Skip to content

Private beta opens Oct 29.Request your invite

We're open. Sign in and try an open-weight model free

Bearer Club

Anthropic Β· Closed

Claude Sonnet 5.5 API Member pricing vs list price

anthropic/claude-sonnet-5-5

Closed

Claude Sonnet 5.5 is the newest model on Bearer Club in Anthropic's Sonnet line, which sits between Haiku and Opus: a closed model with a 1M-token context window at $2.00 per 1M input tokens and $10.00 per 1M output tokens at list, 33% cheaper than Claude Sonnet 4.6. It is for members only.

Claude Sonnet 5.5 prices per 1M tokens

Input / output, by membership tier and data policy. Every price is a percent of the provider's public list price.

Claude Sonnet 5.5 prices per 1M tokens by tier and data policy
TierPrivateResearch ShareFinancial incentive notice
List price$2.00 input, $10.00 output per 1M tokens
GuestMembers onlyBecome a MemberMembers onlyBecome a Member
Member$1.90 input, $9.50 output per 1M tokens5% off list price$1.80 input, $9.00 output per 1M tokens10% off list price
Executive$1.70 input, $8.50 output per 1M tokens15% off list price$1.60 input, $8.00 output per 1M tokens20% off list price

Does Member pay for itself on Claude Sonnet 5.5?

Member costs $199 a year. At list price, a Member Private key saves $0.10 per 1M input tokens and $0.50 per 1M output tokens. It pays for itself at about $3,980 a year ($332 a month) of Claude Sonnet 5.5 spend at list price.

At $2.00 per 1M input tokens that is about 2B input tokens a year, or 166M a month, counting input only. A coding agent that runs 10K tasks a month at 5,000 input tokens each sends 50M input tokens, 30% of that; output tokens bring the point closer.

  • Member ($199 a year) pays for itself once your Claude Sonnet 5.5 spend at list price passes $332 a month with a Private key (about 83M tokens at a 3:1 input-to-output mix) or $166 a month with Research Share.
  • Executive ($1,999 a year) costs less than Member above $1,500 a month (Private keys), about 375M tokens a month.

100M tokens a month at 3 input : 1 output is $400 a month at list price.

At this volume Member Β· Research Share saves $23.42 a month against list price.

Monthly cost of Claude Sonnet 5.5 by plan at 100M tokens a month
PlanUsage / moFee / moNet vs list / moPays off above
Member Β· Private$380$16.58$3.4283M tokens
Member Β· Research Share$360$16.58$23.4241M tokens
Executive Β· Private$340$167βˆ’$107278M tokens
Executive Β· Research Share$320$167βˆ’$86.58208M tokens

Usage at each plan's price per token. The fee is the annual membership fee divided by 12 and covers every model, so spend on other models counts toward it too.

Specs

Claude Sonnet 5.5 specs
ProviderAnthropic
Model typeClosed (proprietary API)
Context window1,000,000 tokens (1M)
Input and outputText in, text out (chat completions)
Model IDanthropic/claude-sonnet-5-5
EndpointPOST https://api.bearer.club/v1/chat/completions
PlansMember, Executive
List price per 1M tokens$2.00 input, $10.00 output

List price rank: 56th lowest input price and 58th lowest output price of the 69 models. Its context window is larger than 33 of them.

What Claude Sonnet 5.5 is best at

Production coding agents

Coding agents plan, call tools, read errors and retry, so one task means many long requests. Teams running Claude Sonnet 4.6 can test Claude Sonnet 5.5 as the newer version, 33% cheaper than Claude Sonnet 4.6 on input. Bearer Club passes tools and tool_choice through where the model supports them.

Complex instruction following

Prompts with nested conditions, role constraints and strict output formats are a common reason to pick a Sonnet-class model. If format drift breaks your downstream code, test Claude Sonnet 5.5 against your own templates; JSON mode (response_format) passes through where the model supports it.

Document analysis at production scale

Legal, finance and healthcare documents need long, careful reads. At $2.00 per 1M input tokens, Claude Sonnet 5.5 is 2Γ— cheaper than Claude Opus 5.5, and reading a 100,000-token document costs about $0.20 at list. Your compliance review still applies to any model you use.

What 1,000 requests cost

Example request shapes, priced per 1,000 requests from the per-token prices above.

