Big-AGI Logo
BIG-AGI

BEAM

Features

Rankings

Pro

Docs

GitHub

LAUNCH APP

Use AWS Bedrock Models in Big-AGI.

Bring your own AWS Bedrock key and use AWS Bedrock at its own API rates, with no markup. Keys and chats stay in your browser. Run AWS Bedrock in parallel with other models, then compare and merge the answers.

Claude Sonnet 5
Claude Fable 5
Claude Opus 4.8
Launch Big-AGI

All supported AWS Bedrock models

ModelContextInputOutputReleased

Claude Sonnet 5

NEW
VisionTools / functions

Best combination of speed and intelligence, with the largest gains in coding and agentic tasks (Bedrock Inference Profile)

1M

$2

$10

Jun 2026

Claude Fable 5

NEW
VisionReasoningTools / functions

Most capable widely released model for the most demanding reasoning and long-horizon agentic work (Bedrock Inference Profile)

1M

$10

$50

Jun 2026

Claude Opus 4.8

NEW
VisionTools / functions

Most capable Opus-tier model for complex reasoning and agentic coding (Bedrock Inference Profile)

1M

$5

$25

May 2026

Claude Opus 4.7

VisionTools / functions

Previous most capable model for complex reasoning and agentic coding (Bedrock Inference Profile)

1M

$5

$25

Apr 2026

Claude Sonnet 4.6

VisionTools / functions

Best combination of speed and intelligence for everyday tasks (Bedrock Inference Profile)

1M

$3

$15

Feb 2026

Claude Opus 4.6

VisionTools / functions

Previous most intelligent model for complex agents and coding, with adaptive thinking (Bedrock Inference Profile)

1M

$5

$25

Feb 2026

Claude Opus 4.5

VisionTools / functions

Previous most intelligent model with advanced reasoning for complex agentic workflows (Bedrock Inference Profile)

200K

$5

$25

Nov 2025

Claude Haiku 4.5

VisionTools / functions

Fastest model with exceptional speed and performance (Bedrock Inference Profile)

200K

$1

$5

Oct 2025

Claude Sonnet 4.5

VisionTools / functions

Previous best combination of speed and intelligence for complex agents and coding (Bedrock Inference Profile)

200K

$3

$15

Sep 2025

Claude Opus 4.1

deprecated
VisionTools / functions

Previous Opus model. Deprecated June 5, 2026, retiring August 5, 2026. (Bedrock Inference Profile)

200K

$15

$75

Aug 2025

Claude Sonnet 4 [Retired]

VisionTools / functions

High-performance model. Retired June 15, 2026 (except on Bedrock and Vertex AI). (Bedrock Inference Profile)

200K

$3

$15

May 2025

�️ Claude Haiku 3 [Retired]

VisionTools / functions

Fast and compact model for near-instant responsiveness. Retired April 20, 2026. (Bedrock Foundation Model)

200K

$0.25

$1.25

Mar 2024

DeepSeek V3.2

DeepSeek model via OpenAI-Compatible API (Bedrock Foundation Model)

164K

-

-

-

GPT-OSS 20B

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Mistral AI Mistral Large 3

Vision

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Amazon Nova 2 Lite

Tools / functions

Amazon model via Converse API (Bedrock Inference Profile)

-

-

-

-

Moonshot AI Kimi K2.5

Vision

Moonshot AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Writer Palmyra Vision 7B

Vision

Writer model via OpenAI-Compatible API (Bedrock Foundation Model)

4K

-

-

-

Z.AI GLM 4.7 Flash

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

203K

-

-

-

Google Gemma 4 E2b

Google model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Google Gemma 4 26b A4b

Google model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Amazon Nova Micro

Tools / functions

Amazon model via Converse API (Bedrock Inference Profile)

-

-

-

-

Qwen3 Next 80B A3B

Tools / functions

Qwen model via Converse API (Bedrock Foundation Model)

262K

-

-

-

Amazon Nova Pro

VisionTools / functions

Amazon model via Converse API (Bedrock Foundation Model)

10K

-

-

-

OpenAI gpt-oss-120b

Tools / functions

OpenAI model via Converse API (Bedrock Foundation Model)

