GPT-6 Luna
standardcompute/openai/gpt-6-luna · family gpt-luna · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$0.20
Blended $/1M (3:1)
$0.1
Input $/1M
$0.5
Output $/1M
$0.60
1M in + 1M out
$0.01 −90%
Cache read $/1M
#1850 of 8,543
Cheapest rank
- Provider
- Standard Compute (
standardcompute) - Kind
- text (outputs text)
- Context
- 1,050,000 tokens
- Max output
- 50,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“GPT-6 Luna” is offered by 31 providers — cheapest-effective first. This one (Standard Compute) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Standard Compute (this) | $0.1 | $0.5 | $0.20 | 1.1M |
| NEAR AI Cloud | $0.1 | $0.5 | $0.20 | 1.1M |
| Kilo Gateway | $0.1 | $0.5 | $0.20 | 1.1M |
| Venice AI | $0.1 | $0.5 | $0.20 | 1.1M |
| CommandCode | $0.1 | $0.5 | $0.20 | 1.1M |
| LowRouter | $0.1 | $0.5 | $0.20 | 1.1M |
| 302.AI | $0.1 | $0.5 | $0.20 | 1.1M |
| OpenRouter | $0.1 | $0.5 | $0.20 | 1.1M |
| Azure | $0.1 | $0.5 | $0.20 | 1.1M |
| Azure Cognitive Services | $0.1 | $0.5 | $0.20 | 1.1M |
| Cloudflare AI Gateway | $0.1 | $0.5 | $0.20 | 1.1M |
| Vercel AI Gateway | $0.1 | $0.5 | $0.20 | 1.1M |
| Ofox | $0.1 | $0.5 | $0.20 | 1.1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Standard Compute and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"openai/gpt-6-luna","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):