GPT-5.6 Sol, Terra & Luna Now Available
OpenAI's new GPT-5.6 family is live on LLM Gateway from day one: Sol for frontier reasoning at $5/$30 per 1M tokens, Terra balancing intelligence and cost at $2.50/$15, and Luna for high-volume workloads at $1/$6 — all with a 1.05M-token context window, reasoning, vision, tool calling, and web search.
Picking an OpenAI model used to mean trading capability against cost across scattered version numbers. The new GPT-5.6 family makes the trade-off explicit — three models, one lineup — and all three are available on LLM Gateway today, the day OpenAI released them.
Three Models, One Family
| Model | Best for | Input / 1M | Cached input / 1M | Output / 1M |
|---|---|---|---|---|
gpt-5.6-sol | Frontier reasoning and complex professional work | $5.00 | $0.50 | $30.00 |
gpt-5.6-terra | Balanced intelligence and cost | $2.50 | $0.25 | $15.00 |
gpt-5.6-luna | High-volume tasks like classification and extraction | $1.00 | $0.10 | $6.00 |
Every model in the family shares the same capabilities:
- Context window: 1,050,000 tokens, with 128,000 max output tokens
- Knowledge cutoff: February 16, 2026
- Reasoning, vision, tool calling, web search, and structured outputs
- Flex (50% cheaper) and Priority (2x, low-latency) service tiers
Getting Started
All three models work through the unified API right now:
1curl -X POST https://api.llmgateway.io/v1/chat/completions \2 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "openai/gpt-5.6-sol",6 "messages": [{"role": "user", "content": "Hello GPT-5.6!"}]7 }'1curl -X POST https://api.llmgateway.io/v1/chat/completions \2 -H "Authorization: Bearer $LLM_GATEWAY_API_KEY" \3 -H "Content-Type: application/json" \4 -d '{5 "model": "openai/gpt-5.6-sol",6 "messages": [{"role": "user", "content": "Hello GPT-5.6!"}]7 }'Swap gpt-5.6-sol for gpt-5.6-terra or gpt-5.6-luna to move down the cost curve without touching anything else in your integration. Available on all plans.