claude-sonnet-4-6
Anthropic·Token-based
Alias:
claude-sonnet-4.6Anthropic 的 claude-sonnet-4-6 模型，支持文本、图像输入和文本输出。支持推理、工具调用。
textimagestreamingfunction_callingtoolsvisionreasoningcachingcontext:1000000
- Starting price
- Input / Output · 1M
- Context
- 1M
- Maximum input window
- Max output
- 128K
- Maximum tokens per response
- Modalities
- →
- Knowledge cutoff
- Aug 2025
- Released
- Feb 2026
Pricing by Supplier
Anthropic
-10%Anthropic 官方
Input$3$2.7/ 1M
Output$15$13.5/ 1M
Cache Read$0.3$0.27/ 1M
Cache Write (5m)$3.75$3.375/ 1M
Cache Write (1h)$6$5.4/ 1M
AmazonBedrock
-40%AWS 官方
Input$3$1.8/ 1M
Output$15$9/ 1M
Cache Read$0.3$0.18/ 1M
Cache Write (5m)$3.75$2.25/ 1M
Cache Write (1h)$6$3.6/ 1M
claude特供
-40%适合生产环境，AWS Bedrock组成
Input$3$1.8/ 1M
Output$15$9/ 1M
Cache Read$0.3$0.18/ 1M
Cache Write (5m)$3.75$2.25/ 1M
Cache Write (1h)$6$3.6/ 1M
CCMax
-70%使用自用 vibe coding，纯血 ccmax号池
Input$3$0.9/ 1M
Output$15$4.5/ 1M
Cache Read$0.3$0.09/ 1M
Cache Write (5m)$3.75$1.125/ 1M
Cache Write (1h)$6$1.8/ 1M
Claude kiro
-90%使用自用 vibe coding，kiro号池
Input$3$0.3/ 1M
Output$15$1.5/ 1M
Cache Read$0.3$0.03/ 1M
Cache Write (5m)$3.75$0.375/ 1M
Cache Write (1h)$6$0.6/ 1M
CCMax-ZL
-70%CCmax微注-可蒸
Input$3$0.9/ 1M
Output$15$4.5/ 1M
Cache Read$0.3$0.09/ 1M
Cache Write (5m)$3.75$1.125/ 1M
Cache Write (1h)$6$1.8/ 1M
Capabilities / Supported modalities
StreamingFunction callingToolsVisionReasoningPrompt caching
Input
Output
Provider & data privacy
Provider
AnthropicDocs
Tokenizer
Anthropic Claude tokenizerLicense
Proprietary (commercial)Proprietary
Data retention42 daysNot used for upstream training by default
Performance
API access
Code samples
RequestPOST
/v1/messagesExample request
Parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Replace <YOUR_API_KEY> with the API key from your token settings.
Authentication
All requests must include Authorization: Bearer <TOKEN> header. Anthropic-formatted endpoints accept the x-api-key header instead.
Generate tokens from the Tokens page; you can scope them to specific models, groups, IPs, and rate-limits.
Supported parameters
Generation parameters
| Parameter | Type | Default / range | Description |
|---|---|---|---|
temperature | number | = 10 ~ 2 | Sampling temperature; lower is more deterministic |
top_p | number | = 10 ~ 1 | Nucleus sampling probability mass |
max_tokens | integer | >= 1 | Maximum number of tokens in the response |
frequency_penalty | number | = 0-2 ~ 2 | Penalises repetition of frequent tokens |
presence_penalty | number | = 0-2 ~ 2 | Encourages introducing new topics |
stop | array | — | Up to 4 strings that stop generation |
seed | integer | — | Deterministic sampling seed (best-effort) |
n | integer | = 1>= 1 | Number of completions to generate |
stream | boolean | = false | Stream tokens via Server-Sent Events |
response_format | object | — | Force JSON object or schema-conforming output |
tools | array | — | Tool / function declarations the model may call |
tool_choice | string | autononerequired | Tool-choice policy or specific tool name |
logprobs | boolean | = false | Return per-token log probabilities |
top_logprobs | integer | 0 ~ 20 | Number of top log probabilities returned per token |
logit_bias | object | — | Per-token logit bias map |
user | string | — | End-user identifier for abuse monitoring |
Rate limits
| Supplier | RPM | TPM | RPD |
|---|---|---|---|
| AmazonBedrock | 480 | 190K | 9.5K |
| Anthropic | 670 | 269K | 14K |
| CCMax | 580 | 232K | 12K |
| CCMax-ZL | 700 | 281K | 14K |
| Claude kiro | 1.0K | 399K | 20K |
| claude特供 | 540 | 215K | 11K |
| default | 410 | 165K | 8.2K |
RPM = requests per minute, TPM = tokens per minute, RPD = requests per day. Limits apply per token group.
API access questions
Everything you need to decide before creating an account.