Claude Opus 5

The AI Opus 5 API is a high-reasoning model featuring a 1M token context window and native visual PDF analysis. Built by Anthropic for complex autonomous agents, it offers frontier-tier intelligence at standard Opus pricing via GPTProto.com.

Modalities

Context

API Usage Examples

curl --request POST "https://gptproto.com/v1/chat/completions" \
  --header "Authorization: Bearer $GPTPROTO_API_KEY" \
  --header "Content-Type: application/json" \
  --data '{
    "model": "claude-opus-5",
    "messages": [
      {
        "role": "user",
        "content": "Hello"
      }
    ]
  }'

Claude Opus 5 pricing

Estimate a request with real work scenarios. GPTProto token pricing is 10% below official rates.

UsageQuantityRateCost

Input tokens($4.5/1M)

tokens

$4.5/1M$0.0067

Output tokens($22.5/1M)

tokens

$22.5/1M$0.018

Cache write tokens($5.625/1M)

tokens

$5.625/1M$0.0168

Cache read tokens($0.45/1M)

tokens

$0.45/1M$0.0112

Cost per request$0.0528

Requests

Top-up amount

Top-up $100 and you get:

Top-up credits with permanent validity. You will receive a total of $100.00.

Additional 10% model discount, saving $11.0962 versus direct official Claude API calls.

Related Models

All Models

Claude Opus 5

Current

byClaude1M context$4.5/M input$22.5/M output

Hy4 Preview

byHunyuan$0.7923/M input$2.376/M output

GPT 6 Astra

byOpenAI1.05M context$8/M input$40/M output

Gemini 3.8 Flash

byGoogle1.05M context$0.9/M input$4.5/M output

Claude Fable 5.1

byClaude1M context$9/M input$45/M output

Qwen3.8 Max 0902

byQwen1M context$1.8/M input$5.4/M output

GLM 5.3 Flash

byZ-AI1.31M context$0.15/M input$0.5/M output

DeepSeek v4 Flash Vision Exp

byDeepSeek1.05M context$0.44/M input$1.32/M output

GLM 5.3

byZ-AI1.31M context$1.26/M input$3.96/M output

Gemini 3.7 Flash

byGoogle1.05M context$0.9/M input$4.5/M output

Grok 4.6

byGrok500K context$1.2/M input$3.6/M output

Qwen3.8 Max

byQwen1M context$1.8/M input$5.4/M output

Gemini 3.6 Flash

byGoogle1.05M context$0.9/M input$4.5/M output

Kimi K3

byMoonshotAI1.05M context$2.7/M input$13.5/M output

GPT 5.6 Luna

byOpenAI1.05M context$0.16/M input$0.96/M output

GPT 5.6 Terra

byOpenAI1.05M context$1.6/M input$9.6/M output

Grok 4.5

byGrok500K context$1.2/M input$3.6/M output

Claude Sonnet 5

byClaude1M context$1.8/M input$9/M output

MiniMax M3

byMiniMax1.05M context$0.48/M input$0.96/M output

GLM 5.2

byZ-AI1.05M context$1.26/M input$3.96/M output

Claude Fable 5

byClaude1M context$9/M input$45/M output

Qwen3.7 Max

byQwen1M context$0.36/M input$1.44/M output

Claude Opus 4.8 Thinking

byClaude1M context$4.5/M input$22.5/M output

Claude Opus 4.8

byClaude1M context$4.5/M input$22.5/M output

DeepSeek v4 Flash

byDeepSeek1.05M context$0.374/M input$1.122/M output

DeepSeek v4 Pro

byDeepSeek1.05M context$1.122/M input$3.366/M output

Grok 4.3

byGrok1M context$0.75/M input$1.5/M output

Kimi K2.6

byMoonshotAI262K context$0.855/M input$3.6/M output

Claude Opus 4.7 Thinking

byClaude1M context$4.5/M input$22.5/M output

MiniMax M2.5

byMiniMax205K context$0.24/M input$0.96/M output

Kimi K2.5

byMoonshotAI262K context$0.54/M input$2.7/M output

Doubao Seed 1.6 Thinking (Build 250715)

byBytedance262K context$0.0971/M input$0.9714/M output

Doubao Seed 1.6 Thinking (Build 250615)

byBytedance262K context$0.0971/M input$0.9714/M output

Doubao Seed 1.6 Flash (Build 250615)

