Claude Opus 5.5

15% OFFanthropic/claude-opus-5.5

Claude Opus 5.5 is the most powerful model in the Claude 5 family from Anthropic. It excels at complex reasoning, analysis, and creative tasks with superior accuracy and nuance. It supports text, image, and file inputs with text output, reasoning support and a 1M-token context window.

Input price
$3.40$4.00USD / 1M tokens
Output price
$17.00$20.00USD / 1M tokens
Cache read
$0.17$0.20USD / 1M tokens
Cache write
$4.25$5.00USD / 1M tokens
Context window
1M
Max output
128K

Specifications

CapabilitiesChatVisionReasoningStructured outputFunction calling
Input
Text, image
Output
Text
Available

About this model

Claude Opus 5.5 is the largest model in Anthropic's Claude 5 family. It takes text and images, writes text, and has a 1M-token context window. Use it for the hard parts of a system: long-document analysis, multi-step agent work and code changes where a wrong answer costs more than the tokens.

When to use it

  • Agents that plan, call tools and recover from their own mistakes over many steps.
  • Reading a whole codebase, contract set or research corpus in one request.
  • Reviewing or rewriting work produced by cheaper models.

Call it

The model works on Chat Completions (/v1/chat/completions), so the OpenAI SDK only needs a new base URL. It also works on Anthropic's Messages API (/v1/messages), which you need for Messages-only features such as output_format, stop_sequences and cache_control.

from openai import OpenAI

client = OpenAI(base_url="https://api.sandbase.ai/v1", api_key="$SANDBASE_API_KEY")

resp = client.chat.completions.create(
    model="anthropic/claude-opus-5.5",
    messages=[{"role": "user", "content": "Explain what an API gateway does."}],
    max_tokens=512,
)
print(resp.choices[0].message.content)

What works on SandBase

Checked with real calls through SandBase on October 28, 2026.

FeatureWorksNotes
StreamingYesstream: true; the last chunk carries usage when stream_options.include_usage is set.
Tool callingYesOpenAI-style tools and tool_choice; returns tool_calls.
Image inputYesimage_url parts with an https URL or a data: URI.
Structured outputMessages API onlyOn Chat Completions response_format is ignored and the model answers in prose. On /v1/messages, output_format: {"type": "json_schema", "schema": …} returns JSON that matches the schema.
Stop sequencesMessages API onlyChat Completions rejects stop for this model with a 400. Use stop_sequences on /v1/messages.

Limits and parameters

  • Context window: 1,000,000 tokens.
  • Maximum output: 128,000 tokens per request (max_tokens).
  • top_p is rejected with "top_p is deprecated for this model". Use temperature (0 to 2) instead.
  • It counts more tokens for the same text than older Claude models: one 9,419-token system prompt on Claude Haiku 4.5 counted 13,320 input tokens on Opus 5.5. Budget cost and context from a real count, not an older estimate.

Example response

Real response to "In two sentences, explain what an API gateway does." through Chat Completions, trimmed.

{
  "id": "81ea378c-6a4…",
  "object": "chat.completion",
  "model": "anthropic/claude-opus-5.5",
  "choices": [
    {
      "index": 0,
      "finish_reason": "stop",
      "message": {
        "role": "assistant",
        "content": "An API gateway is a server that sits between clients and a collection of backend services, acting as a single entry point that receives API requests and routes…"
      }
    }
  ],
  "usage": {
    "completion_tokens": 120,
    "completion_tokens_details": {
      "reasoning_tokens": 0
    },
    "prompt_tokens": 24,
    "prompt_tokens_details": {
      "cache_write_tokens": 0,
      "cached_tokens": 0
    },
    "total_tokens": 144
  }
}

Pricing

TokensPrice per 1M
Input$4.00
Output$20.00
Cached input (read)$0.20
Cache write, 5-minute$5.00
Cache write, 1-hour$8.00

Prompt caching works through cache_control blocks on /v1/messages: the first call reports cache_creation_input_tokens, a repeat within the cache lifetime reports the same count as cache_read_input_tokens. Reads cost 5% of the input price.

Related models

Independent evaluations

Benchmarks

Scores on standardized evaluations, compared with other models on SandBase.

Metrics sourced from Artificial Analysis · Intelligence Index v5 · Updated 2026-11-13

Questions

FAQ

How do I call Anthropic Claude Opus 5.5 through SandBase?

Create a SandBase API key, then send requests with the model ID "anthropic/claude-opus-5.5" to Chat Completions API (/v1/chat/completions) or Messages API (/v1/messages) at https://api.sandbase.ai. The request examples on this page show the exact payload.

How much does Anthropic Claude Opus 5.5 cost?

$3.40 per 1M input tokens and $17 per 1M output tokens with the current 15% discount (list price $4 / $20), billed per request from your SandBase balance.

What is the context window of Anthropic Claude Opus 5.5?

1M tokens of context, with up to 128K output tokens per response.

How does Anthropic Claude Opus 5.5 score on benchmarks?

Anthropic Claude Opus 5.5 scores 59.1 on the Artificial Analysis Intelligence Index (v5), ranking #3 of 31 models on SandBase. Source: Artificial Analysis, measured as Claude Opus 5.5 (Max, Default Fallback).

Which features does Anthropic Claude Opus 5.5 support?

Anthropic Claude Opus 5.5 supports vision (image input), reasoning, function calling, structured output. See Specifications above for the full list.

Do I need a separate Anthropic account?

No. One SandBase API key and balance gives you access to Anthropic Claude Opus 5.5 and the other models in the catalog; you do not need to sign up with Anthropic separately.