GPT-5.6 Sol (US) pricing, context window and limits
GPT-5.6 Sol (US) costs $4.4 per million input tokens and $22 per million output tokens at Amazon Bedrock list price. It accepts up to 1,050,000 tokens of context and returns up to 128,000 tokens.
- Model id
bedrock/us.openai.gpt-5.6-sol - Snapshot
What does GPT-5.6 Sol (US) cost?
| Input | $4.4 |
|---|---|
| Output | $22 |
| Cached input (read) | $0.44 |
| Cache write | $5.5 |
US dollars per million tokens. A dash means no price is published.
How much can GPT-5.6 Sol (US) read and write?
| Context window | 1,050,000 |
|---|---|
| Max input | 922,000 |
| Max output | 128,000 |
What can GPT-5.6 Sol (US) do?
| Vision (image input) | Yes |
|---|---|
| Tool calling | Yes |
| Structured output | No |
| Reasoning | Yes |
| Input | text, image |
| Output | text |
What does a request to GPT-5.6 Sol (US) cost?
| A typical request: 1,000 tokens in, 500 out | $0.015 |
|---|---|
| A long request: 10,000 tokens in, 1,000 out | $0.066 |
| 1,000 typical requests | $15.4 |
| 1 million tokens in and 1 million out | $26.4 |
Input read from the provider's prompt cache costs $0.44 per million tokens instead of $4.4, 90% less. A request that repeats a 1,000-token prompt from the cache costs $0.011 instead of $0.015.
Among 191 Amazon Bedrock models with a published price, GPT-5.6 Sol (US) is the 145th cheapest by input price. Its context window is the 3rd largest of 191. List prices only; discounts, batch prices and prices above 200K tokens are not shown.
How do I call GPT-5.6 Sol (US) through DVARA?
Configure the bedrock provider in the DVARA LLM Gateway and send the model id bedrock/us.openai.gpt-5.6-sol. DVARA, the AI governance platform, applies your policies, audit and cost attribution to the call. See LLM cost attribution and budgets.
In DVARA, if you haven't set your own price for a model, its calls are costed at the price in the catalogue that ships with your DVARA version. A price you set in Flightdeck always wins. You can switch catalogue prices off. Then a model with no price you set is counted as costing nothing. Every cost record says which price it used.
What should I check before relying on this data?
The weekly review marked this entry. A person saw each mark and kept the model listed.
- The provider charges more above 200K tokens of input; the table shows the base price.
Which other Amazon Bedrock models are there?
- GPT-5.6 Luna (US)$0.22 in · $1.32 out · 1.05M context
- GPT-5.6 Terra (US)$2.2 in · $13.2 out · 1.05M context
- GPT-6 Astra (US)$11 in · $55 out · 1.05M context
- GPT-6 Luna (US)$0.11 in · $0.55 out · 1.05M context
- GPT-6 Sol (US)$2.2 in · $11 out · 1.05M context
- GPT-6.1 Sol (US)$2.2 in · $11 out · 1.05M context
- gpt-oss-20b (GovCloud)$0.084 in · $0.36 out · 128K context
- gpt-oss-120b (GovCloud)$0.18 in · $0.72 out · 128K context
- GPT OSS Safeguard 20B$0.07 in · $0.2 out · 128K context
- GPT OSS Safeguard 120B$0.15 in · $0.6 out · 128K context
- gpt-oss-20b$0.07 in · $0.3 out · 131K context
- gpt-oss-20b$0.07 in · $0.3 out · 131K context
Which models from other providers are similar to GPT-5.6 Sol (US)?
These are the closest in context window and input price, one per provider.
- GPT-5.6OpenAI · $4 in · $20 out · 1.05M context
- Claude Opus 5.5Anthropic · $4 in · $20 out · 1M context
- Kimi K3Moonshot AI · $3 in · $15 out · 1.05M context
- Qwen Deep ResearchAlibaba Qwen · $7.742 in · $23.367 out · 1M context
- Gemini 3.1 Pro PreviewGoogle Gemini · $2 in · $12 out · 1.05M context