Documentation Index Fetch the complete documentation index at: https://docs.tokenlab.sh/llms.txt
Use this file to discover all available pages before exploring further.
错误响应格式
所有错误返回一致的 JSON 格式,并可选包含 Agent-First hints :
{
"error" : {
"message" : "Human-readable error description" ,
"type" : "error_type" ,
"code" : "error_code" ,
"param" : "parameter_name" ,
"did_you_mean" : "suggested_model" ,
"suggestions" : [{ "id" : "model-id" }],
"hint" : "Next step guidance" ,
"retryable" : true ,
"retry_after" : 30
}
}
基础字段(message, type, code, param)始终存在。提示字段(did_you_mean, suggestions, hint, retryable, retry_after, balance_usd, estimated_cost_usd)是用于 AI agent 自我纠正的可选扩展。详情见 Agent-First API guide 。
兼容 OpenAI 的端点使用 TokenLab 的稳定网关错误类型。兼容 Anthropic 和 Gemini 的端点使用它们各自原生的错误类别和响应格式。
HTTP 状态码
代码 描述 400 错误请求 - 参数无效 401 未授权 - API key 无效或缺失 402 需要付款 - 余额不足 403 禁止 - 访问被拒或模型不允许 404 未找到 - 模型或资源未找到 413 负载过大 - 输入或文件大小超限 429 请求过多 - 超出速率限制 500 服务器内部错误 502 错误网关 - 上游提供商错误 503 服务不可用 - 服务暂时不可用 504 网关超时 - 请求超时
错误类型
认证错误 (401)
类型 代码 描述 invalid_api_keyinvalid_api_keyAPI key 缺失或无效 expired_api_keyexpired_api_keyAPI key 已被撤销
from openai import OpenAI, AuthenticationError
try :
response = client.chat.completions.create( ... )
except AuthenticationError as e:
print ( f "Authentication failed: { e.message } " )
支付错误 (402)
类型 代码 描述 insufficient_balanceinsufficient_balance账户余额过低 quota_exceededquota_exceededAPI key 使用限额已达
from openai import OpenAI, APIStatusError
try :
response = client.chat.completions.create( ... )
except APIStatusError as e:
if e.status_code == 402 :
print ( "Please top up your account balance" )
访问错误 (403)
类型 代码 描述 access_deniedaccess_denied访问资源被拒绝 access_deniedmodel_not_allowed该 API key 不允许使用此模型
{
"error" : {
"message" : "You don't have permission to access this model" ,
"type" : "access_denied" ,
"code" : "model_not_allowed"
}
}
验证错误 (400)
类型 描述 invalid_request_error请求参数无效 context_length_exceeded输入超出模型的上下文长度 model_not_found请求的模型在当前公共合约中不可用
{
"error" : {
"message" : "Model not found: please check the model name" ,
"type" : "invalid_request_error" ,
"param" : "model" ,
"code" : "model_not_found" ,
"did_you_mean" : "gpt-5.4" ,
"suggestions" : [{ "id" : "gpt-5.4" }, { "id" : "gpt-5-mini" }],
"hint" : "Did you mean 'gpt-5.4'? Use GET https://api.tokenlab.sh/v1/models to list all available models."
}
}
公共路由不会在响应体中区分拼写错误、隐藏、延迟或非公开的模型状态。如果模型当前无法通过公共合约访问,TokenLab 会返回 model_not_found。
速率限制错误 (429)
当超过速率限制时:
{
"error" : {
"message" : "Rate limit: 60 rpm exceeded" ,
"type" : "rate_limit_exceeded" ,
"code" : "rate_limit_exceeded" ,
"retryable" : true ,
"retry_after" : 8 ,
"hint" : "Rate limited. Retry after 8s. Current limit: 60/min for user role."
}
}
包含的头部:
Retry-After 头和 retry_after 字段都指示在重试前应等待的确切秒数。
负载过大 (413)
当输入或文件大小超过限制时:
{
"error" : {
"message" : "Input size exceeds maximum allowed" ,
"type" : "invalid_request_error" ,
"code" : "payload_too_large"
}
}
常见原因:
图像文件过大(最大 20MB)
音频文件过大(最大 25MB)
输入文本超过模型上下文长度
上游错误 (502, 503)
类型 描述 upstream_error提供方返回错误 all_channels_failed没有可用的提供方 timeout_error请求超时
当所有通道都失败时,响应会包含备选模型:
{
"error" : {
"message" : "Model claude-opus-4-6 temporarily unavailable" ,
"code" : "all_channels_failed" ,
"retryable" : true ,
"retry_after" : 30 ,
"alternatives" : [
{ "id" : "claude-sonnet-4-6" , "status" : "available" , "tags" : []},
{ "id" : "gpt-5-mini" , "status" : "available" , "tags" : []}
],
"hint" : "Retry in 30s or switch to an available model."
}
}
在 Python 中处理错误
from openai import OpenAI, APIError, RateLimitError, APIConnectionError
client = OpenAI(
api_key = "sk-your-api-key" ,
base_url = "https://api.tokenlab.sh/v1"
)
def chat_with_retry ( messages , max_retries = 3 ):
for attempt in range (max_retries):
try :
return client.chat.completions.create(
model = "gpt-4o" ,
messages = messages
)
except RateLimitError as e:
if attempt < max_retries - 1 :
import time
time.sleep( 2 ** attempt) # Exponential backoff
continue
raise
except APIConnectionError as e:
print ( f "Connection error: { e } " )
raise
except APIError as e:
print ( f "API error: { e.status_code } - { e.message } " )
raise
在 JavaScript 中处理错误
import OpenAI from 'openai' ;
const client = new OpenAI ({
apiKey: 'sk-your-api-key' ,
baseURL: 'https://api.tokenlab.sh/v1'
});
async function chatWithRetry ( messages , maxRetries = 3 ) {
for ( let attempt = 0 ; attempt < maxRetries ; attempt ++ ) {
try {
return await client . chat . completions . create ({
model: 'gpt-4o' ,
messages
});
} catch ( error ) {
if ( error instanceof OpenAI . RateLimitError ) {
if ( attempt < maxRetries - 1 ) {
await new Promise ( r => setTimeout ( r , 2 ** attempt * 1000 ));
continue ;
}
}
throw error ;
}
}
}
最佳实践
当受到速率限制时,在重试之间逐步延长等待时间: wait_time = 2 ** attempt # 1s, 2s, 4s, 8s...
始终设置合理的超时时间以避免请求挂起: client = OpenAI( timeout = 60.0 ) # 60 second timeout
记录完整的错误响应,包括请求 ID 以便支持: except APIError as e:
logger.error( f "API Error: { e.status_code } - { e.message } " )
一些模型有特定要求(例如,最大 tokens、图像格式)。在发起请求前验证输入。