Bedrock models with long context (200k+)
These Amazon Bedrock models accept at least 200,000 tokens in a single call — roughly a 500-page book, a large codebase, or a full day of meeting transcripts. Above that threshold you can usually stop chunking and let the model see the whole thing.
26 of the models on Bedrock qualify today, from $2.50 per 1M input tokens. Rebuilt daily from the AWS catalogue, so this list does not go stale.
What teams get wrong about this
A large window is a capacity, not a budget. Filling a 1M-token window once, at typical rates, costs more than a thousand ordinary requests — and long prompts also raise latency and can dilute attention on the part that mattered. Long context is worth paying for when the alternative is a chunking pipeline you have to build and maintain, not as a default.
All 26 models, cheapest first
| Model | Input /1M | Context |
|---|---|---|
| Nova Premier amazon.nova-premier-v1:0 | $2.50 | 1M |
| Claude Fable 5 anthropic.claude-fable-5 | $10.00 | 1M |
| Claude Opus 4.6 anthropic.claude-opus-4-6-v1 | $5.00 | 1M |
| Claude Opus 4.7 anthropic.claude-opus-4-7 | $5.00 | 1M |
| Claude Opus 4.8 anthropic.claude-opus-4-8 | $5.00 | 1M |
| Claude Opus 5 anthropic.claude-opus-5 | $5.00 | 1M |
| Claude Sonnet 4.6 anthropic.claude-sonnet-4-6 | $3.00 | 1M |
| Claude Sonnet 5 anthropic.claude-sonnet-5 | $3.00 | 1M |
| GPT-5.6 Luna openai.gpt-5.6-luna | $0.200 | 1M |
| GPT-5.6 Sol openai.gpt-5.6-sol | $4.00 | 1M |
| GPT-5.6 Terra openai.gpt-5.6-terra | $2.00 | 1M |
| Grok 4.6 xai.grok-4.6 | $2.00 | 500K |
| Nova Lite amazon.nova-lite-v1:0 | $0.060 | 300K |
| Nova Pro amazon.nova-pro-v1:0 | $0.800 | 300K |
| Jamba 1.5 Large ai21.jamba-1-5-large-v1:0 | — | 256K |
| Jamba 1.5 Mini ai21.jamba-1-5-mini-v1:0 | — | 256K |
| Claude 3 Haiku anthropic.claude-3-haiku-20240307-v1:0 | $0.250 | 200K |
| Claude 3 Sonnet anthropic.claude-3-sonnet-20240229-v1:0 | $3.00 | 200K |
| Claude 3.5 Sonnet anthropic.claude-3-5-sonnet-20240620-v1:0 | — | 200K |
| Claude 3.5 Sonnet v2 anthropic.claude-3-5-sonnet-20241022-v2:0 | — | 200K |
| Claude 3.7 Sonnet anthropic.claude-3-7-sonnet-20250219-v1:0 | — | 200K |
| Claude Haiku 4.5 anthropic.claude-haiku-4-5-20251001-v1:0 | $1.00 | 200K |
| Claude Opus 4.1 anthropic.claude-opus-4-1-20250805-v1:0 | — | 200K |
| Claude Opus 4.5 anthropic.claude-opus-4-5-20251101-v1:0 | $5.00 | 200K |
| Claude Sonnet 4 anthropic.claude-sonnet-4-20250514-v1:0 | — | 200K |
| Claude Sonnet 4.5 anthropic.claude-sonnet-4-5-20250929-v1:0 | $3.00 | 200K |
Capability flags come from the AWS Bedrock model catalogue; prices from the Price List API. Region counts include cross-region inference profiles. Methodology.
Questions
Which Bedrock model has the largest context window?
The table on this page is sorted by window size, largest first, so the top row is the current answer. It is regenerated from the AWS catalogue daily, so it stays correct as models ship.
What does it cost to fill a 1M-token context window?
Multiply the input price per 1M tokens shown in the table by one — that is the whole point of the per-1M unit. At $3 per 1M, one full-window call costs $3 in input alone, before output. Prompt caching is what makes repeatedly sending a large context affordable.