返回 CodeWhale
default_coverage_unpriced.json
根目录 / crates / tui / src / pricing / default_coverage_unpriced.json
1 [
2 {
3 "reason": "no_pricing_row",
4 "review": "Source reviewed at 36f11b82; fixture recorded time is 2026-09-08T12:00Z with 1000 input/100 output and no cache usage or live/signed/override price state. Exact default tuples below have no usable provider-owned bundled/hand row (pricing.rs:1639,1674,2282; provider_lake.rs:993). OpenRouter official identity with no frozen quote uses immutable bundled fallback (pricing.rs:2011,2089); its DeepSeek Pro row is costless. Zen resolves gpt-5.6 to wire gpt-5.6-sol (route/offering.rs:312), while its hand fallback prices only DeepSeek Flash (pricing.rs:2426). Wanjie is not the direct-DeepSeek retired-alias/hand-price owner. No numeric rates or model-owner rates are inferred. ZenMux review: metered OpenAI-compatible aggregator; its deepseek/deepseek-v4.1-flash default has no bundled/hand pricing row and resolves costless until the live catalog prices it. ModelScope review (ba62522a20 omitted this row): same shape — metered default with no bundled/hand row in pricing.rs.",
5 "routes": [
6 ["atlascloud", "deepseek-ai/deepseek-v4-flash", "https://api.atlascloud.ai/v1", "chat_completions", "metered"],
7 ["codewhale", "deepseek/deepseek-v4-pro", "https://api.codewhale.net/v1", "chat_completions", "metered"],
8 ["deepinfra", "deepseek-ai/DeepSeek-V4-Pro", "https://api.deepinfra.com/v1/openai", "chat_completions", "metered"],
9 ["edenai", "deepseek/deepseek-v4-pro", "https://api.edenai.run/v3", "chat_completions", "metered"],
10 ["google", "gemini-3.1-pro-preview", "https://generativelanguage.googleapis.com/v1beta/openai", "chat_completions", "metered"],
11 ["huggingface", "deepseek-ai/DeepSeek-V4-Pro", "https://router.huggingface.co/v1", "chat_completions", "metered"],
12 ["longcat", "LongCat-2.0", "https://api.longcat.chat/openai/v1", "chat_completions", "metered"],
13 ["modelscope", "Qwen/Qwen3.5-397B-A17B", "https://api-inference.modelscope.cn/v1", "chat_completions", "metered"],
14 ["novita", "deepseek/deepseek-v4-pro", "https://api.novita.ai/openai/v1", "chat_completions", "metered"],
15 ["nvidia-nim", "deepseek-ai/deepseek-v4-pro", "https://integrate.api.nvidia.com/v1", "chat_completions", "metered"],
16 ["opencode-zen", "gpt-5.6-sol", "https://opencode.ai/zen/v1", "responses", "metered"],
17 ["openmodel", "deepseek-v4-flash", "https://api.openmodel.ai", "anthropic_messages", "metered"],
18 ["openrouter", "deepseek/deepseek-v4-pro", "https://openrouter.ai/api/v1", "chat_completions", "metered"],
19 ["orcarouter", "deepseek/deepseek-v4-pro", "https://api.orcarouter.ai/v1", "chat_completions", "metered"],
20 ["qianfan", "ernie-4.0-turbo-8k", "https://api.baiduqianfan.ai/v1", "chat_completions", "metered"],
21 ["sakana", "fugu", "https://api.sakana.ai/v1", "chat_completions", "metered"],
22 ["siliconflow", "deepseek-ai/DeepSeek-V4-Pro", "https://api.siliconflow.com/v1", "chat_completions", "metered"],
23 ["siliconflow-CN", "deepseek-ai/DeepSeek-V4-Pro", "https://api.siliconflow.cn/v1", "chat_completions", "metered"],
24 ["telecomjs", "deepseek-v4-pro", "https://aigw.telecomjs.com/v1", "chat_completions", "metered"],
25 ["together", "deepseek-ai/DeepSeek-V4-Pro", "https://api.together.xyz/v1", "chat_completions", "metered"],
26 ["wanjie-ark", "deepseek-reasoner", "https://maas-openapi.wanjiedata.com/api/v1", "chat_completions", "metered"],
27 ["zenmux", "deepseek/deepseek-v4.1-flash", "https://zenmux.ai/api/v1", "chat_completions", "metered"]
28 ]
29 },
30 {
31 "reason": "unverified_live_pricing",
32 "review": "Baseten exact named template+endpoint is recognized by the production envelope despite default Unknown mode (cost_status.rs:230; pricing.rs:2149); absent frozen quote fails with UnverifiedLivePricing (pricing.rs:2018). The old test-only identity-free audit helper is not this production path.",
