Skip to content

feat(bedrock): full support for Claude Opus 4.7 (registry + API compat layer) #316

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
vandre-sales wants to merge 2 commits into
base: main
Choose a base branch
from
+66 −12
Open

feat(bedrock): full support for Claude Opus 4.7 (registry + API compat layer) #316

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
140867f
feat(bedrock): add anthropic.claude-opus-4-7 to native model registry
vandre-sales May 24, 2026
b917925
feat(bedrock): support Claude 4.7+ adaptive thinking and remove tempe…
May 24, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
27 changes: 27 additions & 0 deletions packages/types/src/providers/bedrock.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,6 +167,30 @@ export const bedrockModels = {
},
],
},
"anthropic.claude-opus-4-7": {
maxTokens: 8192,
contextWindow: 200_000, // Default 200K, extendable to 1M with beta flag 'context-1m-2025-08-07'
supportsImages: true,
supportsPromptCache: true,
supportsReasoningBudget: true,
inputPrice: 5.0, // $5 per million input tokens (≤200K context) — verify against Bedrock console
outputPrice: 25.0, // $25 per million output tokens (≤200K context) — verify against Bedrock console
cacheWritesPrice: 6.25, // $6.25 per million tokens
cacheReadsPrice: 0.5, // $0.50 per million tokens
minTokensPerCachePoint: 1024,
maxCachePoints: 4,
cachableFields: ["system", "messages", "tools"],
// Tiered pricing for extended context (requires beta flag 'context-1m-2025-08-07')
tiers: [
{
contextWindow: 1_000_000, // 1M tokens with beta flag
inputPrice: 10.0, // $10 per million input tokens (>200K context)
outputPrice: 37.5, // $37.50 per million output tokens (>200K context)
cacheWritesPrice: 12.5, // $12.50 per million tokens (>200K context)
cacheReadsPrice: 1.0, // $1.00 per million tokens (>200K context)
Comment on lines +176 to +190
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot May 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

🧩 Analysis chain

🌐 Web query:

What are the official Amazon Bedrock pricing rates for model ID "anthropic.claude-opus-4-7" (input, output, prompt cache write/read), including any 1M-context tier pricing and the exact effective date/region notes?

💡 Result:

Amazon Bedrock (model ID anthropic.claude-opus-4-7) pricing rates (standard on-demand inference): 1) Tokens - Input: $5.00 per 1M input tokens [1] - Output: $25.00 per 1M output tokens [1] 2) Prompt caching (cache write / cache read) - Cache read (hits): $0.50 per 1M input tokens (10% of standard input) [2] - Cache write: not directly published as $/token in the AWS prompt-caching doc we found, but Anthropic’s pricing multipliers indicate cache write is 1.25x base for 5-minute cache writes and 2x base for 1-hour cache writes, implying for Opus 4.7: - 5-minute cache write: $6.25 per 1M input tokens [2] - 1-hour cache write: $10.00 per 1M input tokens [2] 3) 1M-context tier pricing - No separate “1M-context tier” surcharge is listed in the sources found; Opus 4.7’s standard input/output rates apply for the 1M context window (i.e., context length doesn’t add a separate pricing tier in these sources). [2] 4) Exact effective date / region notes - AWS prompt caching is available in all AWS Regions where the supported models are available, but the caching page does not provide an “effective date” for the specific model’s rates in the content surfaced. [3] - The sources above do not provide an explicit effective date/region schedule for Bedrock pricing for anthropic.claude-opus-4-7; they only state the general availability and that you should use the Bedrock pricing page for the current per-model rates. [3] Note: Bedrock pricing can vary by region and by active features (on-demand vs batch vs provisioned throughput vs reserved tiers). For the “official” per-region numbers, you should verify directly on the Bedrock Pricing page for your selected region, since the AWS HTML pricing table content was not fully extractable from the sources we captured here. [4][3]

Citations:

🌐 Web query:

Bedrock pricing "anthropic.claude-opus-4-7" 1M context "context-1m" tier pricing input output cache write/read

💡 Result:

Bedrock model: anthropic.claude-opus-4-7; 1M context (“context-1m”) On-demand per 1M tokens (base prices) - Input: $5.00 / 1M input tokens [1][2] - Output: $25.00 / 1M output tokens [1][2] Prompt caching (Claude prompt caching multipliers; Bedrock is billed per-token using its pricing page, and the cache multipliers are defined by Claude’s pricing docs) - Cache write (5-minute TTL): 1.25× base input price [2] => $6.25 / 1M tokens [2] - Cache write (1-hour TTL): 2.0× base input price [2] => $10.00 / 1M tokens [2] - Cache read (hit): 0.1× base input price [2] => $0.50 / 1M tokens [2] Cache durations - Cache read (hit) tokens use the same duration as the preceding write [2]. Context window / “context-1m” - Claude Opus 4.7 is specified with a 1M context window and uses standard pricing across the 1M context window (caching/batch discounts apply at standard rates) [1][2]. If you share the AWS region plus whether you mean Bedrock on-demand vs Batch vs Provisioned Throughput, I can map these into the exact Bedrock line items for that configuration (the Bedrock model card points to the Bedrock pricing page for the definitive rates) [3].