byBytedance262K context$0.0182/M input$0.1821/M output

Model					Input → Output
Claude Opus 5Current $		1M	$4.50 / $22.50 per 1M	$5.63 / $0.45 per 1M	Input: TextInput: ImageInput: Document Output: Text
Hy4 Preview $		—	$0.79 / $2.38 per 1M	— / $0.04 per 1M	Input: Text Output: Text
GPT 6 Astra $		1.05M	$8.00 / $40.00 per 1M	$10.00 / $0.80 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.8 Flash $		1.05M	$0.90 / $4.50 per 1M	$0.60 / $0.09 per 1M	Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text
Claude Fable 5.1 $		1M	$9.00 / $45.00 per 1M	$11.25 / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Qwen3.8 Max 0902 $		1M	$1.80 / $5.40 per 1M	$2.25 / $0.23 per 1M	Input: TextInput: ImageInput: VideoInput: DocumentInput: Audio Output: Text
GLM 5.3 Flash $	—	1.31M	$0.15 / $0.50 per 1M	— / $0.03 per 1M	Input: TextInput: ImageInput: VideoInput: Document Output: Text
DeepSeek v4 Flash Vision Exp $	—	1.05M	$0.44 / $1.32 per 1M	— / $0.01 per 1M	Input: TextInput: Image Output: Text
GLM 5.3 $		1.31M	$1.26 / $3.96 per 1M	— / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Gemini 3.7 Flash $		1.05M	$0.90 / $4.50 per 1M	$0.60 / $0.09 per 1M	Input: TextInput: ImageInput: Document Output: Text
Grok 4.6 $		500K	$1.20 / $3.60 per 1M	— / $0.30 per 1M	Input: TextInput: Image Output: Text
Qwen3.8 Max $		1M	$1.80 / $5.40 per 1M	$2.25 / $0.23 per 1M	Input: TextInput: ImageInput: VideoInput: Document Output: Text
Gemini 3.6 Flash $		1.05M	$0.90 / $4.50 per 1M	$0.60 / $0.09 per 1M	Input: TextInput: ImageInput: Document Output: Text
Kimi K3 $		1.05M	$2.70 / $13.50 per 1M	$0.27 / $0.27 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Luna $		1.05M	$0.16 / $0.96 per 1M	$0.20 / $0.02 per 1M	Input: TextInput: ImageInput: Document Output: Text
GPT 5.6 Terra $		1.05M	$1.60 / $9.60 per 1M	$2.00 / $0.16 per 1M	Input: TextInput: ImageInput: Document Output: Text
Grok 4.5 $		500K	$1.20 / $3.60 per 1M	$0.30 / $0.30 per 1M	Input: TextInput: Image Output: Text
Claude Sonnet 5 $		1M	$1.80 / $9.00 per 1M	$2.25 / $0.18 per 1M	Input: TextInput: Document Output: Text
MiniMax M3 $		1.05M	$0.48 / $0.96 per 1M	$0.10 / $0.10 per 1M	Input: TextInput: ImageInput: Document Output: Text
GLM 5.2 $		1.05M	$1.26 / $3.96 per 1M	$0.23 / $0.23 per 1M	Input: TextInput: ImageInput: Document Output: Text
Claude Fable 5 $		1M	$9.00 / $45.00 per 1M	$11.25 / $0.90 per 1M	Input: TextInput: Document Output: Text
Qwen3.7 Max $		1M	$0.36 / $1.44 per 1M	$0.07 / $0.07 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.8 Thinking $		1M	$4.50 / $22.50 per 1M	$5.63 / $0.45 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.8 $		1M	$4.50 / $22.50 per 1M	$5.63 / $0.45 per 1M	Input: TextInput: Document Output: Text
DeepSeek v4 Flash $		1.05M	$0.37 / $1.12 per 1M	— / $0.01 per 1M	Input: Text Output: Text
DeepSeek v4 Pro $		1.05M	$1.12 / $3.37 per 1M	— / $0.04 per 1M	Input: Text Output: Text
Grok 4.3 $		1M	$0.75 / $1.50 per 1M	$0.12 / $0.12 per 1M	Input: TextInput: Image Output: Text
Kimi K2.6 $		262K	$0.85 / $3.60 per 1M	$0.14 / $0.14 per 1M	Input: TextInput: Document Output: Text
Claude Opus 4.7 Thinking $		1M	$4.50 / $22.50 per 1M	$5.63 / $0.45 per 1M	Input: TextInput: Document Output: Text
MiniMax M2.5 $		205K	$0.24 / $0.96 per 1M	$0.30 / $0.02 per 1M	Input: TextInput: Document Output: Text
Kimi K2.5 $		262K	$0.54 / $2.70 per 1M	$0.09 / $0.09 per 1M	Input: TextInput: Document Output: Text
Doubao Seed 1.6 Thinking (Build 250715) $		262K	$0.10 / $0.97 per 1M	—	Input: TextInput: Image Output: Text
Doubao Seed 1.6 Thinking (Build 250615) $		262K	$0.10 / $0.97 per 1M	—	Input: TextInput: Image Output: Text
Doubao Seed 1.6 Flash (Build 250615) $		262K	$0.02 / $0.18 per 1M	—	Input: TextInput: Image Output: Text

