星海词元星海词元
Ready to build?Get an API key — all models at 50% of the official price →
Home › Models › claude-opus-4-8

claude-opus-4-8 API

Call claude-opus-4-8 through a single OpenAI-compatible endpoint — one key, no separate vendor account, no multi-provider wiring.

AnthropicChatVisionReasoningCoding工具调用Long context
41.8
Intelligence index
74.3
Coding index
41.9
Agentic index

Pricing

Input$1.25 / 1M tokens  (¥8.12)
Output$6.25 / 1M tokens  (¥40.62)
Output multiplier×5.00
Context window1M tokens

Prices are per 1M tokens in USD · ¥6.5 = $1 · Billed in CNY

Anthropic

Claude models are the usual pick for long-document reasoning and agentic coding. StarSeaAPI terminates the Anthropic Messages protocol natively, so Claude Code and other Anthropic-native clients work without a translation layer.

When to use it

At $1.25 per 1M input tokens it sits above the catalogue median of $0.50 — a capability-first choice. Best for coding agents and repository-scale edits. Every model here is reachable with the same API key, so trialling it against a stronger sibling costs one line of code.

Code

from openai import OpenAI
client = OpenAI(
  base_url="https://starseaapi.com/v1",
  api_key="sk-your-key"
)
r = client.chat.completions.create(
  model="claude-opus-4-8",
  messages=[{"role": "user", "content": "Explain prefix caching in one paragraph"}]
)
print(r.choices[0].message.content)

Integrations · Quickstart

Other models from this provider

ModelsInput $/MOutput $/MIntelligence indexCoding index
claude-haiku-5-5$0.025$0.12——
claude-sonnet-5$0.50$2.5038.271.5
claude-sonnet-5-5 frontier$0.50$2.5056.0—
claude-sonnet-4-6$0.75$3.7524.7—
claude-opus-5-5 frontier$1.00$5.0057.6—
claude-opus-4-6$1.25$6.2526.4—
claude-opus-4-7$1.25$6.2540.773.6
claude-opus-5$1.25$6.2550.878.0
claude-fable-5$2.50$12.5049.676.5
claude-fable-5-1$2.50$12.5053.481.6

Capabilities