128K

-

-

-

Google Gemma 4 31b

Google model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

AI21 Labs Jamba 1.5 Large

AI21 Labs model via Unsupported API (Bedrock Foundation Model)

-

-

-

-

Cohere Command R+

Cohere model via Unsupported API (Bedrock Foundation Model)

-

-

-

-

MiniMax M2

Reasoning

MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)

410K

-

-

-

Cohere Command R

Cohere model via Unsupported API (Bedrock Foundation Model)

-

-

-

-

GPT-OSS 120B

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Amazon Nova Lite

VisionTools / functions

Amazon model via Converse API (Bedrock Foundation Model)

-

-

-

-

Writer Palmyra X5

Tools / functions

Writer model via Converse API (Bedrock Inference Profile)

-

-

-

-

Google Gemma 3 12B IT

Vision

Google model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Mistral AI Devstral 2 123B

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Google Gemma 3 4B IT

Vision

Google model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Qwen3 Coder Next

Qwen model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Writer Palmyra X4

Tools / functions

Writer model via Converse API (Bedrock Inference Profile)

-

-

-

-

MiniMax M2.1

Reasoning

MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)

197K

-

-

-

Openai Gpt 5.4

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Qwen3 32B (dense)

Tools / functions

Qwen model via Converse API (Bedrock Foundation Model)

33K

-

-

-

Qwen3 VL 235B A22B

VisionTools / functions

Qwen model via Converse API (Bedrock Foundation Model)

262K

-

-

-

OpenAI gpt-oss-20b

Tools / functions

OpenAI model via Converse API (Bedrock Foundation Model)

128K

-

-

-

Google Gemma 3 27B PT

Vision

Google model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Qwen3 VL 235B

Vision

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Xai Grok 4.3

Xai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Mistral Pixtral Large 25.02

Tools / functions

Mistral model via Converse API (Bedrock Inference Profile)

-

-

-

-

DeepSeek V3.1

Deepseek model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Meta Llama 4 Maverick 17B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Mistral AI Ministral 3 8B

Vision

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Meta Llama 3.1 70B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Moonshot AI Kimi K2 Thinking

ReasoningTools / functions

Moonshot AI model via Converse API (Bedrock Foundation Model)

262K

-

-

-

Qwen3 Next 80B

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Meta Llama 3.2 1B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Meta Llama 3 8B Instruct

Tools / functions

Meta model via Converse API (Bedrock Foundation Model)

-

-

-

-

Anthropic Claude 3 Sonnet · US

VisionTools / functions

Anthropic model (Bedrock Inference Profile)

200K

-

-

-

Twelvelabs TwelveLabs Marengo Embed 3.0

Tools / functions

Twelvelabs model via Converse API (Bedrock Inference Profile)

-

-

-

-

Z.AI GLM 5

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

203K

-

-

-

MiniMax M2.5

Reasoning

MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)

197K

-

-

-

Cohere Embed v4

Tools / functions

Cohere model via Converse API (Bedrock Inference Profile)

-

-

-

-

Openai Gpt 5.5 2026 04 23

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Mistral AI Ministral 3B

Vision

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Qwen3 Coder 30B

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Qwen3 32B

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Mistral AI Voxtral Small 24B 2507

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

33K

-

-

-

Mistral AI Ministral 14B 3.0

Vision

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Meta Llama 3.2 3B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Kimi K2 Thinking

Moonshotai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

NVIDIA Nemotron Nano 12B v2 VL BF16

Vision

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Mistral AI Mistral Small (24.02)

Tools / functions

Mistral AI model via Converse API (Bedrock Foundation Model)

-

-

-

-

Meta Llama 3.3 70B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Mistral AI Mistral 7B Instruct

Tools / functions

Mistral AI model via Converse API (Bedrock Foundation Model)

-

-

-

-

Qwen3 Coder 480B

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Meta Llama 3.2 11B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Meta Llama 3.2 90B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

NVIDIA Nemotron 3 Super 120B A12B

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Anthropic Claude Haiku 4 5

Anthropic model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

OpenAI GPT OSS Safeguard 120B

Reasoning

OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Deepseek DeepSeek-R1

Tools / functions

Deepseek model via Converse API (Bedrock Inference Profile)

-

-

-

-

Qwen3 235B A22B

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Mistral AI Magistral Small 2509

