Claude Sonnet 5.5

AnthropicChatIDAU
Claude Sonnet 5.5 is Anthropic's mid-tier model, positioned to balance speed and intelligence, with adaptive thinking, a 1M-token context window and up to 128K output tokens; list price $2.00 in / $10.00 out per 1M tokens, provider list as at 1 November 2026.
Seedrise is an independent provider and is not affiliated with or endorsed by Anthropic. Claude is a trademark of Anthropic, PBC.

Provider list price

Claude Sonnet 5.5Per 1M tokens, as at 1 November 2026
Token typePrice
Input2.00
Output10.00
Cached input0.10
AUD is shown at a reference rate of 1 USD = 1.53 AUD; invoices use the rate on the day.

Your Seedrise rate is quoted per account against this list price. Request a rate card.

Pinning to an Australian region carries the provider's regional premium on top of the list price shown.

Launch rate (global routing): 1.80 input · 9.00 output per 1M tokens, 10% below Anthropic's published list price, for rate card requests by 31 Jan 2027. Terms

Specifications

Model IDclaude-sonnet-5-5
ProviderAnthropic
TypeChat
Context window1M tokens (1,000,000)
Max output128K tokens (128,000)
ModalitiesTextVisionToolsReasoning
RegionAU Can be pinned to Sydney or Melbourne on request
EndpointsOpenAI Chat Completions: https://api.seedrise.ai/v1
Anthropic Messages: https://api.seedrise.ai
Prices checked1 November 2026

Marked AU: can be pinned to Sydney or Melbourne on request, where the Australian-region list price is $2.20 in / $11.00 out per 1M tokens (cache reads $0.11). Without pinning it runs on the provider's global routing.

Strengths

  • Rated fast in Anthropic's latency comparison, against moderate for Opus 5.5
  • Adaptive thinking with high as the default effort level
  • Same 1M-token context and 128K output limit as Opus 5.5 at half the list price
  • Cache reads list at $0.10 per 1M tokens

Typical use cases

  • Interactive coding assistants and IDE agents where response time matters
  • Customer-facing chat and support with tool use
  • Sub-agents in Claude Code alongside an Opus 5.5 main session
  • Document processing and extraction at moderate volume

Quickstart

A first request with curl. Replace sk-... with your Seedrise key.

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

OpenAI SDK, Python

python
from openai import OpenAI

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

r = client.chat.completions.create(
    model="claude-sonnet-5-5",
    messages=[{"role": "user", "content": "Summarise this contract in three bullets."}],
)
print(r.choices[0].message.content)

Claude Code

Claude Code talks Anthropic Messages, so it points at the root URL. Set the environment once and start it as usual.

bash
export ANTHROPIC_BASE_URL="https://api.seedrise.ai"
export ANTHROPIC_AUTH_TOKEN="sk-..."                     # your Seedrise key
export ANTHROPIC_API_KEY=""                             # clear any personal key
export ANTHROPIC_DEFAULT_OPUS_MODEL="claude-opus-5-5"
export ANTHROPIC_DEFAULT_SONNET_MODEL="claude-sonnet-5-5"
export ANTHROPIC_DEFAULT_HAIKU_MODEL="claude-haiku-5-5"
export CLAUDE_CODE_SUBAGENT_MODEL="claude-sonnet-5-5"
export CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC=1
claude

Full guide with team settings and troubleshooting: Claude Code on Seedrise

Where it runs

AU Can be pinned to Sydney or Melbourne on request. Pinning is set per key, not per request.

Data residency options for Claude: Claude in Australia

Questions about Claude Sonnet 5.5

What is the model ID for Claude Sonnet 5.5? +
Use claude-sonnet-5-5 as the model field, with no vendor prefix. It works on the OpenAI-compatible endpoint at https://api.seedrise.ai/v1 and on Anthropic Messages at https://api.seedrise.ai. GET /v1/models returns the IDs your key can call.
How does the Seedrise rate for Claude Sonnet 5.5 compare to the list price? +
Anthropic's list price as at 1 November 2026 is US$2.00 per 1M input tokens and US$10.00 per 1M output tokens. Seedrise quotes rates per account against the provider's published list price for the same routing. Volume and committed tiers sit below list. Australian-region routing carries the provider's regional premium.
What is the context window and max output of Claude Sonnet 5.5? +
Claude Sonnet 5.5 has a context window of 1,000,000 tokens and a maximum output of 128,000 tokens, per the provider documentation checked on 1 November 2026.
Can Claude Sonnet 5.5 run in Australia? +
Yes. Claude Sonnet 5.5 can be pinned to Sydney or Melbourne on request. Pinning is set per key, not per request, and carries the provider's regional premium.
When should I choose Claude Sonnet 5.5 over Opus 5.5? +
When latency and cost matter more than the extra capability of Opus. Sonnet 5.5 lists at half the Opus 5.5 price with the same 1M-token context, and Anthropic rates it fast against moderate for Opus 5.5.
Can I use Claude Sonnet 5.5 as the sub-agent model in Claude Code? +
Yes. Set CLAUDE_CODE_SUBAGENT_MODEL to claude-sonnet-5-5 on your Seedrise key to keep sub-agent cost down while the main session runs on Opus 5.5.

Get a rate for Claude Sonnet 5.5

Per-model rates in writing within one business day, then a console login and a trial key.

Request a rate card →