How much does the Claude Opus 5.5 API cost?
On OceanToken, Claude Opus 5.5 costs $3.60 per 1M input tokens and $18.00 per 1M output tokens: 10% off Anthropic’s official price of $4.00 input / $20.00 output, for every account from the first request. Cached input bills at the official $0.20 per 1M tokens at every tier. One request with 100K input and 20K output tokens costs $0.72 here, against $0.80 at the official price.
| per 1M tokens | Official price | OceanToken, every tier |
|---|---|---|
| Input | $4.00 | $3.60 −10% |
| Output | $20.00 | $18.00 −10% |
| Cached inputOfficial price at every tier | $0.20 | $0.20 |
Prices as of November 18, 2026.
What does a typical request cost?
Claude Opus 5.5 costs the same at Tier 1, Tier 2 and Tier 3, so the example below is what every account pays.
| Workload | Official price | OceanToken, every tier |
|---|---|---|
| One request | $0.80 | $0.72 −10% |
| 1,000 requests | $800.00 | $720.00 −10% |
What Claude Opus 5.5 costs over a month
Claude Opus 5.5 is Anthropic's larger model and costs more per token: the same request is $0.72 at Tier 1, against $0.36 on Claude Sonnet 5.5. Over a month the gap is what the table shows; send Opus the tasks where the smaller model's answer falls short.
| A month of requests | Official price | Every tier |
|---|---|---|
| Claude Opus 5.51,000 requests a day for 30 days, uncached | $24,000 | $21,600 −10% |
| Claude Opus 5.5The same, 80% of input from the cache | $14,880 | $13,440 −10% |
One request = 100,000 input tokens and 20,000 output tokens, uncached: about a long document or a large code file in, a detailed answer out. Cached input is billed at the official price at every tier. The cached row reads 80K of each request's 100K input tokens from the cache.
How fast is Claude Opus 5.5? Measured on our API
Measured on the OceanToken API on November 16, 2026: the median of 3 streaming runs per model, one short prompt, up to 150 output tokens. Longer prompts and outputs take longer.
| Model | Time to first token | Output speed |
|---|---|---|
| Claude Opus 5.5 | Varied too much between runs this week; not quoted | |
| Claude Sonnet 5.5 | 1.22 s | 157 tokens/s |
Source: OceanToken /speed, measured November 16, 2026. Every measured model
Use Claude Opus 5.5 in Claude Code
Claude Code speaks the Anthropic Messages API, which OceanToken serves for its Claude models. Point it at OceanToken with two settings (the base URL has no /v1: Claude Code adds it) and name the model exactly as the catalog writes it. The prices above apply; cached input is billed at Anthropic's list price.
{
"env": {
"ANTHROPIC_BASE_URL": "https://api.oceantoken.ai",
"ANTHROPIC_AUTH_TOKEN": "YOUR_API_KEY",
"ANTHROPIC_MODEL": "anthropic/claude-opus-5.5"
}
}export ANTHROPIC_BASE_URL=https://api.oceantoken.ai
export ANTHROPIC_AUTH_TOKEN=YOUR_API_KEY
claude --model anthropic/claude-opus-5.5Every coding agent on OceanToken
Large volume? Enterprise rates are by quote, up to 30% off. Quote by email
Frequently asked questions
How much does the Claude Opus 5.5 API cost per million tokens, and where can I get it cheaper than Anthropic’s list price?
Claude Opus 5.5 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens at Anthropic’s official price. On OceanToken it costs $3.60 input and $18.00 output, 10% off the official price for every account from the first request. Cached input bills at the official $0.20 per 1M tokens. You call the same model with one OpenAI-compatible API key.
Claude Opus 5.5 vs Claude Sonnet 5.5: which should I use?
At Tier 1 on OceanToken, Claude Opus 5.5 costs $3.60 input / $18.00 output per 1M tokens and Claude Sonnet 5.5 costs $1.80 / $9.00. A request with 100K input and 20K output tokens costs $0.72 on Claude Opus 5.5 and $0.36 on Claude Sonnet 5.5. Start with the one that costs less and switch only if the other does better on your own tests; both take the same API key, so switching is a change of model ID.
Is cached input discounted on Claude Opus 5.5?
No. Cached input bills at Anthropic’s official price at every tier: $0.20 per 1M tokens for Claude Opus 5.5. The discounts apply to input and output.
Am I charged for failed requests?
No. If a request fails, you are not charged: that covers a request refused for an insufficient balance or by a safety check, one whose provider fails before returning any output, and a video job that fails or is refused by a safety check, whose held amount goes back to your balance. The one exception: if a request breaks off after the model has started producing output, for example a stream cut off part-way, you pay for the tokens that were processed and generated for it.
Is there a volume discount?
Yes. Enterprise rates are by quote, up to 30% off: ask for a quote by email on the Enterprise page and we activate your rate for you.
Is it the official Claude Opus 5.5 model?
Yes. You call Anthropic’s Claude Opus 5.5 by its model ID, anthropic/claude-opus-5.5, and get that model. The price table shows the official price next to ours.
Do I need a subscription to use Claude Opus 5.5?
No. You add credits by card, and each request is billed at the model’s price. Purchased credits are valid for 12 months.
How do I call the Claude Opus 5.5 API?
Create an API key in the OceanToken console, set the base URL to https://api.oceantoken.ai/v1 and use the model id, for example anthropic/claude-opus-5.5. The OpenAI SDKs and any OpenAI-compatible client work.
from openai import OpenAI
# Your API Key from the OceanToken console
client = OpenAI(base_url="https://api.oceantoken.ai/v1",
api_key="YOUR_API_KEY")
reply = client.chat.completions.create(
model="anthropic/claude-opus-5.5",
messages=[{"role": "user", "content": "Hello"}])
print(reply.choices[0].message.content)# Your API Key from the OceanToken console
curl https://api.oceantoken.ai/v1/chat/completions \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "anthropic/claude-opus-5.5",
"messages": [{"role": "user", "content": "Hello"}]}'Read next
- Claude API: Anthropic Direct vs a Multi-Model Gateway
- Limit LLM API Spend With a Prepaid Balance
- Aider Claude Setup: Keys and Model Pairs
Claude API: every Claude model and price
Keep exploring
Claude Opus 5.5 model page · Claude API · All model prices
Claude Opus 5.5 vs GPT-6.1 Sol · Claude Opus 5.5 vs Claude Sonnet 5.5 · DeepSeek V4.1 Flash vs Claude Opus 5.5 · DeepSeek V4 Pro vs Claude Opus 5.5 · DeepSeek V3.2 vs Claude Opus 5.5 · GLM 5.3 Prime vs Claude Opus 5.5 · All comparisons
Claude Sonnet 5.5 API price · GPT-5.5 API price · GPT-6 Sol API price · Gemini 3.1 Pro API price · DeepSeek V4.1 Flash API price · Seedance 2.5 API price · MiniMax H3 API price · Kling v3.0 API price