gpt-5-6-lunaGPT-5.6 Luna by OpenAI: 1.1M context, 64K max output, with Vision, File input, Function calling, Structured output, Streaming, Reasoning, Code execution, Web search. On Hostlinku: Performance starts at 0.1648/1M input · Low-Cost starts at 0.103/1M input.
Hostlinku price · per 1M token
Performance · Best quality & stability
Input
/ 1M token
Output
/ 1M token
Cache read
per 1M token
0.0165
$0.02Cache write (5m)
per 1M token
0.206
$0.25Cache write (1h)
per 1M token
0.206
$0.25Web search
per 1K calls
10.3
$10Tiered pricing (long prompts)
≥272K tokens: 0.3296 in · 1.48 out
Billing in (1 = $1). Strikethrough = vendor list price (only when the price is cheaper). Service Mode is selected per API key.
Get API Key + freeContext window
1.1M
1,050,000 tokens
Max output
64.0K
64,000 tokens
7-day uptime
100.00%
33 requests · 0 failed
Measured throughput
—
Real traffic, last 7 days · output side · 2.23s avg
What this model can do through the Hostlinku gateway.
Vision
Reads images, screenshots, and diagrams alongside text. Send image inputs directly in the messages payload.
Function calling
The model calls tools you define and folds their results into the reply. Required for agentic workflows and multi-step automation.
Reasoning
Spends extra thinking tokens on hard problems before answering. Best for math, code, and multi-step logic.
Prompt caching
Response schema
Guarantees JSON output that matches a schema you provide. No brittle post-parsing on your side.
Streaming
Streams tokens as they are generated for real-time UX. Supported on every Hostlinku protocol.
Web search
Runs server-side web searches and folds the results into the answer. Billed per 1K calls.
Audio
Video
File input
Accepts documents such as PDFs and spreadsheets as context. Great for Q&A over long attachments.
Realtime
Session
Media
Multipart form
Binary response
Hostlinku measures this model from real request traffic: uptime and latency, not self-reported.
100.00%
33 requests in 7 days, 0 failed · automatic failover to backup channels
Latency and uptime are measured from real request traffic over the last 7 days; throughput from user output.
Swap the base URL and everything else stays the same. Native protocols pass through; adapted protocols are translated by the Hostlinku gateway.
curl https://api.hostlinku.com/v1/messages \
-H "x-api-key: $HOSTLINKU_API_KEY" \
-H "anthropic-version: 2023-06-01" \
-H "content-type: application/json" \
-d '{
"model": "gpt-5-6-luna",
"max_tokens": 1024,
"messages": [
{ "role": "user", "content": "Explain edge failover in one paragraph." }
]
}'Every billed dimension, with the vendor list price (struck through when higher) next to the 🪙 price per Service Mode.
| Item | Unit | Original ($) | Performance | Low-Cost |
|---|---|---|---|---|
| Input (prompt) | per 1M tokens | $0.20 | 0.1648 | 0.103 |
| Output (completion) | per 1M tokens | $1.20 | 0.9888 | 0.618 |
| Cache read | per 1M tokens | $0.02 | 0.0165 | 0.0103 |
| Cache write (5m) | per 1M tokens | $0.25 | 0.206 | 0.1288 |
| Cache write (1h) | per 1M tokens | $0.25 | 0.206 | 0.1288 |
| Web search | per 1K calls | $10 | 10.3 | 10.3 |
| Input (prompt)≥272K tokens | per 1M tokens | $0.40 | 0.3296 | 0.206 |
| Output (completion)≥272K tokens | per 1M tokens | $1.80 | 1.48 | 0.927 |
| Cache read≥272K tokens | per 1M tokens | $0.04 | 0.033 | 0.0206 |
| Cache write (5m)≥272K tokens | per 1M tokens | $0.50 | 0.412 | 0.2575 |
| Cache write (1h)≥272K tokens | per 1M tokens | $0.50 | 0.412 | 0.2575 |
Vendor list price is struck through when at least one Service Mode is cheaper. Dimensions without strikethrough (e.g. web search) are not discounted upstream. 1 = $1.
Other models from the same vendor, with prices and context for comparison.
Common questions about GPT-5.6 Luna: pricing, capabilities, and how they are measured.
OpenAI
Integrate GPT-5.6 Luna into your app with clear documentation, official SDKs, and transparent per-token pricing (1 = $1).