Claude Sonnet 4.5 is a previous-generation Sonnet model that remains available on the Claude platform.
- Input
- text image $3/M
- Output
- text $15/M
- Cache read
- $0.3/M
- Context
- 200K
- vs GPT-4o
- ~40% cheaper
- Knowledge cutoff
- 2025-01
Benchmarks
Vendor-published: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai
Price in context
Where the price sits among 60 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) | 200,000 |
|---|---|
| Max output (vendor spec) | 64,000 |
| Knowledge cutoff | 2025-01 |
| Training data through | 2025-07 knowledge cutoff 2025-01 |
Prompt caching
| How it caches | explicit (opt-in) |
|---|---|
| Min prefix | 1,024 |
| Lifetime | 5m default, 1h option |
| Write cost | 1.25x (5m) / 2x (1h) |
Thinking
| Vendor control | thinking.type "enabled" + budget_tokens |
|---|---|
| Accepted values | budget_tokens at least 1,024 and below max_tokens; "adaptive" returns 400 |
| Default | off, with no thinking unless the request sets it applied when the request sets nothing |
| Can be turned off | Yes |
| Thinking behaviour | Extended thinking only, with no effort parameter; earlier turns' thinking blocks are stripped, keeping only the last; interleaved thinking requires the interleaved-thinking-2025-05-14 beta header. |
| Parameter | reasoning_effort |
| Values | minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies |
Model
| Modalities | text + image → text |
|---|
- Legacy model
- 1M-context beta (context-1m-2025-08-07) retired 2026-04-30, now capped at 200k context / 64k max output
Use Claude Sonnet 4.5 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-sonnet-4-5",
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-sonnet-4-5",
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-sonnet-4-5",
"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-sonnet-4-5",
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-sonnet-4-5")
.addUserMessage("Summarize this diff")
.reasoningEffort(ReasoningEffort.MEDIUM)
.build());
System.out.println(resp.choices().get(0).message().content().orElse(""));About Claude Sonnet 4.5
- It pairs fast comparative latency with strong reasoning, supporting a 200K-token context window, up to 64K output tokens, extended thinking, vision input, and the full Claude tool-use stack at $3/$15 per million tokens.
- Anthropic introduced it as its best model for complex agents and coding, with the highest intelligence across most tasks at the time, and it is the release where structured outputs first shipped in public beta before going generally available.
- One limit is worth knowing before sizing a workload: its 1M-token context beta was retired in April 2026, and requests above the standard 200K window now return an error rather than silently truncating.
- Thinking is the older extended-thinking style with an explicit token budget, the adaptive thinking type returns an error, and there is no effort parameter; interleaved thinking requires a beta header, and thinking blocks from earlier turns are stripped rather than carried forward.
- Prompt caching starts at a 1,024-token prefix.
- Anthropic now recommends newer Sonnet releases for improved performance, but Sonnet 4.5 remains a stable pinned snapshot for workloads tuned against it.
- Synthorai continues to serve it behind the same OpenAI-compatible API as the rest of the catalog.
FAQ
Is the Claude Sonnet 4.5 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $3/M input tokens, that credit alone covers roughly 41 requests of ~8K tokens against Claude Sonnet 4.5.
What is Claude Sonnet 4.5 best at?
Fast latency paired with strong reasoning; $3/$15 per million with 200K context; stable pinned snapshot for tuned workloads. See the About section for the full picture from the vendor's own release notes.
How much does Claude Sonnet 4.5 cost?
Claude Sonnet 4.5 costs $3 per million input tokens and $15 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.3/M.
Does Claude Sonnet 4.5 support prompt caching?
Yes, via opt-in: mark stable prefixes with cache_control breakpoints. Cached input tokens bill at $0.3/M vs $3/M uncached; prompts need a 1,024-token stable prefix to cache (TTL 5m default, 1h option). Prompt caching guide →
How do I get access to Claude Sonnet 4.5?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="claude-sonnet-4-5", and you're done. One API key covers every model on the gateway.
What is Claude Sonnet 4.5's knowledge cutoff?
Claude Sonnet 4.5's knowledge cutoff is 2025-01, per the vendor's official documentation (as of 2026-07-09).
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.