AWS Bedrock Provider
AWS Bedrock provides access to multiple foundation models from different providers through a single API. Includes models from Anthropic, Meta, Cohere, AI21, Amazon, and more with enterprise-grade security and compliance.
Cohere embedding models are detected both as direct model IDs such as cohere.embed-v4 and cross-region inference profile IDs such as us.cohere.embed-v4:0. The request body uses the Cohere embedding shape in both cases.
Setup
Installation
The AWS Bedrock provider is included in the Go AI SDK:
import (
"github.com/digitallysavvy/go-ai/pkg/ai"
"github.com/digitallysavvy/go-ai/pkg/providers/bedrock"
)
Configuration
provider := bedrock.New(bedrock.Config{
Region: "us-east-1",
AWSAccessKeyID: os.Getenv("AWS_ACCESS_KEY_ID"),
AWSSecretAccessKey: os.Getenv("AWS_SECRET_ACCESS_KEY"),
})
model, err := provider.LanguageModel("anthropic.claude-sonnet-5-5")
if err != nil {
log.Fatal(err)
}
Get Started
- Sign up for AWS account at aws.amazon.com
- Request model access in Bedrock Console
- Create IAM user with Bedrock permissions
- Set environment variables:
export AWS_ACCESS_KEY_ID=AKIA...
export AWS_SECRET_ACCESS_KEY=...
export AWS_REGION=us-east-1
Available Models
Use the constants in pkg/providers/bedrock/model_ids.go instead of raw strings. Availability and pricing vary by AWS Region. See the Amazon Bedrock model catalog and pricing page.
Anthropic Claude models
| Model ID | Go constant |
|---|---|
anthropic.claude-opus-5-5 | bedrock.ModelAnthropicClaudeOpus5_5 |
anthropic.claude-opus-5 | bedrock.ModelAnthropicClaudeOpus5 |
anthropic.claude-sonnet-5-5 | bedrock.ModelAnthropicClaudeSonnet5_5 |
anthropic.claude-sonnet-5 | bedrock.ModelAnthropicClaudeSonnet5 |
anthropic.claude-fable-5-1 | bedrock.ModelAnthropicClaudeFable5_1 |
anthropic.claude-fable-5 | bedrock.ModelAnthropicClaudeFable5 |
anthropic.claude-opus-4-8 | bedrock.ModelAnthropicClaudeOpus4_8 |
anthropic.claude-opus-4-7 | bedrock.ModelAnthropicClaudeOpus4_7 |
anthropic.claude-sonnet-4-6-v1 | bedrock.ModelAnthropicClaudeSonnet4_6V1 |
anthropic.claude-haiku-4-5-20251001-v1:0 | bedrock.ModelAnthropicClaudeHaiku45_V1 |
Cross-region inference profiles use a prefix, for example us.anthropic.claude-sonnet-5-5 (bedrock.ModelUSAnthropicClaudeSonnet5_5), eu.anthropic.claude-opus-4-8 and global.anthropic.claude-fable-5-1. Earlier Claude generations also have constants.
