glm-5.2 has no entry in the fallback table, so getFallbackPricing falls
through to `strings.Contains(modelLower, "glm-5")` and prices it at
GLM-5 rates ($1.00 in / $3.20 out per MTok) instead of the official
z.ai rates ($1.40 / $4.40) — roughly 27% under.
LiteLLM carries no bare `glm-5.2` key either (only provider-prefixed
`cloudflare/@cf/zai-org/glm-5.2` and `fireworks_ai/.../glm-5p2`, which
the lookup candidates never match), so the request always lands on the
fallback path and the discrepancy shows up directly in usage logs.
Add the glm-5.2 entry (same price as glm-5.1 per docs.z.ai) and match it
before the bare `glm-5` branch, with a note that dotted variants must
precede it. The existing regression test asserting the old glm-5 price
is updated accordingly.
Source: https://docs.z.ai/guides/overview/pricing
Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Follow-up fixes for the #3775 audit findings:
- Bill Grok video generation per second of output, matching the xAI rate
card: parse the request duration (1-15s, upstream default 8s) and compute
cost as per-second price x duration x count. The built-in rate card values
were already xAI per-second prices but were previously charged per video,
undercharging up to 15x with a user-controlled duration.
- Group video_price_* fields are now documented and surfaced as per-second
rates (USD/s); admin UI labels, placeholders and hints updated accordingly.
- Persist video_count/video_resolution/video_duration_seconds on usage_logs
(migration 172) so video billing is auditable, and exempt any row with
video_count > 0 from the image_size check constraint: a video billed via a
token-mode channel price produces billing_mode='token' with image_count=1
and no image_size, which the previous constraint rejected, dropping the
whole billing transaction.
- Only refetch the group in apiKeyWithFreshGroupMediaPricing when the group
object actually looks like it is missing media pricing fields (both media
multipliers zero and all prices nil, impossible for a normally loaded
group), removing a per-usage DB query for groups without overrides.
- Frontend: drop the unused admin.groups.mediaPricing locale block, map
cleared price inputs to null (create) / -1 (update, cleared via backend
normalizePrice) instead of sending "" that failed *float64 unmarshalling,
and align video price placeholders with the text-to-video default model
(grok-imagine-video 0.05/0.07, 1080p only on 1.5 at 0.25).
避免 Codex OAuth 模型归一化把 gpt-5.5-pro 降级为 gpt-5.5。\n\n同时补充 GPT-5.5 Pro 的计费回退与长上下文计费策略，保证保留上游模型名后仍使用现有 GPT-5.5/GPT-5.4 计费规则。\n\n验证：\n- go test ./internal/service/...\n- go build ./cmd/server/
The "[Billing] Using fallback pricing for model: X" warn was emitted on
every request for any model not in LiteLLM but matched by getFallbackPricing
(e.g. "glm-5.2" substring-matches the "glm-5" fallback price). Via the stdlib
log bridge it is inferred as WARN and persisted to ops_system_logs, producing
tens of thousands of rows/day. It fired even when channel pricing already
overrides the price, and from several call sites (resolver, account-stats
pricing, non-channel billing, admin lookup).
Dedup the warn at the source (BillingService.GetModelPricing) via a sync.Map
keyed by the already-lowercased model name, so each model logs at most once
per process while keeping one audit line. Billing amounts are unchanged.
Also clarify the model/mapping pattern conflict error to state that names are
matched case-insensitively, so an existing entry (e.g. "GLM-5.2") already
covers all case variants and the lowercase variant need not be added — the
behavior the issue mistook for a case-sensitivity bug.
Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Address copilot-pull-request-reviewer feedback on #2157:
- billing_service_test.go: extend TestGetFallbackPricing_FamilyMatching
with optional expectedOutput / expectedCacheRead fields and assert
full Input/Output/CacheRead pricing for all 4 DeepSeek cases
(v4-pro, v4-flash, deepseek-chat→flash, deepseek-reasoner→flash),
preventing silent regression to 0 output/cache cost.
- billing_service.go: rewrite the DeepSeek block comment to explicitly
describe its scope (V4 Pro/Flash + chat/reasoner aliases, no
unknown-deepseek fallback) and tighten the OpenAI comment to make
it unambiguous that it only describes the OpenAI/Codex branch
immediately below it.
When channel pricing is configured, image output token price now
correctly overrides all other sources (LiteLLM, group config).
Add ImageOutputPriceExplicit flag to distinguish intentional zero
price from missing price, preventing fallback to output price.
Affects Gemini, OpenAI inline image gen, and Images API paths.
Follow-up to #2816 (already merged): the same long-context pricing
exemption that affected cache_read also applies to all three
cache_creation price fields (standard, 5m ephemeral, 1h ephemeral).
computeCacheCreationCost reads these prices directly from pricing and
never sees the LongContextInputMultiplier that computeTokenBreakdown
applies to inputPrice / outputPrice / cacheReadPrice.
For GPT-5.4 / 5.5 above the 272k threshold, this causes the cache_write
portion of long sessions to be billed at roughly half what it should
be (default multiplier 2.0). Cache writes are conceptually input-side
operations and should share the same long-context treatment as input /
cache_read.
This patch threads an explicit multiplier into computeCacheCreationCost
so the function can be unit-tested in isolation and matches the existing
pattern used for cache_read. computeTokenBreakdown captures the long
context decision once and passes LongContextInputMultiplier when it
applies, 1.0 otherwise.
Adds three regression tests mirroring the #2816 cache_read tests:
- positive: long-context triggered -> cache_creation scaled by 2.0x
- negative: below threshold -> cache_creation stays at base price
- breakdown: 5m + 1h ephemeral prices both scaled when applicable
Refs #2816
Co-authored-by: Cursor <cursoragent@cursor.com>
When session long-context pricing is triggered in computeTokenBreakdown
(e.g. GPT-5.4 / GPT-5.5 above the 272k token threshold), the multiplier
was only being applied to InputPricePerToken and OutputPricePerToken.
The cache_read price was left at its base value, so CacheReadCost was
silently undercharged whenever a long-context session also had cache
hits — which is essentially every long Codex / Claude Code session.
Concretely for gpt-5.4 with 300k cache_read tokens, the bug
under-billed the request by exactly 1x the LongContextInputMultiplier
on the cache portion (e.g. 0.075 instead of 0.150 in the regression
test).
Cache reads are conceptually input-side replays, so they should scale
with LongContextInputMultiplier, matching the treatment of
InputPricePerToken.
Adds two regression tests:
- positive: long-context triggered -> cache_read scaled by 2.0x
- negative: below threshold -> cache_read stays at base price
Fixes#2293
Co-authored-by: Cursor <cursoragent@cursor.com>
