GPT-5.6 Luna Pro
prime/openai/gpt-5.6-luna-pro · family gpt-luna · in: image, text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning image text.
$2.25
Blended $/1M (3:1)
$1
Input $/1M
$6
Output $/1M
$7.00
1M in + 1M out
—
Cache read $/1M
#5933 of 8,504
Cheapest rank
- Provider
- Prime Inference (
prime) - Kind
- text (outputs text)
- Context
- 1,050,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning image text
Same model, other providers
“GPT-5.6 Luna Pro” is offered by 4 providers — cheapest-effective first. Venice AI is the cheapest at $0.45 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Venice AI | $0.2 | $1.2 | $0.45 | 1M |
| OpenRouter | $0.2 | $1.2 | $0.45 | 1.1M |
| AI/ML API | $0.2116 | $1.27 | $0.48 | 1.1M |
| Prime Inference (this) | $1 | $6 | $2.25 | 1.1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Prime Inference 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-5.6-luna-pro","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):