Use AWS Bedrock Models in Big-AGI.
Frontier models - Claude, GPT and Grok among them - inside the AWS account your company already trusts: your credentials, regions and policies, billed by AWS.
All supported AWS Bedrock models
Claude Fable 5.1
NEWHOTMost capable widely released model for demanding reasoning and long-horizon agentic work (Bedrock Inference Profile)
1M
$10.00
$50.00
Sep 2026
Claude Opus 5
NEWHOTStep-change improvement over Opus 4.8 for complex agentic coding and enterprise work (Bedrock Inference Profile)
1M
$5.00
$25.00
Jul 2026
Claude Sonnet 5
HOTBest combination of speed and intelligence, with the largest gains in coding and agentic tasks (Bedrock Inference Profile)
1M
$2.00
$10.00
Jun 2026
Claude Fable 5
Previous Fable-tier model for the most demanding reasoning and long-horizon agentic work (Bedrock Inference Profile)
1M
$10.00
$50.00
Jun 2026
Claude Opus 4.8
Previous most capable Opus-tier model for complex reasoning and agentic coding (Bedrock Inference Profile)
1M
$5.00
$25.00
May 2026
GPT-5.5
Openai model via OpenAI-Compatible Responses API on AWS Bedrock Mantle
272K
-
-
Apr 2026
Claude Opus 4.7
Previous most capable model for complex reasoning and agentic coding (Bedrock Inference Profile)
1M
$5.00
$25.00
Apr 2026
DeepSeek V3.1
Deepseek model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Mar 2026
GPT-5.4
Openai model via OpenAI-Compatible Responses API on AWS Bedrock Mantle
272K
-
-
Mar 2026
Claude Sonnet 4.6
Best combination of speed and intelligence for everyday tasks (Bedrock Inference Profile)
1M
$3.00
$15.00
Feb 2026
MiniMax M2.5
MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)
197K
-
-
Feb 2026
Z.AI GLM 5
Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)
203K
-
-
Feb 2026
Claude Opus 4.6
Previous most intelligent model for complex agents and coding, with adaptive thinking (Bedrock Inference Profile)
1M
$5.00
$25.00
Feb 2026
Qwen3 Coder Next
Qwen model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
Feb 2026
Moonshot AI Kimi K2.5
Moonshot AI model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
Jan 2026
Z.AI GLM 4.7 Flash
Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)
203K
-
-
Jan 2026
MiniMax M2.1
MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)
197K
-
-
Dec 2025
Z.AI GLM 4.7
Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)
203K
-
-
Dec 2025
DeepSeek V3.2
DeepSeek model via OpenAI-Compatible API (Bedrock Foundation Model)
164K
-
-
Dec 2025
Claude Opus 4.5
Previous most intelligent model with advanced reasoning for complex agentic workflows (Bedrock Inference Profile)
200K
$5.00
$25.00
Nov 2025
Kimi K2 Thinking
Moonshotai model via OpenAI-Compatible API on AWS Bedrock Mantle
262K
-
-
Nov 2025
Mistral AI Voxtral Small 24B 2507
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
33K
-
-
Oct 2025
OpenAI GPT OSS Safeguard 20B
OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
Oct 2025
MiniMax M2
MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)
410K
-
-
Oct 2025
GLM 4.6
Zai model via OpenAI-Compatible API on AWS Bedrock Mantle
205K
-
-
Sep 2025
Claude Sonnet 4.5
HOTPrevious best combination of speed and intelligence for complex agents and coding (Bedrock Inference Profile)
200K
$3.00
$15.00
Sep 2025
Qwen3 VL 235B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Sep 2025
Mistral AI Magistral Small 2509
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
Sep 2025
Qwen3 Next 80B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Sep 2025
GPT-OSS 120B
Openai model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Aug 2025
GPT-OSS 20B
Openai model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Aug 2025
Claude Opus 4.1 [Retired]
Previous Opus model. Retired August 5, 2026 (except on Bedrock and Vertex AI). (Bedrock Inference Profile)
200K
$15.00
$75.00
Aug 2025
Qwen3 Coder 30B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Jul 2025
Qwen3 235B A22B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Jul 2025
Claude Sonnet 4 [Retired]
High-performance model. Retired June 15, 2026 (except on Bedrock and Vertex AI). (Bedrock Inference Profile)
200K
$3.00
$15.00
May 2025
Qwen3 32B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
Apr 2025
Google Gemma 3 12B IT