Citations:

🌐 Web query:

"context-1m-2025-08-07" pricing claude opus bedrock

💡 Result:

For the Amazon Bedrock “Claude Opus” 1M-context beta variant identified by the header value context-1m-2025-08-07, the pricing works as follows: 1) How to enable the 1M context variant You must include the anthropic_beta parameter/header value “context-1m-2025-08-07” in your request body; otherwise you’re limited to the standard ~200K context window (and may get an error if you exceed 200K tokens). [1] 2) Base model pricing you will pay (on-demand) AWS Bedrock’s standard token pricing for Claude Opus is listed as: - Input: $5.00 per 1M input tokens - Output: $25.00 per 1M output tokens (These are the on-demand rates for the Opus model versions shown in sources.) [2][3] 3) What changes for long-context requests (premium pricing) AWS states (in its Bedrock/Claude long-context beta documentation) that for requests exceeding 200K input tokens, the long-context rate applies to the entire request (not only the tokens above the threshold). [4] Because AWS’s public “Bedrock pricing” page is dynamic by model/provider/region and does not show the long-context beta “context-1m-2025-08-07” premium multiplier directly in the sources I found, I cannot state the exact long-context premium percentage/multiplier for that specific beta value from AWS primary pricing text. Practical takeaway: expect the request to be billed at the long-context premium whenever your request exceeds 200,000 input tokens, and otherwise use the standard Opus $5 / $25 per 1M input/output token rates. [4][1] If you tell me your AWS region and which exact Opus model ID you’re calling in Bedrock (e.g., anthropic.claude-opus-4.x or opus-4.6 vs opus-4.7), I can re-check the Bedrock pricing page for the exact long-context token rates that apply there.

Citations:

🌐 Web query:

AWS Bedrock prompt caching cache write price multiplier 5-minute vs 1-hour

💡 Result:

Answer: For Amazon Bedrock prompt caching (Claude models that support 1-hour TTL), the cache-write price multiplier is 1.25x of the normal input price for the default 5-minute cache, and 2x of the normal input price for the 1-hour cache. Cache reads are ~0.1x of the normal input price in both cases. Evidence: - AWS Bedrock docs confirm the TTL options (5 minutes or 1 hour) are available for certain Claude 4.5 models, and that the default is 5 minutes when no ttl is provided.[1] - AWS “what’s new” notes that the 1-hour TTL is billed at a different rate than the standard 5-minute cache.[2] - Multiple sources that summarize the published Bedrock/Claude prompt-caching rate card state: 5-minute cache writes cost 1.25x base input, while 1-hour cache writes cost 2x base input, and cache reads cost 0.1x (90% discount) of base input.[3][4] So, the specific “multiplier” comparison you asked for is: - 1-hour cache write vs 5-minute cache write: 2x / 1.25x = 1.6x more expensive to write when using the 1-hour TTL. Notes: - This is about the cache-write rate (the token cost for “writing/creating/refreshing” a cached prompt prefix). The read rate (when the next request hits the cached prefix) stays much lower.[1][3][4]

Citations:

Fix unverified extended-context (context-1m) tier pricing for Opus 4.7

In packages/types/src/providers/bedrock.ts (lines ~176-190), the base on-demand rates ($5/$25 input/output) and prompt-caching rates (cacheReadsPrice: 0.5, cacheWritesPrice: 6.25) match published Claude prompt-caching multipliers (5-minute TTL) and the published Opus base pricing.

However, the extended-context tier values in tiers[0] (marked context-1m-2025-08-07 / >200K): inputPrice: 10.0, outputPrice: 37.5, cacheWritesPrice: 12.5, cacheReadsPrice: 1.0 are not backed by the Bedrock/Claude sources found; long-context beta “context-1m” pricing is not explicitly published in a way that establishes these exact numbers.

