Trying Out GPT-6 Sol/Luna, Now Available on Amazon Bedrock
This page has been translated by machine translation. View original
Introduction
On September 22, 2026 (UTC), OpenAI announced GPT-6 Sol/Luna, and they became available on Amazon Bedrock the same day.
In this article, I call Sol and Luna from Bedrock in three ways (Converse, the Responses API, and Chat Completions) and check the model IDs, how to invoke them, and the pricing.
Overview of the GPT-6 Family
Sol and Luna join GPT-6 Astra, completing the lineup of three models.
| Model | Positioning | Main use cases |
|---|---|---|
| Astra | Flagship | Complex tasks requiring the highest quality |
| Sol | Everyday model | Complex coding, agent workflows, data analysis |
| Luna | High-efficiency model | High-volume summarization, extraction, classification, routing |
Luna lets you adjust the reasoning effort, so you can balance quality, speed, and cost on a per-request basis.
GPT-6 Sol/Luna Model List
You can confirm the two models, Sol and Luna, with list-foundation-models.
aws bedrock list-foundation-models \
--region us-east-1 \
--by-provider OpenAI
The Sol and Luna entries were as follows.
{
"modelArn": "arn:aws:bedrock:us-east-1::foundation-model/openai.gpt-6-sol",
"modelId": "openai.gpt-6-sol",
"modelName": "GPT-6 Sol",
"providerName": "OpenAI",
"inputModalities": ["TEXT", "IMAGE"],
"outputModalities": ["TEXT"],
"responseStreamingSupported": true,
"inferenceTypesSupported": ["INFERENCE_PROFILE"],
"modelLifecycle": {
"status": "ACTIVE",
"startOfLifeTime": "2026-09-22T17:00:00+00:00"
}
},
{
"modelArn": "arn:aws:bedrock:us-east-1::foundation-model/openai.gpt-6-luna",
"modelId": "openai.gpt-6-luna",
"modelName": "GPT-6 Luna",
"providerName": "OpenAI",
"inputModalities": ["TEXT", "IMAGE"],
"outputModalities": ["TEXT"],
"responseStreamingSupported": true,
"inferenceTypesSupported": ["INFERENCE_PROFILE"],
"modelLifecycle": {
"status": "ACTIVE",
"startOfLifeTime": "2026-09-22T17:00:00+00:00"
}
}
Because inferenceTypesSupported is only INFERENCE_PROFILE, you use an inference profile ID rather than the model ID for invocation. In this article, I verified with the Global inference profiles (global.openai.gpt-6-sol / global.openai.gpt-6-luna).
Calling from Converse
aws bedrock-runtime converse \
--region us-east-1 \
--model-id global.openai.gpt-6-sol \
--messages '[{"role":"user","content":[{"text":"Say ok"}]}]'
{
"output": {
"message": {
"role": "assistant",
"content": [{"text": "ok"}]
}
},
"stopReason": "end_turn",
"usage": {
"inputTokens": 8,
"outputTokens": 5,
"totalTokens": 13,
"cacheReadInputTokens": 0,
"cacheWriteInputTokens": 0
},
"metrics": {"latencyMs": 540}
}
When I swapped --model-id for global.openai.gpt-6-luna, Luna responded in the same format (I only verified a single text invocation).
Calling via the OpenAI-Compatible Path
You can use the OpenAI-compatible API under /openai/v1/ on the bedrock-runtime endpoint.
I called the Responses API with Sol. Temporary credentials are used for SigV4 authentication. --aws-sigv4 requires curl 7.75 or later.
cat gpt6-sol-responses-body.json
# {"model":"global.openai.gpt-6-sol","input":"Say ok","store":false}
curl --silent --show-error \
--aws-sigv4 'aws:amz:us-east-1:bedrock' \
--user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
-H "x-amz-security-token: $AWS_SESSION_TOKEN" \
-H 'Content-Type: application/json' \
--data-binary @gpt6-sol-responses-body.json \
-w '\nHTTP %{http_code}\n' \
https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1/responses
HTTP 200 was returned, the status in the response body was completed, and model was global.openai.gpt-6-sol.
I called Chat Completions with Luna.
curl --silent --show-error \
--aws-sigv4 'aws:amz:us-east-1:bedrock' \
--user "$AWS_ACCESS_KEY_ID:$AWS_SECRET_ACCESS_KEY" \
-H "x-amz-security-token: $AWS_SESSION_TOKEN" \
-H 'Content-Type: application/json' \
-d '{"model":"global.openai.gpt-6-luna","messages":[{"role":"user","content":"Say ok"}],"max_completion_tokens":16}' \
-w '\nHTTP %{http_code}\n' \
https://bedrock-runtime.us-east-1.amazonaws.com/openai/v1/chat/completions
HTTP 200 was returned, finish_reason was stop, and model was global.openai.gpt-6-luna.
Pricing
These are OpenAI's direct-sale prices (as of 2026-09-22, from OpenAI's announcement).
| Model | Input (/1M tokens) | Output (/1M tokens) |
|---|---|---|
| GPT-6 Sol | $2.00 | $10.00 |
| GPT-6 Luna | $0.10 | $0.50 |
These are lower than the equivalent models in the GPT-5.6 series.
At the time of writing, I could not confirm the prices for GPT-6 Sol/Luna on the Bedrock pricing page. When going through a Global inference profile, OpenAI's prices are expected to apply (for GPT-5.6, the Global inference profile price was the same as OpenAI's direct-sale price).
Summary
I confirmed invocation from the bedrock-runtime endpoint in three ways: Converse, the Responses API, and Chat Completions. The inference profile IDs are global.openai.gpt-6-sol / global.openai.gpt-6-luna.
I have not been able to confirm the pricing on Bedrock at the time of writing, but based on the GPT-5.6 precedent, it is likely that you can use them at the same price as OpenAI when going through a Global inference profile.
Since prices have been reduced across all models compared to GPT-5.6, it is worth considering migrating to GPT-6 if you have GPT-5.6 workloads.
GPT-6 is offered on the bedrock-runtime endpoint and already supports a 1M-token context. Even for workloads that have traditionally used Claude-family models, GPT may be usable, so please give it a try.
References