VisionReasoning

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Mistral AI Mistral Large (24.02)

Tools / functions

Mistral AI model via Converse API (Bedrock Foundation Model)

-

-

-

-

Meta Llama 3.1 8B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Meta Llama 4 Scout 17B Instruct

Tools / functions

Meta model via Converse API (Bedrock Inference Profile)

-

-

-

-

Meta Llama 3 70B Instruct

Tools / functions

Meta model via Converse API (Bedrock Foundation Model)

-

-

-

-

Mistral AI Mixtral 8x7B Instruct

Tools / functions

Mistral AI model via Converse API (Bedrock Foundation Model)

-

-

-

-

Z.AI GLM 4.7

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

203K

-

-

-

Twelvelabs Pegasus v1.2

Tools / functions

Twelvelabs model via Converse API (Bedrock Inference Profile)

-

-

-

-

Twelvelabs TwelveLabs Marengo Embed v2.7

Tools / functions

Twelvelabs model via Converse API (Bedrock Inference Profile)

-

-

-

-

NVIDIA Nemotron Nano 9B v2

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

OpenAI GPT OSS Safeguard 20B

Reasoning

OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)

131K

-

-

-

Mistral AI Voxtral Mini 3B 2507

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

33K

-

-

-

GLM 4.6

Zai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K

-

-

-

Qwen3-Coder-30B-A3B-Instruct

Tools / functions

Qwen model via Converse API (Bedrock Foundation Model)

262K

-

-

-

AI21 Labs Jamba 1.5 Mini

AI21 Labs model via Unsupported API (Bedrock Foundation Model)

-

-

-

-

NVIDIA Nemotron Nano 3 30B

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

262K

-

-

-

Amazon Nova Premier

Tools / functions

Amazon model via Converse API (Bedrock Inference Profile)

-

-

-

-

Claude Sonnet 5

NEW
Jun 2026

Best combination of speed and intelligence, with the largest gains in coding and agentic tasks (Bedrock Inference Profile)

VisionTools / functions
1M · in $2 · out $10

Claude Fable 5

NEW
Jun 2026

Most capable widely released model for the most demanding reasoning and long-horizon agentic work (Bedrock Inference Profile)

VisionReasoningTools / functions
1M · in $10 · out $50

Claude Opus 4.8

NEW
May 2026

Most capable Opus-tier model for complex reasoning and agentic coding (Bedrock Inference Profile)

VisionTools / functions
1M · in $5 · out $25

Claude Opus 4.7

Apr 2026

Previous most capable model for complex reasoning and agentic coding (Bedrock Inference Profile)

VisionTools / functions
1M · in $5 · out $25

Claude Sonnet 4.6

Feb 2026

Best combination of speed and intelligence for everyday tasks (Bedrock Inference Profile)

VisionTools / functions
1M · in $3 · out $15

Claude Opus 4.6

Feb 2026

Previous most intelligent model for complex agents and coding, with adaptive thinking (Bedrock Inference Profile)

VisionTools / functions
1M · in $5 · out $25

Claude Opus 4.5

Nov 2025

Previous most intelligent model with advanced reasoning for complex agentic workflows (Bedrock Inference Profile)

VisionTools / functions
200K · in $5 · out $25

Claude Haiku 4.5

Oct 2025

Fastest model with exceptional speed and performance (Bedrock Inference Profile)

VisionTools / functions
200K · in $1 · out $5

Claude Sonnet 4.5

Sep 2025

Previous best combination of speed and intelligence for complex agents and coding (Bedrock Inference Profile)

VisionTools / functions
200K · in $3 · out $15

Claude Opus 4.1

deprecated
Aug 2025

Previous Opus model. Deprecated June 5, 2026, retiring August 5, 2026. (Bedrock Inference Profile)

VisionTools / functions
200K · in $15 · out $75

Claude Sonnet 4 [Retired]

May 2025

High-performance model. Retired June 15, 2026 (except on Bedrock and Vertex AI). (Bedrock Inference Profile)

VisionTools / functions
200K · in $3 · out $15

�️ Claude Haiku 3 [Retired]

Mar 2024

Fast and compact model for near-instant responsiveness. Retired April 20, 2026. (Bedrock Foundation Model)