Google model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
Mar 2025
Google Gemma 3 4B IT
Google model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
Mar 2025
Google Gemma 3 27B PT
Google model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
Mar 2025
Claude Haiku 3 [Retired]
Fast and compact model for near-instant responsiveness. Retired April 20, 2026. (Bedrock Inference Profile)
200K
$0.25
$1.25
Mar 2024
Xai Grok 4.3
HOTXai model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
-
OpenAI GPT-5.6 Luna
Openai model via OpenAI-Compatible API (Bedrock Inference Profile)
131K
-
-
-
OpenAI GPT-5.6 Sol
Openai model via OpenAI-Compatible API (Bedrock Inference Profile)
131K
-
-
-
OpenAI GPT-5.6 Terra
Openai model via OpenAI-Compatible API (Bedrock Inference Profile)
131K
-
-
-
xAI Grok 4.6
Xai model via Converse API (Bedrock Inference Profile)
-
-
-
-
Anthropic Claude Haiku 4 5
Anthropic model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
$1.00
$5.00
-
Anthropic Claude 3 Sonnet
Anthropic model (Bedrock Inference Profile)
200K
-
-
-
Cohere Command R+
deprecatedCohere model via Unsupported API (Bedrock Foundation Model)
-
-
-
-
Cohere Command R
deprecatedCohere model via Unsupported API (Bedrock Foundation Model)
-
-
-
-
Cohere Embed v4
deprecatedCohere model via Converse API (Bedrock Inference Profile)
-
-
-
-
DeepSeek-R1
Deepseek model via Converse API (Bedrock Inference Profile)
-
-
-
-
Mistral AI Devstral 2 123B
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
Google Gemma 4 26b A4b
Google model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
-
Google Gemma 4 31b
Google model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
-
Google Gemma 4 E2b
Google model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
-
OpenAI gpt-oss-120b
OpenAI model via Converse API (Bedrock Foundation Model)
128K
-
-
-
OpenAI gpt-oss-20b
OpenAI model via Converse API (Bedrock Foundation Model)
128K
-
-
-
OpenAI GPT OSS Safeguard 120B
OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
-
Anthropic Honey
deprecatedAnthropic model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
-
AI21 Labs Jamba 1.5 Large
deprecatedAI21 Labs model via Unsupported API (Bedrock Foundation Model)
-
-
-
-
AI21 Labs Jamba 1.5 Mini
deprecatedAI21 Labs model via Unsupported API (Bedrock Foundation Model)
-
-
-
-
Meta Llama 3.1 70B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3.1 8B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3.2 11B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3.2 1B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3.2 3B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3.2 90B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3.3 70B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 3 70B Instruct
Meta model via Converse API (Bedrock Foundation Model)
-
-
-
-
Meta Llama 3 8B Instruct
Meta model via Converse API (Bedrock Foundation Model)
-
-
-
-
Meta Llama 4 Maverick 17B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Meta Llama 4 Scout 17B Instruct
Meta model via Converse API (Bedrock Inference Profile)
-
-
-
-
Twelvelabs TwelveLabs Marengo Embed v2.7
deprecatedTwelvelabs model via Converse API (Bedrock Inference Profile)
-
-
-
-
Twelvelabs TwelveLabs Marengo Embed 3.0
deprecatedTwelvelabs model via Converse API (Bedrock Inference Profile)
-
-
-
-
Mistral AI Ministral 14B 3.0
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
Mistral AI Ministral 3B
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
Mistral AI Ministral 3 8B
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
Mistral AI Mistral 7B Instruct
Mistral AI model via Converse API (Bedrock Foundation Model)
-
-
-
-
Mistral AI Mistral Large (24.02)
Mistral AI model via Converse API (Bedrock Foundation Model)
-
-
-
-
Mistral AI Mistral Large 3
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
Mistral AI Mistral Small (24.02)
Mistral AI model via Converse API (Bedrock Foundation Model)
-
-
-
-
Mistral AI Mixtral 8x7B Instruct
Mistral AI model via Converse API (Bedrock Foundation Model)
-
-
-
-
NVIDIA Nemotron Nano 12B v2 VL BF16
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
-
NVIDIA Nemotron Nano 3 30B
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
NVIDIA Nemotron Nano 9B v2