33 "routes": [
34 ["baseten", "deepseek-ai/DeepSeek-V4-Pro", "https://inference.baseten.co/v1", "chat_completions", "unknown"]
35 ]
36 },
37 {
38 "reason": "unknown_billing_basis",
39 "review": "No mode/credential product is supplied. Both MiniMax dialects share a PAYG/plan endpoint that cannot prove product (route_billing.rs:253,402; pricing.rs:534); Ollama Cloud is unclassified possible spend, not local/free (pricing.rs:411). Generic Custom and five non-Baseten compatible defaults are transport descriptors without a reviewed product; production envelope refuses Unknown at cost_status.rs:239.",
40 "routes": [
41 ["cerebras", "llama-3.3-70b", "https://api.cerebras.ai/v1", "chat_completions", "unknown"],
42 ["command-code", "deepseek/deepseek-v4-flash", "https://api.commandcode.ai/provider/v1", "chat_completions", "unknown"],
43 ["custom", "custom-model", "http://localhost/v1", "chat_completions", "unknown"],
44 ["dashscope", "qwen3.8-flash", "https://dashscope-intl.aliyuncs.com/compatible-mode/v1", "chat_completions", "unknown"],
45 ["groq", "llama-3.3-70b-versatile", "https://api.groq.com/openai/v1", "chat_completions", "unknown"],
46 ["minimax", "MiniMax-M3", "https://api.minimax.io/v1", "chat_completions", "unknown"],
47 ["minimax-anthropic", "MiniMax-M3", "https://api.minimax.io/anthropic", "anthropic_messages", "unknown"],
48 ["ollama-cloud", "gpt-oss:120b", "https://ollama.com/v1", "chat_completions", "unknown"],
49 ["sensenova", "deepseek-v4-flash", "https://token.sensenova.cn/v1", "chat_completions", "unknown"]
50 ]
51 },
52 {
53 "reason": "routing_dependent_price",
54 "review": "Concentrate is metered but may route upstream at different rates; no verified scoped offering/override reaches the explicit RoutingDependentPrice fallback (pricing.rs:1681). Endpoint is its production Responses route (provider.rs:1568); never inherit native DeepSeek rates.",
55 "routes": [
56 ["concentrate", "deepseek-v4-pro", "https://api.concentrate.ai/v1", "responses", "metered"]
57 ]
58 },
59 {
60 "reason": "not_money_metered",
61 "review": "Exact shipped plan/OAuth/local surfaces are excluded from money coverage before model-price lookup (route_billing.rs:345,470; pricing.rs:398; cost_status.rs:235). Retain exact dialect and plan endpoint distinctions; the same model on PAYG is a different tuple.",
62 "routes": [
63 ["csdn", "glm_for_coding", "https://ai.csdn.net/api/model/v1", "chat_completions", "subscription"],
64 ["modelstudio-coding-plan", "qwen3.8-max", "https://coding-intl.dashscope.aliyuncs.com/v1", "chat_completions", "subscription"],
65 ["modelstudio-coding-plan-anthropic", "qwen3.8-max", "https://coding-intl.dashscope.aliyuncs.com/apps/anthropic", "anthropic_messages", "subscription"],
66 ["modelstudio-token-plan", "qwen3.8-max", "https://token-plan.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1", "chat_completions", "subscription"],
67 ["modelstudio-token-plan-anthropic", "qwen3.8-max", "https://token-plan.ap-southeast-1.maas.aliyuncs.com/apps/anthropic", "anthropic_messages", "subscription"],
68 ["ollama", "unknown", "http://localhost:11434/v1", "chat_completions", "local"],
69 ["openai-codex", "gpt-5.6", "https://chatgpt.com/backend-api", "responses", "subscription"],
70 ["opencode-go", "deepseek-v4-pro", "https://opencode.ai/zen/go/v1", "chat_completions", "subscription"],
71 ["sglang", "deepseek-ai/DeepSeek-V4-Pro", "http://localhost:30000/v1", "chat_completions", "local"],
72 ["vllm", "deepseek-ai/DeepSeek-V4-Pro", "http://localhost:8000/v1", "chat_completions", "local"],
73 ["volcengine", "DeepSeek-V4-Pro", "https://ark.cn-beijing.volces.com/api/coding/v3", "chat_completions", "subscription"],
74 ["xiaomi-mimo", "mimo-v2.5-pro", "https://token-plan-sgp.xiaomimimo.com/v1", "chat_completions", "subscription"],
75 ["zai", "GLM-5.3", "https://api.z.ai/api/coding/paas/v4", "chat_completions", "subscription"]
76 ]
77 }
78 ]
79
79 lines JSON