NewHow we catch a seller listing the wrong model, and refund you if one does.
UberLLM
OpenAI logo

How do I use OpenAI: GPT-6.1 Terra in Claude Code?

openai/gpt-6.1-terra

Claude Code reaches OpenAI: GPT-6.1 Terra through the Anthropic-compatible address of UberLLM. Set ANTHROPIC_BASE_URL to https://api.uberllm.dev (with no /v1 at the end), ANTHROPIC_AUTH_TOKEN to your UberLLM key and ANTHROPIC_MODEL to openai/gpt-6.1-terra[1m], then start claude. Set the opus, sonnet, haiku and subagent model variables to openai/gpt-6.1-terra as well: a slot left unset keeps asking for a Claude model at Claude prices. The [1m] at the end of the id tells Claude Code that OpenAI: GPT-6.1 Terra has a 1M-token context; without it Claude Code plans for 200,000 tokens.

bash
export ANTHROPIC_BASE_URL=https://api.uberllm.dev
export ANTHROPIC_AUTH_TOKEN=ull_your_key
export ANTHROPIC_MODEL='openai/gpt-6.1-terra[1m]'
export ANTHROPIC_DEFAULT_OPUS_MODEL='openai/gpt-6.1-terra'
export ANTHROPIC_DEFAULT_SONNET_MODEL='openai/gpt-6.1-terra'
export ANTHROPIC_DEFAULT_HAIKU_MODEL='openai/gpt-6.1-terra'
export CLAUDE_CODE_SUBAGENT_MODEL='openai/gpt-6.1-terra'
claude

Claude Code calls: Anthropic Messages API https://api.uberllm.dev/v1/messages · Full Claude Code guide

Replace ull_your_key with your UberLLM API key. One key works in every tool and for every model.

By API, OpenAI: GPT-6.1 Terra answers on three addresses with the same UberLLM key and the model id openai/gpt-6.1-terra: OpenAI chat completions at https://api.uberllm.dev/v1/chat/completions, the OpenAI Responses API at https://api.uberllm.dev/v1/responses and the Anthropic Messages API at https://api.uberllm.dev/v1/messages.

How much does the OpenAI: GPT-6.1 Terra API cost?

On November 19, 2026, OpenAI: GPT-6.1 Terra costs $0.099 per million input tokens and $0.4951 per million output tokens through UberLLM, 90.1% below its list price of $1.00 and $5.00. 65 sellers on the market can serve it. In the 7 days before, half of its 4,097 streamed requests got their first token within 2.8 seconds, with a typical prompt of 103,397 tokens. It reads up to 1,050,000 tokens of context. UberLLM adds no fee to these prices, and a request that fails is not billed.

Prices as of 08:00 UTC.

OpenAI: GPT-6.1 Terra in other tools

Other models in Claude Code