Replace the tiers[0] pricing with the exact official Bedrock long-context beta rates for anthropic.claude-opus-4-7 (or omit tiers until verified) to avoid incorrect cost reporting/budget UX for >200K requests.

For Amazon Bedrock, what are the official on-demand per-1M token rates for model ID "anthropic.claude-opus-4-7" when using the beta header value "context-1m-2025-08-07" (i.e., requests exceeding 200K input tokens): input $/1M, output $/1M, and prompt cache write/read $/1M (including the TTL/assumed cache type used for “cacheWritesPrice”/“cacheReadsPrice”)—and note any region differences and effective date?
🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@packages/types/src/providers/bedrock.ts` around lines 176 - 190, The
extended-context tier pricing in the Bedrock provider (the object inside
tiers[0] in packages/types/src/providers/bedrock.ts) is unverified and must not
be published as facts; either replace tiers[0] values with the exact official
Bedrock long‑context beta rates for model "anthropic.claude-opus-4-7" (including
inputPrice, outputPrice, cacheWritesPrice, cacheReadsPrice and any
TTL/assumptions) or remove the entire tiers entry until you can cite the Bedrock
source; update the surrounding comment that references the beta flag
"context-1m-2025-08-07" to reflect that rates were taken from the official
Bedrock source (or note omitted) and ensure you change only the tiers array (not
base inputPrice/outputPrice/cachePrices or cachableFields).

},
],
},
"anthropic.claude-opus-4-5-20251101-v1:0": {
maxTokens: 8192,
contextWindow: 200_000,
Expand Down Expand Up @@ -525,6 +549,7 @@ export const BEDROCK_1M_CONTEXT_MODEL_IDS = [
"anthropic.claude-sonnet-4-5-20250929-v1:0",
"anthropic.claude-sonnet-4-6",
"anthropic.claude-opus-4-6-v1",
"anthropic.claude-opus-4-7",
] as const

// Amazon Bedrock models that support Global Inference profiles
Expand All @@ -535,13 +560,15 @@ export const BEDROCK_1M_CONTEXT_MODEL_IDS = [
// - Claude Haiku 4.5
// - Claude Opus 4.5
// - Claude Opus 4.6
// - Claude Opus 4.7
export const BEDROCK_GLOBAL_INFERENCE_MODEL_IDS = [
"anthropic.claude-sonnet-4-20250514-v1:0",
"anthropic.claude-sonnet-4-5-20250929-v1:0",
"anthropic.claude-sonnet-4-6",
"anthropic.claude-haiku-4-5-20251001-v1:0",
"anthropic.claude-opus-4-5-20251101-v1:0",
"anthropic.claude-opus-4-6-v1",
"anthropic.claude-opus-4-7",
] as const

// Amazon Bedrock Service Tier types
Expand Down
51 changes: 39 additions & 12 deletions src/api/providers/bedrock.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -61,9 +61,20 @@ interface BedrockInferenceConfig {
// Define interface for Bedrock additional model request fields
// This includes thinking configuration, 1M context beta, and other model-specific parameters
interface BedrockAdditionalModelFields {
thinking?: {
type: "enabled"
budget_tokens: number
thinking?:
| {
type: "enabled"
budget_tokens: number
}
| {
// Claude 4.7+ adaptive thinking — no budget_tokens, uses output_config.effort instead
type: "adaptive"
// "summarized" shows thinking content in UI; omit to keep thinking internal only
display?: "summarized" | "none"
}
output_config?: {
// Claude 4.7+ effort levels: "low" | "medium" | "high" | "xhigh" | "max"
effort: string
}
anthropic_beta?: string[]
[key: string]: any // Add index signature to be compatible with DocumentType
Expand Down Expand Up @@ -381,6 +392,11 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH
let additionalModelRequestFields: BedrockAdditionalModelFields | undefined
let thinkingEnabled = false

// Detect model generation for API compatibility
// Claude 4.7+ removed sampling params (temperature/top_p/top_k) and uses adaptive thinking
const baseModelId = this.parseBaseModelId(modelConfig.id)
const isGen47Model = baseModelId.includes("opus-4-7") || baseModelId.includes("sonnet-4-7")
Comment on lines +395 to +398
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai Bot May 24, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟠 Major | ⚡ Quick win

🧩 Analysis chain

🏁 Script executed:

#!/bin/bash
set -euo pipefail

FILE="$(fd '^bedrock\.ts$' src/api/providers | head -n1)"

echo "== createMessage Claude 4.7 handling =="
sed -n '392,440p' "$FILE"

echo
echo "== completePrompt inferenceConfig =="
sed -n '764,779p' "$FILE"

Repository: Zoo-Code-Org/Zoo-Code

Length of output: 2877

Mirror the Claude 4.7+ temperature omission in completePrompt
createMessage already omits temperature for anthropic.claude-opus-4-7 / sonnet-4-7, but completePrompt still sets inferenceConfig.temperature unconditionally—so the single-completion path can still hit the same Bedrock 400 validation error.