VisionTools / functions
200K · in $0.25 · out $1.25

DeepSeek V3.2

-

DeepSeek model via OpenAI-Compatible API (Bedrock Foundation Model)

164K · in - · out -

GPT-OSS 20B

-

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Mistral AI Mistral Large 3

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
262K · in - · out -

Amazon Nova 2 Lite

-

Amazon model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Moonshot AI Kimi K2.5

-

Moonshot AI model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
262K · in - · out -

Writer Palmyra Vision 7B

-

Writer model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
4K · in - · out -

Z.AI GLM 4.7 Flash

-

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

203K · in - · out -

Google Gemma 4 E2b

-

Google model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Google Gemma 4 26b A4b

-

Google model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Amazon Nova Micro

-

Amazon model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Qwen3 Next 80B A3B

-

Qwen model via Converse API (Bedrock Foundation Model)

Tools / functions
262K · in - · out -

Amazon Nova Pro

-

Amazon model via Converse API (Bedrock Foundation Model)

VisionTools / functions
10K · in - · out -

OpenAI gpt-oss-120b

-

OpenAI model via Converse API (Bedrock Foundation Model)

Tools / functions
128K · in - · out -

Google Gemma 4 31b

-

Google model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

AI21 Labs Jamba 1.5 Large

-

AI21 Labs model via Unsupported API (Bedrock Foundation Model)

- · in - · out -

Cohere Command R+

-

Cohere model via Unsupported API (Bedrock Foundation Model)

- · in - · out -

MiniMax M2

-

MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)

Reasoning
410K · in - · out -

Cohere Command R

-

Cohere model via Unsupported API (Bedrock Foundation Model)

- · in - · out -

GPT-OSS 120B

-

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Amazon Nova Lite

-

Amazon model via Converse API (Bedrock Foundation Model)

VisionTools / functions
- · in - · out -

Writer Palmyra X5

-

Writer model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Google Gemma 3 12B IT

-

Google model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
131K · in - · out -

Mistral AI Devstral 2 123B

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

262K · in - · out -

Google Gemma 3 4B IT

-

Google model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
131K · in - · out -

Qwen3 Coder Next

-

Qwen model via OpenAI-Compatible API (Bedrock Foundation Model)

262K · in - · out -

Writer Palmyra X4

-

Writer model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

MiniMax M2.1

-

MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)

Reasoning
197K · in - · out -

Openai Gpt 5.4

-

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Qwen3 32B (dense)

-

Qwen model via Converse API (Bedrock Foundation Model)

Tools / functions
33K · in - · out -

Qwen3 VL 235B A22B

-

Qwen model via Converse API (Bedrock Foundation Model)

VisionTools / functions
262K · in - · out -

OpenAI gpt-oss-20b

-

OpenAI model via Converse API (Bedrock Foundation Model)

Tools / functions
128K · in - · out -

Google Gemma 3 27B PT

-

Google model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
131K · in - · out -

Qwen3 VL 235B

-

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

Vision
131K · in - · out -

Xai Grok 4.3

-

Xai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Mistral Pixtral Large 25.02

-

Mistral model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

DeepSeek V3.1

-

Deepseek model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Meta Llama 4 Maverick 17B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Mistral AI Ministral 3 8B

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
262K · in - · out -

Meta Llama 3.1 70B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Moonshot AI Kimi K2 Thinking

-

Moonshot AI model via Converse API (Bedrock Foundation Model)

ReasoningTools / functions
262K · in - · out -

Qwen3 Next 80B

-

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Meta Llama 3.2 1B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Meta Llama 3 8B Instruct

-

Meta model via Converse API (Bedrock Foundation Model)

Tools / functions
- · in - · out -

Anthropic Claude 3 Sonnet · US

-

Anthropic model (Bedrock Inference Profile)

VisionTools / functions
200K · in - · out -

Twelvelabs TwelveLabs Marengo Embed 3.0

-

Twelvelabs model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Z.AI GLM 5

-

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

203K · in - · out -

MiniMax M2.5

-

MiniMax model via OpenAI-Compatible API (Bedrock Foundation Model)

Reasoning
197K · in - · out -

Cohere Embed v4

-

Cohere model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Openai Gpt 5.5 2026 04 23

