Claude Sonnet 5.5

Claude Sonnet 5.5 (anthropic/claude-sonnet-5.5) is the update to the fifth-generation Sonnet: code, agentic and professional work. Besides the OpenAI-compatible POST /v1/chat/completions, the model is available over the Anthropic protocol POST /v1/messages — so it works in Claude Code and the Anthropic SDK directly, without adapters.

Parameters and capabilities

Parameter	Value
`model`	`anthropic/claude-sonnet-5.5`
Images on input	yes (`image_url`, data URLs)
Files on input	yes (PDF/DOCX/TXT etc., up to 5)
Reasoning	`reasoning_effort`: `low`, `medium`, `high`, `xhigh`, `max`; disabled with `off`
Native web search	yes — `web_search: "native"`
Cache read	$0.25 per 1M tokens
Cache write	$3.125 per 1M tokens

Cache read is exactly a tenth of the input price; write is ×1.25 — in a dense session the cache lives start to finish thanks to sliding renewal. Thinking is billed as output tokens and eats the max_tokens budget — see Context caching.

Examples

from openai import OpenAI

client = OpenAI(base_url="https://api.mixen.ai/v1", api_key="mxn-...")

resp = client.chat.completions.create(
    model="anthropic/claude-sonnet-5.5",
    messages=[{"role": "user", "content": "Analyze this crash log and find the root cause"}],
    reasoning_effort="high",
)
print(resp.choices[0].message.content)

curl https://api.mixen.ai/v1/chat/completions \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-sonnet-5.5",
    "messages": [{"role": "user", "content": "Analyze this crash log and find the root cause"}],
    "reasoning_effort": "high"
  }'

Anthropic SDK

The same key and balance work over POST /v1/messages. The base URL carries no /v1 suffix: the SDK appends it to the path itself, unlike the OpenAI SDK.

from anthropic import AsyncAnthropic

client = AsyncAnthropic(
    base_url="https://api.mixen.ai",
    api_key="mxn-...",  # the x-api-key header is supported
)
msg = await client.messages.create(
    model="anthropic/claude-sonnet-5.5",
    max_tokens=1024,
    messages=[{"role": "user", "content": "Hi!"}],
)
print(msg.content[0].text)

Claude Code maps this model to the ANTHROPIC_DEFAULT_SONNET_MODEL variable — setup is in the Claude Code guide.

Pricing

Per 1M tokens: input — $2.5, output — $12.5 — Opus 5.5 territory. Cache: read — $0.25, write — $3.125. Showcase prices follow the live exchange rate — take fresh values from the catalog.

Strengths and limitations

Code and agentic work is the Sonnet profile; reasoning up to xhigh/max, switched off with off for routine jobs.
Claude Code and the Anthropic SDK connect directly — tool use, streaming, count_tokens and cache_control work.
Native web search: sources in annotations.
Output at $12.5 per 1M is flagship territory; for bulk routine Claude Haiku 5.5 is cheaper — $0.12 input / $0.6 output (model card).

All models — in the catalog. The general workflow — chat guide.