'user',
        content:
          'Rewrite this delivery update in a clear, friendly tone, keeping it under 40 words: Your shipment has experienced an unforeseen logistical delay. We anticipate dispatch within two business days and will provide tracking information upon fulfillment.',
      },
    ],
    max_completion_tokens: 256,
    reasoning_effort: 'none',
  },
)
console.log(response)
curl https://api.cloudflare.com/client/v4/accounts/$CLOUDFLARE_ACCOUNT_ID/ai/v1/chat/completions \
  --header "Authorization: Bearer $CLOUDFLARE_API_TOKEN" \
  --header "Content-Type: application/json" \
  --data '{
  "model": "openai/gpt-6.1-terra",
  "messages": [
    {
      "role": "user",
      "content": "Rewrite this delivery update in a clear, friendly tone, keeping it under 40 words: Your shipment has experienced an unforeseen logistical delay. We anticipate dispatch within two business days and will provide tracking information upon fulfillment."
    }
  ],
  "max_completion_tokens": 256,
  "reasoning_effort": "none"
}'
Your shipment is slightly delayed, but we expect to dispatch it within two business days. We’ll send you tracking information as soon as it’s on its way.
{
  "id": "resp_0c11f8df88dbcabd006adfa1295b2087d1bc7cabf9e0226961",
  "object": "chat.completion",
  "created": 1793040682,
  "model": "gpt-6.1-terra",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Your shipment is slightly delayed, but we expect to dispatch it within two business days. We’ll send you tracking information as soon as it’s on its way.",
        "refusal": null
      },
      "finish_reason": "stop",
      "logprobs": null
    }
  ],
  "usage": {
    "prompt_tokens": 48,
    "completion_tokens": 36,
    "total_tokens": 84,
    "completion_tokens_details": {
      "reasoning_tokens": 0
    }
  }
}

Parameters

Schema variant
instructions
string
temperature
numberminimum: 0maximum: 2
max_output_tokens
numberexclusiveMinimum: 0
top_p
numberminimum: 0maximum: 1
stream
boolean
tool_choice
id
string
object
stringconst: response
created_at
number
model
string
output_text
string
status
stringenum: in_progress, completed, failed, incomplete

API Schemas (Raw)

Input
Output

Was this helpful?