Cost of 1,000 Claude Sonnet 5.5 requests by request shape and plan
Request (input / output tokens)List priceMember PrivateExecutive Private
Short chat reply1,000 / 300$5.00$4.75$4.25
Document summary20,000 / 1,000$50.00$47.50$42.50
Long-context read200,000 / 2,000$420$399$357

Claude Sonnet 5.5 vs similar models

  • vs Claude Sonnet 4.6: Claude Sonnet 4.6 costs $3.00 per 1M input tokens at list, 50% more than Claude Sonnet 5.5, with the same 1,000,000-token window as Claude Sonnet 5.5. For new workloads, start with Claude Sonnet 5.5; keep Claude Sonnet 4.6 where prompts and evals are pinned to it.
  • vs Claude Opus 5.5: Claude Opus 5.5 costs $4.00 per 1M input tokens at list, 2Γ— the price of Claude Sonnet 5.5. Run your workload on Claude Sonnet 5.5 first and move up when your evals show it falling short.
  • vs DeepSeek V4 Pro 0423: DeepSeek V4 Pro costs $0.9553 per 1M input tokens at list, 2.1Γ— cheaper than Claude Sonnet 5.5. It is open-weight, so Guests can call it with no membership fee. Test both on your own task before committing; keep each where your evals favour it.
  • Claude Sonnet 4.6

    Earlier Sonnet

    $3.00 input / $15.00 output at list, 50% more than Claude Sonnet 5.5 at a 3:1 mix; 1M-token context; closed, members only.

  • Claude Opus 5.5

    Anthropic's Opus tier

    $4.00 input / $20.00 output at list, 2Γ— the price of Claude Sonnet 5.5 at a 3:1 mix; 1M-token context; closed, members only.

  • Claude Haiku 4.5

    Anthropic's Haiku tier

    $1.00 input / $5.00 output at list, 2Γ— cheaper than Claude Sonnet 5.5 at a 3:1 mix; 200K-token context; closed, members only.

  • Claude Fable 5.1

    Anthropic Fable

    $10.00 input / $50.00 output at list, 5Γ— the price of Claude Sonnet 5.5 at a 3:1 mix; 1M-token context; closed, members only.

  • DeepSeek V4 Pro 0423

    DeepSeek's Pro tier

    $0.9553 input / $1.91 output at list, 3.3Γ— cheaper than Claude Sonnet 5.5 at a 3:1 mix; 1M-token context; open-weight, on the Guest plan.

Data policy for this model

Private: Your prompts and outputs are never used for training and never shared or licensed. For security, abuse prevention and debugging we store request and response content, encrypted, and delete it after 30 days; error details may be kept longer. We also keep usage details (model, tokens, cost, latency, status and time). The model provider may keep requests briefly for abuse monitoring under its own terms.

Research Share: available. Opt in per key and pay less. Data from that key will be used to accelerate AGI and supplied to top frontier labs for AGI purposes, and only for traffic after you opt in.

How the Research Program works

Regions

Each model is served only in the regions its provider supports. Per-model region details are not published yet.

Use Claude Sonnet 5.5 with the OpenAI SDK

Change two settings: point the SDK at https://api.bearer.club/v1 and use your Bearer Club key, then pass anthropic/claude-sonnet-5-5 as the model.

curl https://api.bearer.club/v1/chat/completions \  -H "Authorization: Bearer $BEARER_CLUB_API_KEY" \  -H "Content-Type: application/json" \  -d '{    "model": "anthropic/claude-sonnet-5-5",    "messages": [{"role": "user", "content": "Hello from the Club!"}]  }'

The official OpenAI SDKs and most OpenAI-compatible tools, such as Cursor, Cline, Continue, Open WebUI and LiteLLM, work the same way; the name of the base URL setting varies by tool.

Claude Sonnet 5.5 FAQ

How does Claude Sonnet 5.5 compare with Claude Sonnet 4.6?

Claude Sonnet 5.5 is the newer version, at $2.00 per 1M input tokens against $3.00, with the same 1,000,000-token window as Claude Sonnet 4.6. Start new workloads on Claude Sonnet 5.5; keep Claude Sonnet 4.6 where prompts and evals are pinned to it.

What context window does Claude Sonnet 5.5 support?

1,000,000 tokens, roughly 750,000 English words. The prompt and the answer together have to fit in it.

When should I move from Claude Sonnet 5.5 to Claude Opus 5.5?

When your evals show Claude Sonnet 5.5 failing on your specific tasks, not as a default. Claude Opus 5.5 is 2Γ— the price of Claude Sonnet 5.5 on input.

Is Claude Sonnet 5.5 available on the Guest tier?

No. Claude Sonnet 5.5 is a closed model from Anthropic, and it needs a Member ($199 a year) or Executive ($1,999 a year) membership.

What is the model ID for Claude Sonnet 5.5 on Bearer Club?

Use anthropic/claude-sonnet-5-5 as the model in requests to https://api.bearer.club/v1/chat/completions. The same id appears in the https://api.bearer.club/v1/models list.

Further reading

Discounts are measured against each provider's public list price and vary by model, membership tier and data policy. See Pricing.