Modelsell
Claude

claude-sonnet-5

AnthropicToken-based
Create API Key

Anthropic 的 claude-sonnet-5 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
Jan 2026
Released
Jun 2026

Pricing by Supplier

Anthropic
-10%
Anthropic 官方
Input$2$1.8/ 1M
Output$10$9/ 1M
Cache Read$0.2$0.18/ 1M
Cache Write (5m)$2.5$2.25/ 1M
Cache Write (1h)$4$3.6/ 1M
AmazonBedrock
-40%
AWS 官方
Input$2$1.2/ 1M
Output$10$6/ 1M
Cache Read$0.2$0.12/ 1M
Cache Write (5m)$2.5$1.5/ 1M
Cache Write (1h)$4$2.4/ 1M
Vertex Claude
-30%
Google Vertex 官方 Claude直连
Input$2$1.4/ 1M
Output$10$7/ 1M
Cache Read$0.2$0.14/ 1M
Cache Write (5m)$2.5$1.75/ 1M
Cache Write (1h)$4$2.8/ 1M
claude特供
-40%
适合生产环境，AWS Bedrock组成
Input$2$1.2/ 1M
Output$10$6/ 1M
Cache Read$0.2$0.12/ 1M
Cache Write (5m)$2.5$1.5/ 1M
Cache Write (1h)$4$2.4/ 1M
CCMax
-70%
使用自用 vibe coding，纯血 ccmax号池
Input$2$0.6/ 1M
Output$10$3/ 1M
Cache Read$0.2$0.06/ 1M
Cache Write (5m)$2.5$0.75/ 1M
Cache Write (1h)$4$1.2/ 1M
Claude kiro
-90%
使用自用 vibe coding，kiro号池
Input$2$0.2/ 1M
Output$10$1/ 1M
Cache Read$0.2$0.02/ 1M
Cache Write (5m)$2.5$0.25/ 1M
Cache Write (1h)$4$0.4/ 1M
CCMax-ZL
-70%
CCmax微注-可蒸
Input$2$0.6/ 1M
Output$10$3/ 1M
Cache Read$0.2$0.06/ 1M
Cache Write (5m)$2.5$0.75/ 1M
Cache Write (1h)$4$1.2/ 1M

Capabilities / Supported modalities

StreamingFunction callingToolsVisionReasoningPrompt caching
Input
Output

Provider & data privacy

Provider
AnthropicDocs
Tokenizer
Anthropic Claude tokenizer
License
Proprietary (commercial)Proprietary
Data retention44 daysNot used for upstream training by default

Performance

API access

Code samples

RequestPOST/v1/messages
Example request
Parameters
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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
ParameterTypeDefault / rangeDescription
temperature
number
=10 ~ 2
Sampling temperature; lower is more deterministic
top_p
number
=10 ~ 1
Nucleus sampling probability mass
max_tokens
integer>= 1Maximum 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
integer0 ~ 20Number 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

SupplierRPMTPMRPD
AmazonBedrock540216K11K
Anthropic860344K17K
CCMax640254K13K
CCMax-ZL500198K9.9K
Claude kiro760302K15K
Claude kiro ZL860344K17K
claude特供800320K16K
default570227K11K
Vertex Claude350139K6.9K

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.

Discover more models