Amazon models
| Model ID | Go constant |
|---|---|
us.amazon.nova-2-lite-v1:0 | bedrock.ModelAmazonNova2LiteV1 |
us.amazon.nova-premier-v1:0 | bedrock.ModelAmazonNovaPremierV1 |
us.amazon.nova-pro-v1:0 | bedrock.ModelAmazonNovaProV1 |
us.amazon.nova-lite-v1:0 | bedrock.ModelAmazonNovaLiteV1 |
us.amazon.nova-micro-v1:0 | bedrock.ModelAmazonNovaMicroV1 |
amazon.titan-text-express-v1 | bedrock.ModelAmazonTitanTextExpressV1 |
Meta Llama models
| Model ID | Go constant |
|---|---|
us.meta.llama4-maverick-17b-instruct-v1:0 | bedrock.ModelUSMetaLlama4Maverick17BInstructV1 |
us.meta.llama4-scout-17b-instruct-v1:0 | bedrock.ModelUSMetaLlama4Scout17BInstructV1 |
us.meta.llama3-3-70b-instruct-v1:0 | bedrock.ModelUSMetaLlama3370BInstructV1 |
meta.llama3-1-405b-instruct-v1:0 | bedrock.ModelMetaLlama31405BInstructV1 |
meta.llama3-2-90b-instruct-v1:0 | bedrock.ModelMetaLlama3290BInstructV1 |
Other language models
| Model ID | Go constant |
|---|---|
cohere.command-r-plus-v1:0 | bedrock.ModelCohereCommandRPlusV1 |
cohere.command-r-v1:0 | bedrock.ModelCohereCommandRV1 |
mistral.mistral-large-2402-v1:0 | bedrock.ModelMistralLarge2402V1 |
us.mistral.pixtral-large-2502-v1:0 | bedrock.ModelUSMistralPixtralLarge2502V1 |
openai.gpt-oss-120b-1:0 | bedrock.ModelOpenAIGPTOSS120B |
us.deepseek.r1-v1:0 | bedrock.ModelUSDeepSeekR1V1 |
Embedding models
| Model ID | Dimensions | Best for |
|---|---|---|
amazon.titan-embed-text-v2:0 | 1024 | General embeddings |
cohere.embed-english-v3 | 1024 | English text |
cohere.embed-multilingual-v3 | 1024 | Multilingual |
Image generation
| Model ID | Best for |
|---|---|
amazon.titan-image-generator-v2:0 | General images |
stability.stable-diffusion-xl-v1 | Artistic |
Provider-Specific Features
Model Access Control
Request access to models in the Bedrock Console before calling them; the SDK does not expose an API to list or manage model access.
Cross-Region Inference
Cross-region inference profiles are plain model IDs with a region prefix (e.g. us., eu., or no prefix for global profiles) — pass the profile ID directly to LanguageModel, there is no separate config field:
provider := bedrock.New(bedrock.Config{
Region: "us-east-1",
AWSAccessKeyID: os.Getenv("AWS_ACCESS_KEY_ID"),
AWSSecretAccessKey: os.Getenv("AWS_SECRET_ACCESS_KEY"),
})
model, err := provider.LanguageModel("us.anthropic.claude-sonnet-5-5")
Guardrails
Apply AWS Bedrock Guardrails for content filtering:
result, err := ai.GenerateText(ctx, ai.GenerateTextOptions{
Model: model,
Prompt: prompt,
ProviderOptions: map[string]interface{}{
"amazonBedrock": map[string]interface{}{
"guardrailIdentifier": "your-guardrail-id",
"guardrailVersion": "1",
},
},
})
Examples
Basic Text Generation
package main
import (
"context"
"fmt"
"log"
"os"
"github.com/digitallysavvy/go-ai/pkg/ai"
"github.com/digitallysavvy/go-ai/pkg/providers/bedrock"
)
func main() {
ctx := context.Background()
provider := bedrock.New(bedrock.Config{
Region: "us-east-1",
AWSAccessKeyID: os.Getenv("AWS_ACCESS_KEY_ID"),
AWSSecretAccessKey: os.Getenv("AWS_SECRET_ACCESS_KEY"),
})
model, err := provider.LanguageModel("anthropic.claude-sonnet-5-5")
if err != nil {
log.Fatal(err)
}
result, err := ai.GenerateText(ctx, ai.GenerateTextOptions{
Model: model,
Prompt: "Explain AWS Bedrock benefits",
})
if err != nil {
log.Fatal(err)
}
fmt.Println(result.Text)
}
Multi-Model Comparison
models := []string{
"anthropic.claude-sonnet-5-5",
"us.meta.llama3-3-70b-instruct-v1:0",
"cohere.command-r-plus-v1:0",
}
prompt := "Write a haiku about clouds"
for _, modelID := range models {
model, err := provider.LanguageModel(modelID)
if err != nil {
log.Printf("Failed to load %s: %v", modelID, err)
continue
}
result, err := ai.GenerateText(ctx, ai.GenerateTextOptions{Model: model, Prompt: prompt})
if err != nil {
log.Printf("Failed to generate with %s: %v", modelID, err)
continue
}
