GPT-5.6 Luna
perplexity-agent/openai/gpt-5.6-luna · family gpt-luna · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$0.45
Blended $/1M (3:1)
$0.2
Input $/1M
$1.2
Output $/1M
$1.40
1M in + 1M out
$0.02 −90%
Cache read $/1M
#3008 of 8,750
Cheapest rank
- Provider
- Perplexity Agent (
perplexity-agent) - 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-5.6 Luna” is offered by 42 providers — cheapest-effective first. Kenari is the cheapest at $0.44 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Kenari | $0.2 | $1.14 | $0.44 | 1.1M |
| Perplexity Agent (this) | $0.2 | $1.2 | $0.45 | 1.1M |
| Ofox | $0.2 | $1.2 | $0.45 | 1.1M |
| Abacus | $0.2 | $1.2 | $0.45 | 1M |
| Venice AI | $0.2 | $1.2 | $0.45 | 1M |
| Opper | $0.2 | $1.2 | $0.45 | 1M |
| AIHubMix | $0.2 | $1.2 | $0.45 | 1.1M |
| Snowflake Cortex | $0.2 | $1.2 | $0.45 | 1.1M |
| Azure Cognitive Services | $0.2 | $1.2 | $0.45 | 1.1M |
| GitHub Copilot | $0.2 | $1.2 | $0.45 | 1.1M |
| Boundless | $0.2 | $1.2 | $0.45 | 262k |
| NEAR AI Cloud | $0.2 | $1.2 | $0.45 | 1.1M |
| Kilo Gateway | $0.2 | $1.2 | $0.45 | 1.1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Perplexity Agent 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):