Sonnet 5
Move an app from Claude Sonnet 4.6 to Claude Sonnet 5: the model IDModel IDThe name a request calls a model by, lab/model, copied from Models.More on Models → changes, three sampling fields go, and reasoning turns on by default.
- Change the model ID.
- Update the request.
- Read the answer.
- Set the effort.
- Compare before you switch.
1. Change the model ID
| From | To | |
|---|---|---|
| Model ID | anthropic/claude-sonnet-4.6 | anthropic/claude-sonnet-5 |
| Context | 1 000 000 tokens | 1 000 000 tokens |
| Longest answer | 128 000 tokens | 128 000 tokens |
| Reasoning | off unless you ask | on unless you turn it off: default_enabled is true |
| Effort levels | low · medium · high · max | low · medium · high · xhigh · max |
supported_parameters | holds temperature, top_p, top_k | holds none of the three |
GET /v1/model/{lab}/{model} answers each model's entry: its context, its longest answer, its fields, its reasoning. The request keeps its shape; model changes.
{
"model": "anthropic/claude-sonnet-5",
"reasoning": {
"effort": "high"
},
"messages": [
{
"role": "user",
"content": "Write the product page for a wool burnous."
}
]
}2. Update the request
| You send today | On Sonnet 5 | Send instead |
|---|---|---|
temperature, top_p or top_k | not taken; Anthropic refuses any value but the default | nothing: steer with the prompt |
a thinking budget: reasoning.max_tokens or thinking.budget_tokens | not honoured: reasoning is adaptive only | an effort level |
| no reasoning setting | the model reasons | nothing, or reasoning turned off, as below |
To keep Sonnet 4.6's behaviour, turn reasoning off in the request.
| Route | Reasoning off |
|---|---|
/v1/chat/completions | reasoning: {"enabled": false} |
/v1/messages | thinking: {"type": "disabled"} |
Keep temperature: 0 to make answers repeat. Sonnet 5 does not take it.
Ask for a fixed shape with Structured outputs, and state in the prompt what must not vary.
3. Read the answer
With reasoning on, every answer carries it, and the reasoning shares the ceiling with the reply.
| Route | Where the reasoning lands | Change |
|---|---|---|
/v1/chat/completions | choices[0].message.reasoning, counted in usage.completion_tokens_details.reasoning_tokens | raise max_tokens: too low a ceiling ends with no text |
/v1/messages | thinking blocks, ahead of the text block | read blocks by type, never content[0]; send thinking blocks back unchanged with tool results |
Sonnet 5 counts text differently: Anthropic puts the same text at about 30 % more tokens than on Sonnet 4.6. Recount what your prompts hold, and check your max_tokens. Both routes: Chat · Messages.
4. Set the effort
| Route | Field |
|---|---|
/v1/chat/completions | reasoning.effort, or reasoning_effort |
/v1/messages | output_config.effort |
Anthropic gives high as the default. xhigh is new, between high and max, for the hardest coding and agent work. Set the level in every request: lower it where answers hold.
5. Compare before you switch
Send the same set of real prompts to both IDs, and compare three things.
| Compare | Where |
|---|---|
| the answers | your own check: a test suite, a reviewer, the task's pass rate |
| what each cost | usage.cost, in DADAThe Algerian dinar, the one currency the docs show.More on Balance and charges →, on every answer |
| how much each reasoned | usage.completion_tokens_details.reasoning_tokens |
The script sends each prompt three ways and prints one line per run: how the answer ended, what the prompt counted, what the model reasoned, and the charge in DA, then the first words of the answer.
| Run | Model | Reasoning |
|---|---|---|
old, off | MODEL | off |
new, off | CANDIDATE | off |
new, on | CANDIDATE | on, at effort high |
import os
from openai import OpenAI
API_KEY = os.environ["OPENDUNES_API_KEY"]
BASE_URL = "https://opendunes.com/v1"
MODEL = "anthropic/claude-sonnet-4.5"
CANDIDATE = "anthropic/claude-sonnet-4.5"
MAX_TOKENS = 4000
PROMPTS = [
"Write the product page for a wool burnous.",
"A customer in Oran asks why her parcel is late. Answer her.",
]
OFF = {"reasoning": {"enabled": False}}
ON = {"reasoning": {"enabled": True, "effort": "high"}}
RUNS = [
("old, off", MODEL, OFF),
("new, off", CANDIDATE, OFF),
("new, on", CANDIDATE, ON),
]
client = OpenAI(base_url=BASE_URL, api_key=API_KEY)
for prompt in PROMPTS:
print(prompt)
for label, model, fields in RUNS:
reply = client.chat.completions.create(
model=model,
max_tokens=MAX_TOKENS,
messages=[{"role": "user", "content": prompt}],
extra_body=fields,
)
usage = reply.usage
details = usage.completion_tokens_details
thought = details.reasoning_tokens if details else 0
print(
f"{label:9} {reply.choices[0].finish_reason:7}",
f"in {usage.prompt_tokens}",
f"thought {thought}",
f"cost {usage.cost}",
)
print(" ", (reply.choices[0].message.content or "")[:60])The samples put anthropic/claude-sonnet-4.5 in both seats, so they run as they stand. Set MODEL to anthropic/claude-sonnet-4.6 and CANDIDATE to anthropic/claude-sonnet-5.
Read the first two lines against each other: the only difference is the model, and in is the recount. The third line is what reasoning adds, in thought and in the charge.
Switch once the new ID holds; going back is the same one-line change. Run your red-team suite on the new ID too: Red teaming.
Last modified on