fmt.Printf("\n=== %s ===\n%s\n", modelID, result.Text)
}
Image Generation with Titan
imageModel, err := provider.ImageModel("amazon.titan-image-generator-v2:0")
if err != nil {
log.Fatal(err)
}
result, err := ai.GenerateImage(ctx, ai.GenerateImageOptions{
Model: imageModel,
Prompt: "A serene mountain landscape at sunset",
Size: "1024x1024",
})
if err != nil {
log.Fatal(err)
}
// Save image
os.WriteFile("output.png", result.Images[0].Data, 0644)
Embeddings with Cohere
embeddingModel, err := provider.EmbeddingModel("cohere.embed-english-v3")
if err != nil {
log.Fatal(err)
}
texts := []string{
"AWS Bedrock provides access to foundation models",
"Amazon offers cloud computing services",
"Machine learning powers AI applications",
}
result, err := ai.EmbedMany(ctx, ai.EmbedManyOptions{
Model: embeddingModel,
Inputs: texts,
})
if err != nil {
log.Fatal(err)
}
fmt.Printf("Generated %d embeddings\n", len(result.Embeddings))
Streaming with Claude
model, err := provider.LanguageModel("anthropic.claude-sonnet-5-5")
if err != nil {
log.Fatal(err)
}
stream, err := ai.StreamText(ctx, ai.StreamTextOptions{Model: model, Prompt: "Write a detailed essay about serverless computing"})
if err != nil {
log.Fatal(err)
}
defer stream.Close()
for chunk := range stream.Chunks() {
fmt.Print(chunk.Text)
}
Advanced Configuration
IAM Role Authentication
// Use IAM role credentials (for EC2, ECS, Lambda)
provider := bedrock.New(bedrock.Config{
Region: "us-east-1",
// Credentials automatically loaded from IAM role
})
Session Token (STS)
provider := bedrock.New(bedrock.Config{
Region: "us-east-1",
AWSAccessKeyID: os.Getenv("AWS_ACCESS_KEY_ID"),
AWSSecretAccessKey: os.Getenv("AWS_SECRET_ACCESS_KEY"),
SessionToken: os.Getenv("AWS_SESSION_TOKEN"),
})
When explicit credentials are provided, the provider uses the explicit SessionToken value only. It does not merge in AWS_SESSION_TOKEN from the environment unless credentials are being resolved from the environment, matching the TypeScript credential precedence.
Custom Endpoint
provider := bedrock.New(bedrock.Config{
Region: "us-east-1",
BaseURL: "https://bedrock-runtime.us-east-1.amazonaws.com",
})
Reasoning and Structured Output
Bedrock drops reasoning blocks that belong to a foreign provider before request signing, so unsigned provider-specific reasoning is not forwarded accidentally. When top-level reasoning is set, custom reasoning configuration properties are merged into the Bedrock request instead of replacing the reasoning config.
Anthropic-on-Bedrock supports native structured output when reasoning is not enabled. The SDK preserves empty text blocks that accompany reasoning content, matching the TypeScript content-shape behavior required by Claude reasoning models.
model, _ := provider.LanguageModel("anthropic.claude-opus-4-7")
// invoiceSchema is a schema.Schema, e.g. schema.NewSimpleJSONSchema(map[string]interface{}{...}).
result, err := ai.GenerateObject(ctx, ai.GenerateObjectOptions{
Model: model,
Prompt: "Extract the invoice total.",
Schema: invoiceSchema,
})
Error Handling
Common Errors
Bedrock surfaces errors as *providererrors.ProviderError, like every other provider. AWS's exception type is folded into Message as "{type}: {message}" (there is no separate error-code field), so match on the message prefix:
result, err := ai.GenerateText(ctx, ai.GenerateTextOptions{Model: model, Prompt: prompt})
if err != nil {
var providerErr *providererrors.ProviderError
if errors.As(err, &providerErr) {
switch {
case strings.HasPrefix(providerErr.Message, "AccessDeniedException"):
log.Fatal("Access denied - check IAM permissions")
case strings.HasPrefix(providerErr.Message, "ResourceNotFoundException"):
log.Fatal("Model not found - request access in Bedrock console")
case strings.HasPrefix(providerErr.Message, "ThrottlingException"):
log.Println("Throttled, retrying...")
