Input
- Official OpenAI
- $2
- Here (−50%)
- $1
gpt-5.6-terra
GPT-5.6 Terra API — price per token
GPT-5.6 Terra is the balanced tier of the GPT-5.6 line — below promotional Sol at 50% of its input rate and 60% of its output rate, with the same reasoning-effort controls and full 1.05M-token context.
Pricing per 1M tokens
| Rate | Official OpenAI | Here (−50%) |
|---|---|---|
| Input | $2 | $1 |
| Cached input | $0.2 | $0.1 |
| Cache write | $2.5 | $1.25 |
| Output | $12 | $6 |
Cached input
- Official OpenAI
- $0.2
- Here (−50%)
- $0.1
Cache write
- Official OpenAI
- $2.5
- Here (−50%)
- $1.25
Output
- Official OpenAI
- $12
- Here (−50%)
- $6
Every request is metered at the official rate first, then the flat 50% B2C discount is subtracted before it touches your prepaid balance. Context window: 1.05M tokens. Max output: 128K tokens. Reasoning efforts: none, low, medium, high, xhigh, max.
Best for
- Day-to-day coding and chat below the promotional flagship price.
- Agentic workflows where flagship cost is not justified.
- High-volume production traffic on the OpenAI-compatible API.
Good to know
- Same reasoning-effort range as the flagship, including max.
- Text and image input, text output. SSE streaming on both Responses and Chat Completions.
- Requests above 272K input tokens bill at OpenAI long-context rates: 2× input and 1.5× output on the whole request.
How to use GPT-5.6 Terra
Create a free account, generate one key, and point any OpenAI-compatible tool at https://router.apitoken.sale/v1 with model ID gpt-5.6-terra — Responses and Chat Completions both work, authenticated with Authorization: Bearer. Eligible new accounts include $5 of platform bonus credit — enough to test the model before topping up. Existing integrations on the legacy host https://openai.api.apitoken.sale/v1 keep working.
Frequently asked questions
How much does the GPT-5.6 Terra API cost?
Officially $2 per 1M input tokens and $12 per 1M output tokens, with cached input at $0.20. With the flat 50% apiToken.sale discount that is $1/$6.
Terra or Sol?
Terra is the balanced default for most workloads: during the Sol promotion it is 50% of Sol input and 60% of Sol output. Route only the hardest reasoning to gpt-5.6-sol. Both run on the same key, balance and endpoint.
What is the model ID?
gpt-5.6-terra. Point any OpenAI-compatible client at https://router.apitoken.sale/v1 and send it as the model parameter.
Run GPT-5.6 Terra on the OpenAI-compatible API at a flat 50% off — instant key, prepaid balance, card or crypto.