Call gpt-5.6-luna through a single OpenAI-compatible endpoint — one key, no separate vendor account, no multi-provider wiring.
OpenAIChatReasoningCodingVisionPrices are per 1M tokens in USD · ¥6.5 = $1 · Billed in CNY
GPT models remain the reference point for instruction following, tool use and structured output, and the GPT-Image family covers text-to-image generation. Both are available through the same OpenAI-compatible endpoint as every other model on the platform.
At $0.20 per 1M input tokens it sits below the catalogue median of $0.69 — a cost-first choice. Best for coding agents and repository-scale edits. Every model here is reachable with the same API key, so trialling it against a stronger sibling costs one line of code.
from openai import OpenAI
client = OpenAI(
base_url="https://starseaapi.com/v1",
api_key="sk-your-key"
)
r = client.chat.completions.create(
model="gpt-5.6-luna",
messages=[{"role": "user", "content": "Explain prefix caching in one paragraph"}]
)
print(r.choices[0].message.content)| Models | Input $/M | Output $/M | Intelligence index | Coding index |
|---|---|---|---|---|
| gpt-6-luna | $0.10 | $0.50 | — | — |
| gpt-image-2 | $0.09 / req | — | — | — |
| gpt-image-2.5 | $0.09 / req | — | — | — |
| gpt-image-2.5-flare | $0.09 / req | — | — | — |
| gpt-image-2.5-sunburst | $0.09 / req | — | — | — |
| gpt-6-sol | $2.00 | $10.00 | — | — |
| codex-auto-review | $2.50 | $15.00 | — | — |
| gpt-5.5 | $5.00 | $30.00 | — | 74.9 |
| gpt-5.6-sol | $5.00 | $30.00 | 51.3 | 77.4 |
| gpt-6-astra | $10.00 | $50.00 | 54.7 | 76.9 |