time.Sleep(time.Second * 5)
case strings.HasPrefix(providerErr.Message, "ValidationException"):
log.Printf("Invalid request: %s", providerErr.Message)
case strings.HasPrefix(providerErr.Message, "ModelNotReadyException"):
log.Println("Model still loading, retry later")
case strings.HasPrefix(providerErr.Message, "ServiceQuotaExceededException"):
log.Fatal("Quota exceeded - request limit increase")
default:
log.Printf("Bedrock error (%d): %s", providerErr.StatusCode, providerErr.Message)
}
}
}
IAM Permission Requirements
Minimum IAM policy for Bedrock:
{
"Version": "2012-10-17",
"Statement": [
{
"Effect": "Allow",
"Action": [
"bedrock:InvokeModel",
"bedrock:InvokeModelWithResponseStream"
],
"Resource": "arn:aws:bedrock:*::foundation-model/*"
}
]
}
Best Practices
-
Model Selection
- Use Claude for complex reasoning and analysis
- Use Llama for cost-effective open-source alternative
- Use Titan for AWS-native integration
- Use Cohere for RAG and search applications
-
Cost Management
- Compare prices across providers
- Use smaller models for simple tasks
- Monitor usage with AWS Cost Explorer
- Set up billing alerts
-
Security
- Use IAM roles instead of access keys
- Apply least privilege IAM policies
- Enable CloudTrail logging
- Use VPC endpoints for private access
-
Performance
- Choose region closest to users
- Use cross-region inference for high availability
- Implement caching for repeated queries
- Use streaming for long responses
-
Compliance
- Review model provider compliance certifications
- Use Guardrails for content filtering
- Enable logging for audit trails
- Configure data retention policies
Rate Limits & Pricing
Rate Limits
Varies by model and region:
| Model Family | Default Tokens/Min | Burst |
|---|---|---|
| Claude | 100K - 400K | 200K |
| Llama | 200K - 800K | 400K |
| Titan | 400K - 1.6M | 800K |
Request quota increases through AWS Support.
Pricing
Pricing varies by model and AWS Region. See the Amazon Bedrock pricing page.
See Also
- API Reference: GenerateText
- Anthropic Provider - Direct Anthropic access
- AWS Bedrock Documentation
- Bedrock Model Access
May 2026 parity updates
Credential precedence
Explicit credentials in bedrock.Config take precedence over environment and shared credential file values. When AWSAccessKeyID and AWSSecretAccessKey are set, AWS_SESSION_TOKEN is not used unless SessionToken is also explicitly configured.
Reasoning and structured output
bedrock.ModelOptions.ReasoningConfig mirrors the TypeScript amazonBedrock.reasoningConfig option. Partial provider configs merge with top-level Reasoning. Foreign-provider reasoning blocks are dropped rather than sent unsigned.
budget := 4096
model, err := p.LanguageModelWithOptions("anthropic.claude-opus-4-7", &bedrock.ModelOptions{
ReasoningConfig: &bedrock.ReasoningConfig{
Type: "enabled",
BudgetTokens: &budget,
},
ServiceTier: "priority",
})
Transport behavior
The TypeScript lazy fetch resolution change has no direct Go runtime equivalent. The Go provider uses its AWS signing request path and explicit configuration fields; no application migration is required for JavaScript fetch patching behavior.
requestMetadata
Pass providerOptions.amazonBedrock.requestMetadata (a map[string]string) to attach key-value pairs to a Converse/ConverseStream request for invocation-log cost attribution:
_, err := ai.GenerateText(ctx, ai.GenerateTextOptions{
Model: model,
Prompt: "hello",
ProviderOptions: map[string]interface{}{
"amazonBedrock": map[string]interface{}{
"requestMetadata": map[string]interface{}{"team": "search", "environment": "prod"},
},
},
})
It is forwarded as a top-level requestMetadata field on the request body, separate from additionalModelRequestFields.
Nova 2 Lite high reasoning
amazon.nova-2-lite-v1:0 rejects a request that combines maxOutputTokens with high/xhigh/max reasoning effort. The provider now drops inferenceConfig.maxTokens and returns an unsupported warning for maxOutputTokens instead of sending a request Bedrock would reject; medium (and lower) reasoning keeps maxOutputTokens unchanged.
Region validation
Region (and Bedrock Mantle's Region) is interpolated directly into the request host (https://bedrock-runtime.{region}.amazonaws.com, https://bedrock-mantle.{region}.api.aws). A value that isn't a single DNS label (letters, digits, and hyphens) is rejected with an InvalidArgumentError before any request is sent — this only applies when no explicit BaseURL or endpoint environment variable is configured, since those make Region unused.