GPT-6.1 Terra API Pricing and Day 0 Support on LiteLLM

LiteLLM now supports GPT-6.1 Terra on Day 0. Use it through the LiteLLM AI Gateway with the same config as every other OpenAI model. Spend, rate limits and logs are in one place.

GPT-6.1 Terra pricing​

• Input: $1.00 / MTok, or $2.00 / MTok above 272K input tokens
• Output: $5.00 / MTok, or $7.50 / MTok above 272K input tokens
• Cache read: $0.05 / MTok, or $0.10 / MTok above 272K input tokens
• Batch and Flex: 50% off. Fast mode costs 2x.

Per OpenAI, these prices are 50% lower than the prices of GPT-5.6 Terra and GPT-6.1 Sol.

Prices on every provider: https://models.litellm.ai/models

What's new in GPT-6.1 Terra​

• 50.3% on Terminal-Bench 4.0 at max effort, more than double GPT-5.6 Terra's 21.5%, per OpenAI
• Fewer factual errors: on OpenAI's error-inducing prompts at low effort, the error rate fell from 53.6% to 16.7%
• Reasoning effort from none to max, with medium as the default
• 1.05M-token context window (922K input) and up to 128K output tokens

Use GPT-6.1 Terra with LiteLLM​

No upgrade needed: open Price Data under Models + Endpoints in the UI and click Reload Price Data (or POST /reload/model_cost_map), on v1.76.0 and above.

model_list:
  - model_name: gpt-6.1-terra
    litellm_params:
      model: openai/gpt-6.1-terra
      api_key: os.environ/OPENAI_API_KEY

docker run -d \
  -p 4000:4000 \
  -e OPENAI_API_KEY=$OPENAI_API_KEY \
  -v $(pwd)/config.yaml:/app/config.yaml \
  ghcr.io/berriai/litellm:v1.106.2 \
  --config /app/config.yaml

curl -X POST "http://0.0.0.0:4000/chat/completions" \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $LITELLM_KEY" \
  -d '{
    "model": "gpt-6.1-terra",
    "messages": [
      {"role": "user", "content": "Read this invoice and list the line items."}
    ],
    "reasoning_effort": "low"
  }'

from litellm import completion

response = completion(
    model="openai/gpt-6.1-terra",
    messages=[
        {"role": "user", "content": "Read this invoice and list the line items."}
    ],
    reasoning_effort="low",
)

print(response.choices[0].message.content)

OpenAI serves tool calling for this model through the Responses API. When reasoning is on, LiteLLM sends a /chat/completions request with tools to /v1/responses for you.

FAQ​

How much does GPT-6.1 Terra cost?​

$1.00 per 1M input tokens and $5.00 per 1M output tokens. Cache reads cost $0.05 per 1M tokens. Above 272K input tokens, the prices are $2.00, $7.50 and $0.10.

What is the context window of GPT-6.1 Terra?​

1,050,000 tokens, with up to 922,000 input tokens and 128,000 output tokens.

How do I call GPT-6.1 Terra with an OpenAI-compatible API?​

Add openai/gpt-6.1-terra to your LiteLLM config. Then send a standard /chat/completions request to the proxy with "model": "gpt-6.1-terra".

Feedback​

Questions and feedback go in GitHub discussion #48443.

References​

• LiteLLM pricing for gpt-6.1-terra: PR #48429