Short answer
TeamoRouter hasn't launched GPT-6.1 Terra Pro yet. With a TeamoRouter key you can use these today:
gpt-6.1-terra: the same underlying model, in standard mode (model page).gpt-6.1-sol: the tier above Terra, for complex coding and long agent work.gpt-6-astra: OpenAI's highest-intelligence GPT-6 model, for the hardest tasks.
To follow its launch on TeamoRouter, or vote for it, see the GPT-6.1 Terra Pro API page.
GPT-6.1 Terra Pro is not a separate model. OpenRouter has listed it as openai/gpt-6.1-terra-pro since October 26, 2026, and describes it as GPT-6.1 Terra served with reasoning.mode set to pro. OpenAI's own model catalog has no separate Terra Pro entry. Its reasoning guide says GPT-5.6 and GPT-6 models support a standard and a pro reasoning mode in the Responses API, and that pro mode does more model work on difficult tasks and bills those tokens at the model's standard rates. For Terra that is $1 per million input tokens and $5 per million output tokens; a pro answer simply uses more tokens.
New accounts start with a $0 balance — top up before your first request. Top up from $5. If a request returns 402 (400 on the OpenAI format) with "wallet balance is insufficient", your balance is empty — your base URL and key are fine. Top up and retry.
Terra Pro vs Terra
| GPT-6.1 Terra | GPT-6.1 Terra Pro | |
|---|---|---|
| What it is | OpenAI model gpt-6.1-terra |
The same model with "reasoning": {"mode": "pro"} |
| API | Responses and Chat Completions (tool calling needs Responses) | Pro mode is documented for the Responses API |
| Price per 1M tokens (input / output) | $1 / $5 | The same rates, more tokens per answer |
| Speed | Fast | Slower: more model work per answer |
| Context window / max output | 1,050,000 / 128,000 | OpenRouter lists the same |
| On TeamoRouter | Yes, gpt-6.1-terra |
Not yet |
Reasoning mode and reasoning effort are separate settings. Mode picks standard or pro execution; reasoning.effort controls how much reasoning the model applies within that mode. For Terra, effort can be none, low, medium (the default), high, xhigh or max. OpenAI's guide recommends pro mode for difficult tasks that can tolerate higher latency and token usage.
Price
From OpenAI's GPT-6.1 Terra model page, per million tokens:
| Standard | Prompts over 272K input tokens | |
|---|---|---|
| Input | $1.00 | $2.00 |
| Cached input | $0.05 | $0.10 |
| Cache write (30-minute retention) | $1.25 | $2.50 |
| Output | $5.00 | $7.50 |
Pro mode uses the same rates. OpenRouter's Terra Pro listing shows the same $1 / $5 and notes that pro mode spends far more tokens, so the same question costs more in pro mode than in standard mode.
TeamoRouter bills per token with no subscription. Current prices for gpt-6.1-terra, gpt-6.1-sol and gpt-6-astra are on the pricing page.
Use GPT-6.1 Terra on TeamoRouter now
Codex CLI (0.159.0 or later). Put this in ~/.codex/config.toml and set your TeamoRouter key in OPENAI_API_KEY:
model_provider = "teamorouter"
model = "gpt-6.1-terra"
[model_providers.teamorouter]
name = "TeamoRouter"
base_url = "https://api.teamorouter.com/v1"
env_key = "OPENAI_API_KEY"
wire_api = "responses"
For a harder task, start a session with codex -m gpt-6.1-sol or codex -m gpt-6-astra. Full setup: Codex CLI guide.
Responses API:
curl https://api.teamorouter.com/v1/responses \
-H "Authorization: Bearer YOUR_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6.1-terra",
"reasoning": {"effort": "high"},
"input": "Review this database migration plan and list the likely failure modes: ..."
}'
We sent both requests to the TeamoRouter gateway on November 2, 2026 with Codex CLI 0.166.0 and curl. For more on Terra itself, including OpenCode setup and image input, see GPT-6.1 Terra API.
Paying for usage
No subscription: you top up a balance from $5 and pay only for the tokens you use, by card or with USDT, USDC or ETH from any exchange app or wallet (how to pay with USDT). The same key works for Claude, Gemini and DeepSeek.
FAQ
Is GPT-6.1 Terra Pro a different model from GPT-6.1 Terra?
No. It is GPT-6.1 Terra with the pro reasoning mode turned on. OpenRouter gives that combination its own ID, openai/gpt-6.1-terra-pro; on OpenAI's API it is a request parameter, not a separate model ID.
Is Terra Pro more expensive?
The price per token is the same: $1 input and $5 output per million at OpenAI's standard rate. Pro mode does more work per answer, so it uses more tokens and each request costs more.
Can I use GPT-6.1 Terra Pro on TeamoRouter?
Not yet. gpt-6.1-terra (standard mode), gpt-6.1-sol and gpt-6-astra are available now. The models that are live are listed on the models page.
Terra Pro or GPT-6.1 Sol?
OpenAI positions Sol for complex coding and long-running agent work and Terra for visual understanding, computer use and writing. If a task is hard coding, try gpt-6.1-sol before reaching for more reasoning on Terra.
Related
- GPT-6.1 Terra API: specs, price, Codex and OpenCode setup
- GPT-6.1 Sol API: the tier above Terra
- Codex CLI guide