-

Openai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Mistral AI Ministral 3B

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
262K · in - · out -

Qwen3 Coder 30B

-

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Qwen3 32B

-

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Mistral AI Voxtral Small 24B 2507

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

33K · in - · out -

Mistral AI Ministral 14B 3.0

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
262K · in - · out -

Meta Llama 3.2 3B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Kimi K2 Thinking

-

Moonshotai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

NVIDIA Nemotron Nano 12B v2 VL BF16

-

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

Vision
131K · in - · out -

Mistral AI Mistral Small (24.02)

-

Mistral AI model via Converse API (Bedrock Foundation Model)

Tools / functions
- · in - · out -

Meta Llama 3.3 70B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Mistral AI Mistral 7B Instruct

-

Mistral AI model via Converse API (Bedrock Foundation Model)

Tools / functions
- · in - · out -

Qwen3 Coder 480B

-

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Meta Llama 3.2 11B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Meta Llama 3.2 90B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

NVIDIA Nemotron 3 Super 120B A12B

-

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

262K · in - · out -

Anthropic Claude Haiku 4 5

-

Anthropic model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

OpenAI GPT OSS Safeguard 120B

-

OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)

Reasoning
131K · in - · out -

Deepseek DeepSeek-R1

-

Deepseek model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Qwen3 235B A22B

-

Qwen model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Mistral AI Magistral Small 2509

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

VisionReasoning
131K · in - · out -

Mistral AI Mistral Large (24.02)

-

Mistral AI model via Converse API (Bedrock Foundation Model)

Tools / functions
- · in - · out -

Meta Llama 3.1 8B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Meta Llama 4 Scout 17B Instruct

-

Meta model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Meta Llama 3 70B Instruct

-

Meta model via Converse API (Bedrock Foundation Model)

Tools / functions
- · in - · out -

Mistral AI Mixtral 8x7B Instruct

-

Mistral AI model via Converse API (Bedrock Foundation Model)

Tools / functions
- · in - · out -

Z.AI GLM 4.7

-

Z.AI model via OpenAI-Compatible API (Bedrock Foundation Model)

203K · in - · out -

Twelvelabs Pegasus v1.2

-

Twelvelabs model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

Twelvelabs TwelveLabs Marengo Embed v2.7

-

Twelvelabs model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -

NVIDIA Nemotron Nano 9B v2

-

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

131K · in - · out -

OpenAI GPT OSS Safeguard 20B

-

OpenAI model via OpenAI-Compatible API (Bedrock Foundation Model)

Reasoning
131K · in - · out -

Mistral AI Voxtral Mini 3B 2507

-

Mistral AI model via OpenAI-Compatible API (Bedrock Foundation Model)

33K · in - · out -

GLM 4.6

-

Zai model via OpenAI-Compatible API on AWS Bedrock Mantle

131K · in - · out -

Qwen3-Coder-30B-A3B-Instruct

-

Qwen model via Converse API (Bedrock Foundation Model)

Tools / functions
262K · in - · out -

AI21 Labs Jamba 1.5 Mini

-

AI21 Labs model via Unsupported API (Bedrock Foundation Model)

- · in - · out -

NVIDIA Nemotron Nano 3 30B

-

NVIDIA model via OpenAI-Compatible API (Bedrock Foundation Model)

262K · in - · out -

Amazon Nova Premier

-

Amazon model via Converse API (Bedrock Inference Profile)

Tools / functions
- · in - · out -
97 models · sorted by release date · prices in USD per 1M tokens · refreshed every 30 minutesCompare every model across vendors →

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 and classic IAM credential trios, signing every request with real SigV4 in your browser or at the edge.
  • 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 is open source and self-hostable, so you can check exactly how AWS Bedrock is called.

Launch Big-AGI

Models

Alibaba

Anthropic

AWS Bedrock

Cerebras

DeepSeek

Fireworks AI

Google Gemini

MiniMax

Mistral

Moonshot

OpenAI

OpenRouter

Sakana AI

Together AI

xAI

Z.ai

BIG-AGI

Product

FeaturesModelsChangelogBEAM Technology

Resources

DocumentationDiscordGitHub

Company

Email UsPrivacyTerms

© 2026 Token Fabrics·Built with passion in San Diego