GPT-6 Luna
sap-ai-core/gpt-6-luna · family gpt-luna · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
This is a text model — providers price it per unit, not per token, so models.dev carries no token price (fields read “—”). See SAP AI Core’s docs for per-unit rates.
- Provider
- SAP AI Core (
sap-ai-core) - Kind
- text (outputs text)
- Context
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“GPT-6 Luna” is offered by 33 providers — cheapest-effective first. LowRouter is the cheapest at $0.20 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| LowRouter | $0.1 | $0.5 | $0.20 | 1.1M |
| Vercel AI Gateway | $0.1 | $0.5 | $0.20 | 1.1M |
| Perplexity Agent | $0.1 | $0.5 | $0.20 | 1.1M |
| Requesty | $0.1 | $0.5 | $0.20 | 1.1M |
| OpenAI | $0.1 | $0.5 | $0.20 | 1.1M |
| NEAR AI Cloud | $0.1 | $0.5 | $0.20 | 1.1M |
| Vivgrid | $0.1 | $0.5 | $0.20 | 1.1M |
| CommandCode | $0.1 | $0.5 | $0.20 | 1.1M |
| GitHub Copilot | $0.1 | $0.5 | $0.20 | 1.1M |
| 302.AI | $0.1 | $0.5 | $0.20 | 1.1M |
| AIHubMix | $0.1 | $0.5 | $0.20 | 1.1M |
| Prime Inference | $0.1 | $0.5 | $0.20 | 1.1M |
| SAP AI Core (this) | — | — | — | 1.1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at SAP AI Core and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gpt-6-luna","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):