new-api

0 Fork 0

mirror of https://github.com/QuantumNous/new-api.git synced 2026-10-28 08:35:33 +08:00

Files

T

History

Calcium-Ion e9d4d6353c feat(billing): bill OpenAI 12-hour prompt cache writes at their own price (#7965 )

OpenAI added a 12-hour prompt cache to the Responses API on 2026-10-20
(prompt_cache_options.ttl "12h", GPT-5.6 and later). A 12-hour write
costs 2.5x the input price, twice the 30-minute write. We already
forwarded the option but billed every cache write at the 30-minute price.

- Read cache_write_tokens_details from Responses usage and keep the split
  through streaming, compaction and format conversion.
- Ratio pricing bills 12-hour writes at twice the cache write ratio, the
  same way Claude 1-hour writes use 6/3.75.
- Expressions get a cc12h price. When an expression leaves the long-lived
  price out, 12-hour writes cost twice the cc price and Claude 1-hour
  writes 6/3.75 times it; without a cc price they bill as input. Claude
  cache writes are no longer free when an expression omits cc or cc1h.
- gpt-6-astra prices 12-hour writes at $25 ($50 above 272K tokens).
- GPT models with a cache write ratio convert to expressions with cc12h.
- Chat Completions forwards prompt_cache_options.
- The pricing editor, cost estimator, pricing pages and usage log details
  show the 12-hour price and tokens.

2026-10-22 22:41:17 +08:00

access_token_audit_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

access_token.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

admin_user_verification_test.go

fix(auth): reject non-standard roles when creating a user

2026-09-30 20:52:10 +08:00

audit.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

auth_flow_test.go

fix(oauth): require account evidence before migrating legacy GitHub bindings

2026-09-18 23:00:37 +08:00

auth_session_test.go

fix(oauth): require account evidence before migrating legacy GitHub bindings

2026-09-18 23:00:37 +08:00

auth_session.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

authz.go

feat: better admin permissions (#5755 )

2026-06-27 17:01:59 +08:00

billing_option_test.go

feat(billing): configure trust threshold and input pre-consume multiplier

2026-09-20 22:17:20 +08:00

billing.go

refactor: extract protocol conversion layer into standalone relaykit module (#6369 )

2026-07-27 15:56:21 +08:00

channel_affinity_cache.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

channel_authz_test.go

refactor: modernize Go code conventions

2026-09-08 20:55:03 +08:00

channel_authz.go

feat: better admin permissions (#5755 )

2026-06-27 17:01:59 +08:00

channel_billing_sub2api_test.go

feat(channel): support Sub2API balance queries (#7749 )

2026-10-13 12:36:43 +08:00

channel_billing_test.go

fix: fall back to CNY when DeepSeek USD wallet is zero (#7917 )

2026-10-20 22:39:42 +08:00

channel_inference_test.go

feat: vllm channel && sglang channel (#7332 )

2026-09-15 00:06:42 +08:00

channel_inference.go

feat: vllm channel && sglang channel (#7332 )

2026-09-15 00:06:42 +08:00

channel_multi_key_test.go

Add Responses WebSocket relay support (#5062 )

2026-09-14 21:04:26 +08:00

channel_pin_retry_test.go

feat(policy): add request policies settings and routing decision records

2026-09-18 11:24:29 +08:00

channel_priority.go

feat(channels): add drag mode for channel priority ordering

2026-10-17 20:19:41 +08:00

channel_task_plugin_bind_test.go

feat(channel): bind multiple task plugins to New API channels

2026-09-20 17:51:51 +08:00

channel_task_plugin_validation_test.go

feat(channel): bind multiple task plugins to New API channels

2026-09-20 17:51:51 +08:00

channel_test_internal_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

channel_test_request_test.go

fix: use max_completion_tokens for gpt-6-sol and gpt-6-luna (#7559 )

2026-09-30 21:50:05 +08:00

channel_upstream_update_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

channel_upstream_update.go

feat(channel): add a per-channel switch to skip upstream TLS verification

2026-10-10 14:02:06 +08:00

channel-billing.go

fix: fall back to CNY when DeepSeek USD wallet is zero (#7917 )