Suggested fix 
+	private isClaude47Model(modelId: string): boolean {
+		const baseModelId = this.parseBaseModelId(modelId)
+		return baseModelId.includes("opus-4-7") || baseModelId.includes("sonnet-4-7")
+	}
+
 	override async *createMessage(
 		systemPrompt: string,
 		messages: Anthropic.Messages.MessageParam[],
@@
-		const baseModelId = this.parseBaseModelId(modelConfig.id)
-		const isGen47Model = baseModelId.includes("opus-4-7") || baseModelId.includes("sonnet-4-7")
+		const baseModelId = this.parseBaseModelId(modelConfig.id)
+		const isGen47Model = this.isClaude47Model(modelConfig.id)
@@
 	async completePrompt(prompt: string): Promise<string> {
 		try {
 			const modelConfig = this.getModel()
+			const isGen47Model = this.isClaude47Model(modelConfig.id)
@@
 			const inferenceConfig: BedrockInferenceConfig = {
 				maxTokens: modelConfig.maxTokens || (modelConfig.info.maxTokens as number),
-				temperature: modelConfig.temperature ?? (this.options.modelTemperature as number),
+				...(isGen47Model
+					? {}
+					: { temperature: modelConfig.temperature ?? (this.options.modelTemperature as number) }),
 			}
🤖 Prompt for AI Agents 
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.

In `@src/api/providers/bedrock.ts` around lines 395 - 398, completePrompt still
sets inferenceConfig.temperature unconditionally which will trigger Bedrock
validation for Claude 4.7+; mirror createMessage's behavior by detecting the
Gen47 models via parseBaseModelId / isGen47Model (same check used where
createMessage omits temperature) and avoid setting inferenceConfig.temperature
in completePrompt for those models (only set temperature for non-Gen47 paths),
ensuring the single-completion code path matches createMessage's omission.


// Determine if thinking should be enabled
// metadata?.thinking?.enabled: Explicitly enabled through API metadata (direct request)
// shouldUseReasoningBudget(): Enabled through user settings (enableReasoningEffort = true)
Expand All @@ -392,27 +408,38 @@ export class AwsBedrockHandler extends BaseProvider implements SingleCompletionH

if ((isThinkingExplicitlyEnabled || isThinkingEnabledBySettings) && modelConfig.info.supportsReasoningBudget) {
thinkingEnabled = true
additionalModelRequestFields = {
thinking: {
type: "enabled",
budget_tokens: metadata?.thinking?.maxThinkingTokens || modelConfig.reasoningBudget || 4096,
},
if (isGen47Model) {
// Claude 4.7+ uses adaptive thinking with effort levels — budget_tokens causes 400 error
// display: "summarized" surfaces thinking content in Zoo Code UI
additionalModelRequestFields = {
thinking: { type: "adaptive", display: "summarized" },
output_config: { effort: "xhigh" },
}
} else {
additionalModelRequestFields = {
thinking: {
type: "enabled",
budget_tokens: metadata?.thinking?.maxThinkingTokens || modelConfig.reasoningBudget || 4096,
},
}
}
logger.info("Extended thinking enabled for Bedrock request", {
ctx: "bedrock",
modelId: modelConfig.id,
thinking: additionalModelRequestFields.thinking,
thinking: additionalModelRequestFields?.thinking,
})
}

const inferenceConfig: BedrockInferenceConfig = {
maxTokens: modelConfig.maxTokens || (modelConfig.info.maxTokens as number),
temperature: modelConfig.temperature ?? (this.options.modelTemperature as number),
// Claude 4.7+ removed temperature parameter entirely — causes 400 error if sent
...(isGen47Model
? {}
: { temperature: modelConfig.temperature ?? (this.options.modelTemperature as number) }),
}

// Check if 1M context is enabled for supported Claude 4 models
// Use parseBaseModelId to handle cross-region inference prefixes
const baseModelId = this.parseBaseModelId(modelConfig.id)
// Use parseBaseModelId to handle cross-region inference prefixes (computed above)
const is1MContextEnabled =
BEDROCK_1M_CONTEXT_MODEL_IDS.includes(baseModelId as any) && this.options.awsBedrock1MContext

Expand Down
Loading