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
131K
-
-
-
NVIDIA Nemotron 3 Super 120B A12B
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
262K
-
-
-
Amazon Nova 2 Lite
Amazon model via Converse API (Bedrock Inference Profile)
-
-
-
-
Amazon Nova Lite
Amazon model via Converse API (Bedrock Inference Profile)
-
-
-
-
Amazon Nova Micro
Amazon model via Converse API (Bedrock Inference Profile)
-
-
-
-
Amazon Nova Premier
Amazon model via Converse API (Bedrock Inference Profile)
-
-
-
-
Amazon Nova Pro
Amazon model via Converse API (Bedrock Foundation Model)
10K
-
-
-
Writer Palmyra Vision 7B
Writer model via OpenAI-Compatible API (Bedrock Foundation Model)
4K
-
-
-
Writer Palmyra X4
Writer model via Converse API (Bedrock Inference Profile)
-
-
-
-
Writer Palmyra X5
Writer model via Converse API (Bedrock Inference Profile)
-
-
-
-
TwelveLabs Pegasus v1.2
Twelvelabs model via Converse API (Bedrock Inference Profile)
-
-
-
-
Mistral Pixtral Large 25.02
Mistral model via Converse API (Bedrock Inference Profile)
-
-
-
-
Qwen3-Coder-30B-A3B-Instruct
Qwen model via Converse API (Bedrock Foundation Model)
262K
-
-
-
Qwen3 Coder 480B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
131K
-
-
-
Qwen3 Next 80B A3B
Qwen model via Converse API (Bedrock Foundation Model)
262K
-
-
-
Qwen3 VL 235B A22B
Qwen model via Converse API (Bedrock Foundation Model)
262K
-
-
-
Mistral AI Voxtral Mini 3B 2507
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
33K
-
-
-
Claude Fable 5.1
NEWHOTMost capable widely released model for demanding reasoning and long-horizon agentic work (Bedrock Inference Profile)
Claude Opus 5
NEWHOTStep-change improvement over Opus 4.8 for complex agentic coding and enterprise work (Bedrock Inference Profile)
Claude Sonnet 5
HOTBest combination of speed and intelligence, with the largest gains in coding and agentic tasks (Bedrock Inference Profile)
Claude Fable 5
Previous Fable-tier model for the most demanding reasoning and long-horizon agentic work (Bedrock Inference Profile)
Claude Opus 4.8
Previous most capable Opus-tier model for complex reasoning and agentic coding (Bedrock Inference Profile)
GPT-5.5
Openai model via OpenAI-Compatible Responses API on AWS Bedrock Mantle
Claude Opus 4.7
Previous most capable model for complex reasoning and agentic coding (Bedrock Inference Profile)
DeepSeek V3.1
Deepseek model via OpenAI-Compatible API on AWS Bedrock Mantle
GPT-5.4
Openai model via OpenAI-Compatible Responses API on AWS Bedrock Mantle
Claude Sonnet 4.6
Best combination of speed and intelligence for everyday tasks (Bedrock Inference Profile)
MiniMax M2.5
MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)
Z.AI GLM 5
Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Claude Opus 4.6
Previous most intelligent model for complex agents and coding, with adaptive thinking (Bedrock Inference Profile)
Qwen3 Coder Next
Qwen model via OpenAI-Compatible API (Bedrock Foundation Model)
Moonshot AI Kimi K2.5
Moonshot AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Z.AI GLM 4.7 Flash
Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)
MiniMax M2.1
MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)
Z.AI GLM 4.7
Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)
DeepSeek V3.2
DeepSeek model via OpenAI-Compatible API (Bedrock Foundation Model)
Claude Opus 4.5
Previous most intelligent model with advanced reasoning for complex agentic workflows (Bedrock Inference Profile)
Kimi K2 Thinking
Moonshotai model via OpenAI-Compatible API on AWS Bedrock Mantle
Mistral AI Voxtral Small 24B 2507
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
OpenAI GPT OSS Safeguard 20B
OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)
MiniMax M2
MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)
GLM 4.6
Zai model via OpenAI-Compatible API on AWS Bedrock Mantle
Claude Sonnet 4.5
HOTPrevious best combination of speed and intelligence for complex agents and coding (Bedrock Inference Profile)
Qwen3 VL 235B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
Mistral AI Magistral Small 2509
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Qwen3 Next 80B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
GPT-OSS 120B
Openai model via OpenAI-Compatible API on AWS Bedrock Mantle