2026-10-20 22:39:42 +08:00

channel-test.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

channel.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

checkin.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

codex_usage.go

feat(channel): add a per-channel switch to skip upstream TLS verification

2026-10-10 14:02:06 +08:00

custom_oauth.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

deployment.go

refactor: modernize Go code conventions

2026-09-08 20:55:03 +08:00

email_binding.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

email_delivery_test.go

feat(email): 添加 resend 邮件服务商接口 (#7880 )

2026-10-19 20:22:37 +08:00

group.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

image.go

feat: support dify upload image file

2025-03-15 19:10:12 +08:00

log_export_test.go

feat(logs): export usage logs from the common log page (#7774 )

2026-10-12 21:33:53 +08:00

log.go

feat(logs): export usage logs from the common log page (#7774 )

2026-10-12 21:33:53 +08:00

login_verification.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

midjourney.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

misc_oidc_test.go

feat(oidc): 支持自定义 OIDC 登录显示名称 (#6012 )

2026-07-29 16:27:15 +08:00

misc.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

missing_models.go

format: package name -> github.com/QuantumNous/new-api (#2017 )

2025-10-11 15:30:09 +08:00

model_list_test.go

fix(oauth): require account evidence before migrating legacy GitHub bindings

2026-09-18 23:00:37 +08:00

model_management_test.go

feat(billing): bill OpenAI 12-hour prompt cache writes at their own price (#7965 )

2026-10-22 22:41:17 +08:00

model_meta.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

model_owned_by_test.go

Feat/auto group (#6590 )

2026-08-01 23:19:01 +08:00

model_pricing_config.go

feat(pricing): convert legacy prices into expression drafts

2026-09-11 21:44:54 +08:00

model_pricing_conversion_endpoints_test.go

fix(pricing): accept declared endpoint arrays in pricing conversion (#7724 )

2026-10-12 17:57:53 +08:00

model_sync.go

fix: isolate TLS configs across HTTP transports (#7627 )

2026-09-30 21:49:33 +08:00

model.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

oauth.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

option_claude_test.go

refactor: extract protocol conversion layer into standalone relaykit module (#6369 )

2026-07-27 15:56:21 +08:00

option_gemini_test.go

refactor: extract protocol conversion layer into standalone relaykit module (#6369 )

2026-07-27 15:56:21 +08:00

option.go

feat(email): 添加 resend 邮件服务商接口 (#7880 )

2026-10-19 20:22:37 +08:00

passkey_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

passkey.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

payment_compliance.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

payment_webhook_availability_test.go

fix(epay): upgrade go-epay to v0.0.5

2026-10-07 21:26:35 +08:00

payment_webhook_availability.go

[Feature Request] Waffo Pancake gateway — full integration with subscription support + admin catalog binding flow (#4935 )

2026-05-22 11:00:58 +08:00

perf_metrics.go

fix(pricing): show recent status samples without gaps

2026-10-10 19:24:32 +08:00

performance.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

playground.go

fix(relay): mask only the custom upstream address in error messages (#7822 )

2026-10-15 15:49:45 +08:00

plugin_endpoint_test.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

plugin_native_e2e_test.go

fix(task): reprice each retry and reserve it before submission

2026-10-20 22:43:11 +08:00

plugin_protocol_image.go

fix(relay): mask only the custom upstream address in error messages (#7822 )

2026-10-15 15:49:45 +08:00

plugin_protocol_limiter_test.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

plugin_protocol_limiter.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

plugin_protocol_sdk_test.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

plugin_protocol_test.go

fix(relay): mask only the custom upstream address in error messages (#7822 )

2026-10-15 15:49:45 +08:00

plugin_protocol.go

fix(relay): stop cutting off slow clients during large stream events

2026-10-22 16:23:17 +08:00

prefill_group.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

pricing.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

rankings.go

fix: enforce header nav access control for public modules (#4889 )

2026-05-16 14:54:47 +08:00

ratio_config.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

ratio_sync_test.go

feat(pricing): adjust synced upstream prices by the site exchange rate

2026-10-22 16:23:19 +08:00

ratio_sync.go

feat(pricing): adjust synced upstream prices by the site exchange rate

2026-10-22 16:23:19 +08:00

redemption_batch_test.go

feat(redemptions): add batch deletion and optional file exports

2026-09-08 20:47:01 +08:00

redemption.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

relay_count_tokens_test.go

feat(relay): hosted-tool conversion fidelity, reasoning normalization, and billing usage integrity (#7137 )

