Claude Opus 5.5 is Anthropic's model for long-running agentic coding and knowledge work, released on September 22, 2026, and Anthropic's models overview recommends starting here for most workloads, reserving Claude Fable 5.1 for the most demanding reasoning.
- Input
- text image $4/M
- Output
- text $20/M
- Cache read
- $0.2/M
- Context
- 1M
- vs GPT-4o
- ~20% cheaper
- Knowledge cutoff
- 2026-06
Benchmarks
Vendor-published: Alibaba (Qwen) Anthropic DeepSeek Google Moonshot OpenAI Z.ai
Price in context
Where the price sits among 67 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Tokens
| Context window (vendor spec) | 1,000,000 |
|---|---|
| Max output (vendor spec) | 128,000 |
| Knowledge cutoff | 2026-06 |
Prompt caching
| How it caches | explicit (opt-in) |
|---|---|
| Min prefix | 512 provider default is 1,024 |
| Lifetime | 5m default, 1h option |
| Write cost | 1.25x (5m) / 2x (1h) |
Thinking
| Vendor control | output_config.effort |
|---|---|
| Accepted values | low · medium · high · xhigh · max |
| Default | medium applied when the request sets nothing |
| Can be turned off | No |
| Thinking behaviour | Adaptive thinking is always on: thinking {"type": "disabled"} and a manual {"type": "enabled", "budget_tokens": N} both return a 400 error, so effort is the only depth control. The default dropped from high on Claude Opus 5 to medium. |
| Parameter | reasoning_effort |
| Values | minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies |
Model
| Modalities | text + image → text |
|---|
- 1M context at standard pricing with no long-context tier
- prompt-cache reads cost 0.05x input ($0.20/M) rather than the usual 0.1x
- minimum cacheable prompt 512 tokens
- forced tool use (tool_choice any or tool) returns a 400
- thinking blocks are tied to the model and conversation that produced them
- up to 300k output tokens on the Message Batches API with the output-300k-2026-03-24 beta header
- fast mode is a research preview on the Claude API only
One prompt, measured through the gateway
Claude Opus 5.5 passed · 3 sentences
When we turned on reasoning, the model began "thinking out loud" before each answer, generating thousands of internal working tokens that users never see but that we are billed for just like the final response. Those hidden tokens are charged at the output rate, typically the most expensive rate, so the same question with the same visible answer now costs roughly twice as much or more. We can bring the bill back down without losing the quality gains by capping the reasoning budget and reserving reasoning mode for the complex tasks that actually benefit from it.
out 263 tok (+102 thinking) latency 5.7 s
Instruction following (exactly three sentences - countable), audience shaping (CFO register), and the hidden-thinking billing gap the token meters below expose.
Claude Opus 5.5 passed · 8/8 cases
```python def longest_run(xs): if not xs: return 0 best = 1 cur = 1 for i in range(1, len(xs)): if xs[i] == xs[i - 1]: cur += 1 best = max(best, cur) else: cur = 1 return best ``` **Explanation:** The original code counted *matching adjacent pairs* rather than *items in a run*. Both `cur` and `best` started at 0, and `cur` reset to 0 on a mismatch, so a run of length *n* was reported as *n − 1*. For a single-element list the loop never executes, so it returned 0 instead of 1. For `[5, 5]` it returned 1 instead of 2. The fix treats every element as the start of a run of length 1: `best` and `cur` start at 1, and `cur` resets to 1 (not 0) when the value changes. An explicit check returns 0 for an empty list. The "misses runs at the last index" reports are the same off-by-one bug rather than a separate one. […]
out 723 tok (+303 thinking) latency 10.4 s
Whether the fix is actually correct (runnable), explanation density, and token efficiency on a bounded task.
Claude Opus 5.5 passed · 5/5 fields, guidance "Withheld pending Q4 close"
```json { "company": "Meridian Robotics", "quarter": "September quarter", "revenue_usd_m": 412, "growth_pct": 11, "guidance": "Withheld pending Q4 close" } ``` **Judgment calls to check:** - **quarter**: Kept as "September quarter" rather than "Q3", since the fiscal calendar isn't stated. The text mentions an upcoming "Q4 close," so it may be fiscal Q3, but that's not certain. - **revenue_usd_m**: The text says only "412 for the topline." It doesn't state currency or units, and the figure is on a constant-currency basis, not reported USD. USD millions is an assumption. Use `null` if you need strictly stated values. - **growth_pct**: The source says "eleven and change," so the true figure is slightly above 11. 11 is an approximation. - **guidance**: Guidance was explicitly withheld. I recorded that rather than `null`, since the text addresses it directly.
out 829 tok (+488 thinking) latency 10.9 s
Schema obedience (no invented fields), hallucination pressure (guidance is explicitly withheld), and structured-output path differences.
