OpenAI: GPT-5.6 Luna (batch)
openai/gpt-5-6-luna-batchGPT-5.6 Luna is a fast, cost-efficient model in OpenAI's GPT-5.6 series.
Modalities
In / out per 1M$0.10 / $0.60
Context1M
ReleasedJul 9, 2026
Providers
7 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
 OpenAI | $0.20 | $1.20 | $0.02 | 2.01s | 58 tps | 100% |
 Amazon Bedrockus-east-1 | $0.22 | $1.32 | $0.02 | 1.05s | 75 tps | 100% |
 Azureswedencentral | $0.22 | $1.32 | $0.02 | 1.56s | 111 tps | 100% |
| OpenAI | $0.40 | $2.40 | $0.04 | 2.15s | 122 tps | 100% |
| Azureeastus2 | $0.22 | $1.32 | $0.02 | 3.87s | 51 tps | 99.58% |
| Azure | $0.20 | $1.20 | $0.02 | 5.71s | 58 tps | 99.36% |
| OpenAI | $0.10 | $0.60 | $0.01 | 2.54s | 47 tps | 98.48% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves GPT-5.6 Luna (batch) in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what GPT-5.6 Luna (batch) costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.10
per 1M tokens
Output
$0.60
per 1M tokens
Cache read
$0.01
per 1M cached tokens
Included in every pass
GPT-5.6 Luna (batch) is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s5.0s10.0s15.0s20.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Azure Azure (swedencentral) OpenAI OpenAI OpenAI Amazon Bedrock (us-east-1) Azure (eastus2)
0 tok/s200 tok/s400 tok/s600 tok/s800 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Azure Azure (swedencentral) OpenAI OpenAI OpenAI Amazon Bedrock (us-east-1) Azure (eastus2)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.62%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.22%
100% 92% 83% 75%
Oct 13, 2:40 PMNow
Apps
Tools that most often run GPT-5.6 Luna (batch), by tokens this week.
Activity
25085.3B tokens processed market-wide in the last month.
01000.0B2000.0B3000.0B4000.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for GPT-5.6 Luna (batch)?
openai/gpt-5.6-luna:batch. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does GPT-5.6 Luna (batch) hold?
1,050,000 tokens per request, of which up to 128,000 can be the response.
What can it accept and return?
Input: file, image, text. Output: text.
What does GPT-5.6 Luna (batch) cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.10 per 1M input tokens and $0.60 per 1M output tokens.
How current is its knowledge?
Training data runs to Feb 2026. Anything later has to come from your prompt or a tool call.
Who built GPT-5.6 Luna (batch)?
OpenAI, in the GPT family.
Explore
Other models your pass can call.