2026-09-01 21:53:35 +08:00

relay_error_log_test.go

feat(logs): export usage logs from the common log page (#7774 )

2026-10-12 21:33:53 +08:00

relay_stream_test.go

fix(relay): Claude 流式请求在准备和重试期间持续保活 (#7857 )

2026-10-19 19:25:11 +08:00

relay_task_plugin_test.go

fix(task): reprice each retry and reserve it before submission

2026-10-20 22:43:11 +08:00

relay.go

fix(relay): stop cutting off slow clients during large stream events

2026-10-22 16:23:17 +08:00

request_policy.go

feat(policy): add request policies settings and routing decision records

2026-09-18 11:24:29 +08:00

responses_websocket_test.go

fix(relay): send a close frame when a Responses WebSocket session ends

2026-10-11 17:10:53 +08:00

responses_websocket.go

fix(relay): mask only the custom upstream address in error messages (#7822 )

2026-10-15 15:49:45 +08:00

return_path_test.go

refactor(auth): replace dashboard sessions with stateless tokens and session control (#6329 )

2026-07-20 16:48:43 +08:00

return_path.go

refactor(auth): replace dashboard sessions with stateless tokens and session control (#6329 )

2026-07-20 16:48:43 +08:00

revalidated_response.go

fix: keep ETag valid across different JSON packages

2026-09-03 20:42:57 +08:00

secure_verification.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

security_account_test.go

test(security): match the email code only as a whole number

2026-10-20 22:43:11 +08:00

security_enrollment_test.go

fix(ci): stabilize checks and configure Bun dependency updates (#7765 )

2026-10-12 18:19:04 +08:00

setup.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

subscription_payment_creem.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

subscription_payment_epay.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

subscription_payment_stripe.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

subscription_payment_waffo_pancake.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

subscription.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

system_info.go

feat(system-info): add stale instance cleanup actions (#5953 )

2026-07-07 21:22:49 +08:00

system_task_handlers.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

system_task_test.go

feat(system-tasks): add filtered task history with cleanup

2026-09-18 11:24:30 +08:00

system_task.go

feat(system-tasks): add filtered task history with cleanup

2026-09-18 11:24:30 +08:00

task_generic_test.go

fix(task): 修复任务提交与轮询的请求头覆盖 (#7918 )

2026-10-20 20:50:02 +08:00

task_log_view_test.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

task_plugin_debug_test.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

task_plugin_debug.go

feat(task): replace built-in task adaptors with a sandboxed JS plugin system (#7076 )

2026-08-29 18:51:57 +08:00

task_plugin_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

task_plugin.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

task.go

fix(task): 修复任务提交与轮询的请求头覆盖 (#7918 )

2026-10-20 20:50:02 +08:00

telegram_test.go

refactor: modernize Go code conventions

2026-09-08 20:55:03 +08:00

telegram.go

feat(auth): migrate Telegram to unified OAuth

2026-09-06 22:48:59 +08:00

theme_compat_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

token_auto_groups_test.go

Feat/auto group (#6590 )

2026-08-01 23:19:01 +08:00

token_test.go

feat(token): let an API key read its owner's quota

2026-10-13 21:39:52 +08:00

token.go

feat(token): let an API key read its owner's quota

2026-10-13 21:39:52 +08:00

topup_creem.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

topup_quota_limit_test.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

topup_stripe.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

topup_waffo_pancake_test.go

refactor: modernize Go code conventions

2026-09-08 20:55:03 +08:00

topup_waffo_pancake.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

topup_waffo.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

topup.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

twofa.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

uptime_kuma.go

refactor: modernize Go code conventions

2026-09-08 20:55:03 +08:00

usedata_flow_test.go

feat(dashboard): add traffic flow sankey chart (#5465 )

2026-06-20 18:57:47 +08:00

usedata.go

feat(logs): export usage logs from the common log page (#7774 )

2026-10-12 21:33:53 +08:00

user_manage_test.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

user_quota.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

user.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00

vendor_meta.go

feat(i18n): translate web console messages in the frontend and AI-client errors in the backend (#7712 )

2026-10-09 21:39:51 +08:00

video_proxy.go

feat(channel): add a per-channel switch to skip upstream TLS verification

2026-10-10 14:02:06 +08:00

wechat.go

feat(notify): turn each kind of notification on or off (#7868 )

2026-10-17 22:17:59 +08:00