AI Opus 5 API Standout Features

Discover the core technical capabilities that make the AI Opus 5 API the leader in reasoning-heavy agentic workflows.

1M Token AI Context

Process massive datasets with nearly perfect recall. This huge context window eliminates the need for complex RAG in many document synthesis tasks.

AI Agentic Persistence

Specifically tuned for long-horizon tasks where the model must iterate autonomously to overcome environment limitations or script errors.

Visual PDF AI Analysis

Native multimodal support allows the model to see charts, diagrams, and tables within PDFs, providing deeper document understanding than text alone.

Prompt Caching API

Save 90% on input costs for repeated long-context queries with a minimum cache size of just 512 tokens, making agents faster and cheaper.

AI Opus 5 API: Frequently Asked Questions

Find answers to common questions about the AI Opus 5 API, including technical specs, token pricing, and agentic capabilities for enterprise deployments at scale.

How does the AI Opus 5 API handle reasoning latency?

Without thinking mode enabled, the AI Opus 5 API latency matches the previous generation. When internal reasoning is active, time-to-first-token averages 2 to 4 seconds. This delay allows the model to perform test-time compute scaling, which significantly improves logic and reduces errors in complex coding or mathematical tasks. For users requiring sub-second response times, we recommend utilizing Fast Mode or our Auto-Fallback routing.

Is data from the AI Opus 5 API used for training?

No. When you access the AI Opus 5 API through GPTProto.com, your data is protected by enterprise-grade privacy standards. Anthropic does not use data sent via the API for training their models by default. This ensures that your proprietary codebases, financial documents, and sensitive customer information remain confidential and secure throughout the inference process, satisfying strict corporate compliance requirements.

What are the PDF processing limits for this AI model?

The AI Opus 5 API supports standard PDFs up to 32MB and 600 pages. For requests where the context window is under 1M tokens, the page limit is 100. Because this AI model uses vision capabilities to analyze documents, each page is processed as both text and image. For very dense documents with complex tables or small fonts, we suggest splitting the PDF into sections or using the Files API to avoid exceeding request size limits.

How does the AI Opus 5 API pricing compare to Fable?

The AI Opus 5 API offers frontier-level reasoning at exactly half the cost of Claude Fable 5. Input tokens are priced at $5.00 per 1M, and output tokens are $25.00 per 1M. This allows developers to build high-intelligence agents without the premium costs associated with standard frontier-tier models. Additionally, GPTProto users benefit from a 90% discount on prompt caching hits, significantly lowering costs for repeated long-context queries.

Does the AI Opus 5 API support tool use changes?

Yes, the AI Opus 5 API supports mid-conversation tool dynamic changes. Using the specific 2026-07-01 header, you can modify tool definitions between conversation turns without losing your prompt cache. This is ideal for multi-step agents that need to adapt their available functions based on the current state of a workflow, such as moving from data extraction tools to database write tools within a single long-running session.

Can the AI Opus 5 API analyze charts in PDFs?

Absolutely. Unlike basic text extraction models, the AI Opus 5 API features native multimodal vision. It converts PDF pages into images to understand visual layouts, charts, graphs, and diagrams. This makes it an ideal tool for financial analysis or visual engineering tasks where the meaning of the document is tied to its visual representation. To ensure full visual understanding, ensure your request is sent to the visual analysis endpoint.