Claude Opus 5.5 passed · 120 words, 0 banned, 1 question
Today we're launching Cross-Provider Prompt Caching for our API gateway. Why pay twice for the same context? Our gateway now stores repeated prompt prefixes, system instructions, and document chunks, then reuses them whether your request goes to OpenAI, Anthropic, Google, or an open-source model. Teams running retrieval pipelines or long agent loops can cut token costs by up to 60 percent and trim latency on every cached call. Setup takes one configuration flag; no code changes are required. Cache rules respect tenant boundaries, expire on your schedule, and log every hit for audit review. Dashboards show savings by provider, route, and application in real time. Cross-Provider Prompt Caching is available on all Pro and Enterprise plans. Turn it on today.
out 1263 tok (+1007 thinking) latency 13.5 s
Constraint obedience (word budget, banned-word list, the single question), style fingerprint, and length control.
Use Claude Opus 5.5 in 30 seconds
OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions
from openai import OpenAI
client = OpenAI(
base_url="https://synthorai.io/v1",
api_key="sk-syn-...",
)
resp = client.chat.completions.create(
model="claude-opus-5-5",
messages=[{"role": "user", "content": "Summarize this diff"}],
reasoning_effort="medium",
)
print(resp.choices[0].message.content)import OpenAI from "openai";
const client = new OpenAI({
baseURL: "https://synthorai.io/v1",
apiKey: "sk-syn-...",
});
const resp = await client.chat.completions.create({
model: "claude-opus-5-5",
messages: [{ role: "user", content: "Summarize this diff" }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);curl https://synthorai.io/v1/chat/completions \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-d '{
"model": "claude-opus-5-5",
"messages": [{"role": "user", "content": "Hello"}],
"reasoning_effort": "medium"
}'package main
import (
"context"
"fmt"
"github.com/openai/openai-go/v3"
"github.com/openai/openai-go/v3/option"
)
func main() {
client := openai.NewClient(
option.WithBaseURL("https://synthorai.io/v1"),
option.WithAPIKey("sk-syn-..."),
)
resp, _ := client.Chat.Completions.New(context.TODO(), openai.ChatCompletionNewParams{
Model: "claude-opus-5-5",
Messages: []openai.ChatCompletionMessageParamUnion{
openai.UserMessage("Summarize this diff"),
},
ReasoningEffort: openai.ReasoningEffortMedium,
})
fmt.Println(resp.Choices[0].Message.Content)
}import com.openai.client.OpenAIClient;
import com.openai.client.okhttp.OpenAIOkHttpClient;
import com.openai.models.chat.completions.*;
import com.openai.models.ReasoningEffort;
OpenAIClient client = OpenAIOkHttpClient.builder()
.baseUrl("https://synthorai.io/v1")
.apiKey("sk-syn-...")
.build();
ChatCompletion resp = client.chat().completions().create(
ChatCompletionCreateParams.builder()
.model("claude-opus-5-5")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About Claude Opus 5.5
- It costs $4 per million input tokens and $20 per million output tokens, and prompt-cache reads are billed at 5% of the input price ($0.20 per million) instead of the usual 10%, which makes agent loops that replay a stable prefix noticeably cheaper.
- It keeps a 1M-token context window with no long-context surcharge, 128K max output, text and image input, and a June 2026 knowledge cutoff.
- Anthropic's documentation lists four breaking changes for code moving from Claude Opus 5: adaptive thinking is always on, so disabling thinking or setting a manual budget returns an error and the effort parameter, now defaulting to medium, is the only depth control; forced tool use through tool_choice any or tool is rejected, so keep tool_choice on auto and use strict tool use or structured outputs for schema-valid JSON; thinking blocks are tied to the model and conversation that produced them; and the earlier computer_20251124 tool is not accepted on the Claude API.
- The short notes the model writes between tool calls now arrive as thinking blocks, so interfaces that stream them should set a thinking display value.
- Synthorai serves Claude Opus 5.5 through the same APIs as the rest of the Claude lineup.
FAQ
Is the Claude Opus 5.5 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $4/M input tokens, that credit alone covers roughly 31 requests of ~8K tokens against Claude Opus 5.5.
What is Claude Opus 5.5 best at?
Anthropic's recommended starting model for most workloads; cache reads at 5% of input, $0.20 per million tokens; thinking always on; effort defaults to medium. See the About section for the full picture from the vendor's own release notes.
How much does Claude Opus 5.5 cost?
Claude Opus 5.5 costs $4 per million input tokens and $20 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.2/M.
Does Claude Opus 5.5 support prompt caching?
Yes, via opt-in: mark stable prefixes with cache_control breakpoints. Cached input tokens bill at $0.2/M vs $4/M uncached; prompts need a 512-token stable prefix to cache (TTL 5m default, 1h option). Prompt caching guide →
How do I get access to Claude Opus 5.5?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="claude-opus-5-5", and you're done. One API key covers every model on the gateway.
What is Claude Opus 5.5's knowledge cutoff?
Claude Opus 5.5's knowledge cutoff is 2026-06, per the vendor's official documentation (as of 2026-09-23).
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.