GPT-OSS 20B
Openai model via OpenAI-Compatible API on AWS Bedrock Mantle
Claude Opus 4.1 [Retired]
Previous Opus model. Retired August 5, 2026 (except on Bedrock and Vertex AI). (Bedrock Inference Profile)
Qwen3 Coder 30B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
Qwen3 235B A22B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
Claude Sonnet 4 [Retired]
High-performance model. Retired June 15, 2026 (except on Bedrock and Vertex AI). (Bedrock Inference Profile)
Qwen3 32B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
Google Gemma 3 12B IT
Google model via OpenAI-Compatible API (Bedrock Foundation Model)
Google Gemma 3 4B IT
Google model via OpenAI-Compatible API (Bedrock Foundation Model)
Google Gemma 3 27B PT
Google model via OpenAI-Compatible API (Bedrock Foundation Model)
Claude Haiku 3 [Retired]
Fast and compact model for near-instant responsiveness. Retired April 20, 2026. (Bedrock Inference Profile)
Xai Grok 4.3
HOTXai model via OpenAI-Compatible API on AWS Bedrock Mantle
OpenAI GPT-5.6 Luna
Openai model via OpenAI-Compatible API (Bedrock Inference Profile)
OpenAI GPT-5.6 Sol
Openai model via OpenAI-Compatible API (Bedrock Inference Profile)
OpenAI GPT-5.6 Terra
Openai model via OpenAI-Compatible API (Bedrock Inference Profile)
xAI Grok 4.6
Xai model via Converse API (Bedrock Inference Profile)
Anthropic Claude Haiku 4 5
Anthropic model via OpenAI-Compatible API on AWS Bedrock Mantle
Anthropic Claude 3 Sonnet
Anthropic model (Bedrock Inference Profile)
Cohere Command R+
deprecatedCohere model via Unsupported API (Bedrock Foundation Model)
Cohere Command R
deprecatedCohere model via Unsupported API (Bedrock Foundation Model)
Cohere Embed v4
deprecatedCohere model via Converse API (Bedrock Inference Profile)
DeepSeek-R1
Deepseek model via Converse API (Bedrock Inference Profile)
Mistral AI Devstral 2 123B
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Google Gemma 4 26b A4b
Google model via OpenAI-Compatible API on AWS Bedrock Mantle
Google Gemma 4 31b
Google model via OpenAI-Compatible API on AWS Bedrock Mantle
Google Gemma 4 E2b
Google model via OpenAI-Compatible API on AWS Bedrock Mantle
OpenAI gpt-oss-120b
OpenAI model via Converse API (Bedrock Foundation Model)
OpenAI gpt-oss-20b
OpenAI model via Converse API (Bedrock Foundation Model)
OpenAI GPT OSS Safeguard 120B
OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)
Anthropic Honey
deprecatedAnthropic model via OpenAI-Compatible API on AWS Bedrock Mantle
AI21 Labs Jamba 1.5 Large
deprecatedAI21 Labs model via Unsupported API (Bedrock Foundation Model)
AI21 Labs Jamba 1.5 Mini
deprecatedAI21 Labs model via Unsupported API (Bedrock Foundation Model)
Meta Llama 3.1 70B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3.1 8B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3.2 11B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3.2 1B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3.2 3B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3.2 90B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3.3 70B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 3 70B Instruct
Meta model via Converse API (Bedrock Foundation Model)
Meta Llama 3 8B Instruct
Meta model via Converse API (Bedrock Foundation Model)
Meta Llama 4 Maverick 17B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Meta Llama 4 Scout 17B Instruct
Meta model via Converse API (Bedrock Inference Profile)
Twelvelabs TwelveLabs Marengo Embed v2.7
deprecatedTwelvelabs model via Converse API (Bedrock Inference Profile)
Twelvelabs TwelveLabs Marengo Embed 3.0
deprecatedTwelvelabs model via Converse API (Bedrock Inference Profile)
Mistral AI Ministral 14B 3.0
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Mistral AI Ministral 3B
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Mistral AI Ministral 3 8B
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Mistral AI Mistral 7B Instruct
Mistral AI model via Converse API (Bedrock Foundation Model)
Mistral AI Mistral Large (24.02)
Mistral AI model via Converse API (Bedrock Foundation Model)
Mistral AI Mistral Large 3
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Mistral AI Mistral Small (24.02)
Mistral AI model via Converse API (Bedrock Foundation Model)
