Back to models

Claude Opus 5

FeaturedAvailable Serverless
Anthropic•
Try this modelView documentation

Claude Opus 5 is Anthropic's flagship model for complex agentic coding and enterprise work. It pairs a 1M-token context window with up to 128K output tokens in a single response, and holds its reasoning quality across long, multi-step tasks. Access it through the DOS.AI gateway alongside every other supported model with one API key and unified billing.

Capabilities:Advanced reasoningBest-in-class codingVisionTool callingLong context (1M)
Use cases:Software engineeringComplex agentsResearchLong-horizon tasks
Modalities
Input / Output Price
$5.25/$26.25/ 1M
Context Length
1M tokens
Released
Jul 24, 2026

Providers

Different companies host the same model. DOS.AI routes your request to one of them based on the routing mode you pick — Balanced (price + speed), Nitro (fastest), or Exacto (highest tool-calling accuracy).

Reasoning effortⓘAll
ProviderInput /1MOutput /1MContext
Anthropic
$5.25$26.251M

Pricing

Transparent pass-through token pricing per million tokens. DOS.AI strictly enforces a Zero-Markup retail policy.

Input / Prompt
$5.25/ 1M tokens
Published official list price
Output / Completion
$26.25/ 1M tokens
Zero-markup retail rate
Prompt Cache Read
$0.525/ 1M tokens
Up to 90% cache discount
Context Window
1Mtokens
Full context window supported

Uptime & Reliability

Live upstream health and gateway reliability. Automatic multi-provider failover protects your production traffic.

All Endpoints Operational
SLA Target: 99.99%Last 30 Days: 100.0%
30 days ago100.0% uptime over past monthToday

Benchmarks & Evaluations

Standardized evaluations & blind battle ratings. Higher is better — rank percentile reflects position among frontier models on DOS.AI.

50.7
Top 3%
Artificial Analysis Intelligence Index
Better than 97% of models compared
78.0
Top 2%
Artificial Analysis Coding Index
Better than 98% of models compared
56.2
Top 2%
Artificial Analysis Agentic Index
Better than 98% of models compared

Reasoning

Complex multi-step logic, graduate-level science, and frontier reasoning

5 benchmarks
GPQA Diamondⓘ
93.2%
Graduate-level scientific reasoning
HLEⓘ
54.9%
Humanity's Last Exam frontier benchmark
AA-LCRⓘ
79.3%
Long context reasoning evaluation
GDPval-AAⓘ
61.8%
Economically valuable tasks & real-world workflows
CritPtⓘ
29.1%
Research-level physics reasoning

Coding

Autonomous repository bug fixing, algorithms, and scientific computation

4 benchmarks
SciCodeⓘ
56.4%
Python programming for scientific computing
SWE-bench Verifiedⓘ
68.8%
Autonomous multi-file bug fixing and test passage
HumanEvalⓘ
92.4%
Algorithmic code generation pass@1
LiveCodeBenchⓘ
65.2%
Recent competitive programming problem set

Knowledge & Reliability

Factual hallucination minimization, tool calling, and domain accuracy

4 benchmarks
AA-Omniscience Accuracyⓘ
60.9%
Proportion of correctly answered questions
AA-Omniscience Non-Hallucination Rateⓘ
39.2%
Rate of avoiding hallucination among non-correct responses
MMLU-Proⓘ
84.1%
Multi-discipline reasoning & higher education knowledge
Exacto BFCL Tool Callingⓘ
96.4%
Strict schema compliance and function execution

Multimodal & Diagram Reasoning

Multi-discipline diagram perception, document parsing, and visual math

3 benchmarks
MMMUⓘ
72.8%
College-level multi-discipline visual perception
MathVistaⓘ
69.4%
Mathematical problem solving with figures and geometry
DocVQAⓘ
93.5%
Structured tables, charts, and scanned document OCR
Standardized evaluations sourced from Artificial Analysis and open frontier model research benchmarks.

API Integration

Use the DOS API to integrate Claude Opus 5 into your applications. Compatible with standard OpenAI SDKs for easy drop-in migration.

</>Run inference
curl https://api.dos.ai/v1/chat/completions \
  -H "Authorization: Bearer $DOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "messages": [
      {
        "role": "user",
        "content": "Hello!"
      }
    ]
  }'
View full documentationGet API key

Explore Related Models

DOS.AI

Auto

DOS.AI Smart Router classifies each request by complexity. Simple and Medium requests use DOS.AI; Complex requests can use an eligible paid route configured in the live catalog.

Usage-based
DOS.AI

DOS

DOS curated meta-model for DOSClaw and first-party DOS products.

$0.07 / 1M tokens
DOS.AI

Qwen3.8-27B

DOS.AI hosted Qwen3.8-27B for reasoning, coding, tool use, and multilingual text generation.

$0.1125 / 1M tokens