Claude Opus 5.5 on Run BiOS

claude-opus-5-5

+50%First top-up bonus

Top up $20 and we add 50%. That gives you about 2.6M input tokens extra on Claude Opus 5.5, on us.

Create an account

1M contextVisionTool callingReasoningPrompt cachingPartner-served

Pricing

USD per 1M tokens

Input	~~$4.00~~ $3.80
Output	~~$20.00~~ $19.00
Cached input	~~$0.20~~ $0.1995% below fresh input
Cache write (5m)	~~$5.00~~ $4.75
Cache write (1h)	~~$8.00~~ $7.60

5% off: Launch offer on Claude Opus 5.5. Promotional price on input, output, cache reads & cache writes. Standard prices shown struck through.

Billed per token with no minimum and no monthly fee. Price your workload

Capabilities and limits

Context window: 1M tokens
Max output: 125K tokens
Modality: text
Tool calling: Supported
Vision: Supported
Reasoning: Always on
Reasoning effort: low, medium, high, xhigh, max (default: medium)
Prompt caching: Supported (automatic)

Measured performance

Time to first token (p50): 6.0 s
Time to first token (p95): 12 s
Throughput (avg): 106.7 tok/s
Throughput (p50): 150.0 tok/s

Measured on real Run BiOS traffic over the trailing 7d. Your figures will vary with prompt shape and region.

Call it now: OpenAI-compatible

curl https://api.runbios.ai/v1/chat/completions \
  -H "Authorization: Bearer $BIOS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5-5",
    "messages": [{ "role": "user", "content": "Hello" }]
  }'

Existing OpenAI SDK code works by changing the base URL and the key. API overview

About Claude Opus 5.5

Anthropic Claude Opus 5.5, served by AWS Bedrock. Adaptive reasoning is always on; tool choice auto/none.

More from Claude

Claude Opus 5$5.00/$25.00 Claude Sonnet 5$2.00/$10.00