Mistral AI Mixtral 8x7B Instruct
Mistral AI model via Converse API (Bedrock Foundation Model)
NVIDIA Nemotron Nano 12B v2 VL BF16
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
NVIDIA Nemotron Nano 3 30B
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
NVIDIA Nemotron Nano 9B v2
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
NVIDIA Nemotron 3 Super 120B A12B
NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)
Amazon Nova 2 Lite
Amazon model via Converse API (Bedrock Inference Profile)
Amazon Nova Lite
Amazon model via Converse API (Bedrock Inference Profile)
Amazon Nova Micro
Amazon model via Converse API (Bedrock Inference Profile)
Amazon Nova Premier
Amazon model via Converse API (Bedrock Inference Profile)
Amazon Nova Pro
Amazon model via Converse API (Bedrock Foundation Model)
Writer Palmyra Vision 7B
Writer model via OpenAI-Compatible API (Bedrock Foundation Model)
Writer Palmyra X4
Writer model via Converse API (Bedrock Inference Profile)
Writer Palmyra X5
Writer model via Converse API (Bedrock Inference Profile)
TwelveLabs Pegasus v1.2
Twelvelabs model via Converse API (Bedrock Inference Profile)
Mistral Pixtral Large 25.02
Mistral model via Converse API (Bedrock Inference Profile)
Qwen3-Coder-30B-A3B-Instruct
Qwen model via Converse API (Bedrock Foundation Model)
Qwen3 Coder 480B
Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle
Qwen3 Next 80B A3B
Qwen model via Converse API (Bedrock Foundation Model)
Qwen3 VL 235B A22B
Qwen model via Converse API (Bedrock Foundation Model)
Mistral AI Voxtral Mini 3B 2507
Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)
Get started in 3 steps
1
Create an API key at the AWS Bedrock console.
2
Paste it into Big-AGI's model settings.
3
Start chatting, or Beam it against other models and fuse the answers.
Running AWS Bedrock in Big-AGI
Connect Amazon Bedrock with your own AWS credentials and use frontier models inside the cloud your company already trusts. Big-AGI adds no markup and no intermediary: the billing relationship runs directly between you and AWS. Traffic keeps flowing between your setup and your AWS account, so your IAM policies, regions, and compliance story keep applying.
- Two ways to connect. The only integration here that isn't paste-an-API-key: Big-AGI supports both AWS's newer Bedrock API keys (sent as bearer tokens) and classic IAM credential trios with real SigV4 signing.
- Your account, your billing. Usage lands on your AWS bill at Bedrock's standard rates.
- One catalog, three AWS APIs merged. Big-AGI combines Bedrock's Foundation Models, Inference Profiles, and OpenAI-compatible listings into one de-duplicated catalog, so a model on just one API still shows up, and each source degrades gracefully.
- Claude on AWS. Run Anthropic's models through Bedrock alongside Llama, Mistral, Nova, and the rest of the catalog.
Why Big-AGI instead of the console?
The Bedrock console is built for one model, one prompt, one AWS account at a time. Big-AGI adds a real workspace on top of it: persistent chats, personas, and attachments, still routed through your own AWS credentials. It's also the only place a Bedrock-hosted model runs in Beam next to GPT, Gemini, and other frontier labs your account may not have in Bedrock at all.
Your keys and your data
Turn on Direct Connection and the browser talks to AWS directly with your credentials, skipping the Big-AGI server, when your setup keeps them client-side and Bedrock allows it. Your credentials stay in your browser. Chats are stored locally first, and sync only if you turn it on. The AI Inspector shows the exact request, the token counts, and a cost estimate against your AWS bill.
AWS Bedrock in Beam
Run a Bedrock-hosted model, Claude, Llama, Nova, whichever your account has access to, in parallel with GPT, Gemini, and more. Fusions then combine, cross-check, and synthesize the parallel answers instead of just picking the best one. Parallel runs use more tokens than a single chat.
Bring your AWS Bedrock key. Keep control.
Your key, your data, your choice of model. Big-AGI's Open branch is open source and self-hostable, so you can check exactly how AWS Bedrock is called.
Launch Big-AGIBIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego