@code-yeongyu/senpi-ai 2026.11.4-2 → 2026.11.6-1

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (33) hide show
  1. package/dist/api/anthropic-messages.js +2 -6
  2. package/dist/api/openai-images-params.d.ts +5 -0
  3. package/dist/api/openai-images-params.js +1 -0
  4. package/dist/api/openai-responses-prompt-cache.d.ts +2 -0
  5. package/dist/api/openai-responses-prompt-cache.js +6 -4
  6. package/dist/api/openai-responses-shared.d.ts +1 -0
  7. package/dist/api/openai-responses-shared.js +6 -1
  8. package/dist/api/openai-responses.js +75 -4
  9. package/dist/api/warm-prompt-cache.js +4 -3
  10. package/dist/auth/pool/slots.d.ts +13 -2
  11. package/dist/auth/pool/slots.js +136 -14
  12. package/dist/auth/types.d.ts +13 -2
  13. package/dist/index.d.ts +1 -1
  14. package/dist/index.js +1 -1
  15. package/dist/models.js +13 -3
  16. package/dist/providers/chatgpt-subscription.d.ts +1 -1
  17. package/dist/providers/chatgpt-subscription.js +68 -8
  18. package/dist/providers/data/.manifest.json +1 -1
  19. package/dist/providers/data/baseten.json +1 -1
  20. package/dist/providers/data/nvidia.json +1 -1
  21. package/dist/providers/data/openai.json +1 -1
  22. package/dist/providers/data/opencode-go.json +1 -1
  23. package/dist/providers/data/opencode.json +1 -1
  24. package/dist/providers/data/openrouter.json +1 -1
  25. package/dist/providers/data/radius.json +1 -1
  26. package/dist/providers/data/together.json +1 -1
  27. package/dist/providers/data/venice.json +1 -1
  28. package/dist/providers/data/vercel-ai-gateway.json +1 -1
  29. package/dist/types.d.ts +3 -2
  30. package/dist/utils/prompt-cache-ttl.d.ts +9 -0
  31. package/dist/utils/prompt-cache-ttl.js +15 -3
  32. package/dist/utils/provider-error.js +3 -2
  33. package/package.json +2 -2
@@ -1,24 +1,84 @@
1
1
  import { openAICodexResponsesApi } from "../api/openai-codex-responses.lazy.js";
2
+ import { openAIResponsesApi } from "../api/openai-responses.lazy.js";
2
3
  import { lazyOAuth } from "../auth/helpers.js";
3
- import { loadChatGptSubscriptionOAuth } from "../auth/oauth/load.js";
4
+ import { loadChatGptSubscriptionOAuth, loadOpenAIChatGPTOAuth } from "../auth/oauth/load.js";
4
5
  import { createProvider } from "../models.js";
5
6
  import { extractChatGptSubscriptionIdentity } from "../utils/chatgpt-subscription-auth.js";
6
7
  import { CHATGPT_SUBSCRIPTION_MODELS } from "./chatgpt-subscription.models.js";
7
8
  export function chatgptSubscriptionProvider() {
9
+ const legacy = lazyOAuth({
10
+ name: "ChatGPT Subscription (Plus/Pro)",
11
+ isSubscription: true,
12
+ accountIdentity: (credential) => extractChatGptSubscriptionIdentity(credential.access),
13
+ load: loadChatGptSubscriptionOAuth,
14
+ });
15
+ const siwc = lazyOAuth({
16
+ name: "ChatGPT Subscription",
17
+ isSubscription: true,
18
+ load: loadOpenAIChatGPTOAuth,
19
+ });
20
+ const responses = openAIResponsesApi();
21
+ const siwcModel = (model) => ({
22
+ ...model,
23
+ api: "openai-responses",
24
+ id: model.upstreamModelId ?? model.id,
25
+ compat: { ...model.compat, siwc: true, webSearchToolType: "web_search" },
26
+ });
8
27
  return createProvider({
9
28
  id: "chatgpt-subscription",
10
29
  name: "ChatGPT Subscription",
11
30
  baseUrl: "https://chatgpt.com/backend-api",
12
31
  auth: {
13
- oauth: lazyOAuth({
14
- name: "ChatGPT Subscription (Plus/Pro)",
15
- isSubscription: true,
16
- accountIdentity: (credential) => extractChatGptSubscriptionIdentity(credential.access),
17
- load: loadChatGptSubscriptionOAuth,
18
- }),
32
+ oauth: {
33
+ ...legacy,
34
+ loginLabel: "Continue with ChatGPT",
35
+ login: async (interaction, options) => {
36
+ if (options?.reauthorize) {
37
+ return options.reauthorize.route === "siwc"
38
+ ? { ...(await siwc.login(interaction, options)), route: "siwc" }
39
+ : legacy.login(interaction, options);
40
+ }
41
+ const route = await interaction.prompt({
42
+ type: "select",
43
+ message: "Sign in to ChatGPT Subscription:",
44
+ options: [
45
+ { id: "siwc", label: "Continue with ChatGPT" },
46
+ { id: "legacy", label: "Legacy sign-in (existing users)" },
47
+ ],
48
+ });
49
+ if (route === "legacy")
50
+ return legacy.login(interaction, options);
51
+ if (route !== "siwc")
52
+ throw new Error(`Unknown ChatGPT sign-in route: ${route}`);
53
+ return { ...(await siwc.login(interaction, options)), route: "siwc" };
54
+ },
55
+ refresh: async (credential, signal) => credential.route === "siwc"
56
+ ? { ...credential, ...(await siwc.refresh(credential, signal)), route: "siwc" }
57
+ : legacy.refresh(credential, signal),
58
+ revoke: async (credential, options) => {
59
+ const flow = await (credential.route === "siwc"
60
+ ? loadOpenAIChatGPTOAuth()
61
+ : loadChatGptSubscriptionOAuth());
62
+ return flow.revoke?.(credential, options) ?? { status: "remote_revocation_unconfirmed" };
63
+ },
64
+ toAuth: async (credential) => credential.route === "siwc"
65
+ ? {
66
+ ...(await siwc.toAuth(credential)),
67
+ api: "openai-responses",
68
+ baseUrl: "https://api.openai.com/v1",
69
+ compat: { siwc: true, webSearchToolType: "web_search" },
70
+ }
71
+ : legacy.toAuth(credential),
72
+ },
19
73
  },
20
74
  models: Object.values(CHATGPT_SUBSCRIPTION_MODELS),
21
- api: openAICodexResponsesApi(),
75
+ api: {
76
+ "openai-codex-responses": openAICodexResponsesApi(),
77
+ "openai-responses": {
78
+ stream: (model, context, options) => responses.stream(siwcModel(model), context, options),
79
+ streamSimple: (model, context, options) => responses.streamSimple(siwcModel(model), context, options),
80
+ },
81
+ },
22
82
  });
23
83
  }
24
84
  //# sourceMappingURL=chatgpt-subscription.js.map
@@ -1 +1 @@
1
- {"schemaVersion":6,"generatedAt":"2026-11-04T15:44:21.467Z","structureHash":"e9b66d443f6aea64fe1f14dd07b1574a94d7a8250fef0bc597a2663308fc4d45","files":{"alibaba-token-plan.json":"9f4d42cc765b2a875bcdcaa392bfdc1323c88968309baf9db9f611a26c595c73","amazon-bedrock.json":"a7e20838b095788cb9d5acbde49664b7f2868fad9b10fb4bbbd66635085bca2d","ant-ling.json":"628feab3ef6c7d80ce96f75999804e1d9f05fec3851e5302e30fff3b69db90f6","anthropic.json":"111384e9f5845e0247bd34edf2400ef7720fcbdac140b944cf8878192d8bd6ab","azure-openai-responses.json":"fd64c6a2a99fa87d768ed2f75f5c7813876df1dbe2f0d1776f7d9bd7ce2e61e4","bai.json":"7e6861aaf27d8af34e1771c6092602194fcec0a0046e6adfab9c3ee54d32b99f","baseten.json":"5bd3c98c61769388b3724368ef964d16b7a58e41a6edcf4ebceb9d4ac0a21d3b","cerebras.json":"2eb969b2956844f9a641d3de52c19f1791293c58f607282fb3b0ebfe85ff66f8","chatgpt-subscription.json":"98320f1d51709d26ca047b3d6e3191cfe2f192f1b27897cbb492f47b0e5a5030","cloudflare-ai-gateway.json":"ac281b8cc18eb84ba61f215eff3234d14732cd66239617fb59d6812b13d6473f","cloudflare-workers-ai.json":"1b9ad4360bde817f0ea358431020308f1052840e2278a57a93629f1790072d2e","deepseek.json":"10a296fb3e898f7715c80890c8af0af4f5fd58f22dbcd6612fdc5d762157ccdc","fireworks.json":"56c557eb97573028e871c211cb17e1d60665eb12d67a712615db4bb255bc9253","github-copilot.json":"474fa92eb88ef242208ca93709ebe6d7f21754917d0cad6210bd1edf2b99a87e","google-vertex.json":"8f986b4aca8c685b0f3481bd252bda21e4858bf9015ad37fc5bcc44b7f01d076","google.json":"d25613a7377e81d785d571be514d67b35436511ce6946247dc66f8674e2a5035","groq.json":"087df37206e9eed8b10f1e558e4c496289bef60074b7e8afba4f20fb102b4ec2","huggingface.json":"209cdcf205961ef2ff203486da614232a86a069ebe0e98266189a14a235fac8f","meta.json":"563f5ec07973f52ab8c3eb26ef91a36ad8a79e950b37174935666cdcb624bf35","minimax-cn.json":"70df757e95e9ea2275bf451956b58a746020835f6cbcbd1a644d7fad5b9941d3","minimax.json":"747038b05f4fc24e41405e8bc810f893d7d5121e214e35e6f812f775769a3806","mistral.json":"aafecc66686645b1baa8c90e81c02856115f09999ff507f9bee004d2e1c77a28","moonshotai-cn.json":"a953eace729ef96c91195d477c63c776a1c40aa36085b61236ca1be0fe5b9337","moonshotai.json":"0435f9dc4e532c0764b6d33d8dfa83ce5fccdbcab54224c5ae74ec2d965290f5","nvidia.json":"0e45bcd4d5a897f6f6785c0e257a9fb03691cef3ff87d9254da5daa5075468da","openai.json":"d61200cdd22d931dfff8181a5ed8d636c89fb34637dcec80f07ec24f8c2ef5c6","opencode-go.json":"de809e50975183fc8da3afb29a74bcf9164b6893271484588166a38b9930513f","opencode.json":"ff443ac2d4230e4fb0694c827a08dcb63421ae46b8b708141c1609189af536f5","opengateway.json":"c39301d5db2d88aee71705143a6039ebfce2513ef4648979125def43ef409d49","openrouter.json":"651672080ce8b06136b443400b9039d34909786f02a4fbaf47778f4b4057eb6c","qwen-token-plan-cn.json":"751b18bd443fceb16659ea33013fed90fbf3bbdb4e0ffd7607c93cee2b4cf40d","qwen-token-plan-individual.json":"35ffb0ba1a1ce3f68fc73262dd5e07fbcb5bf5911ad1e6e17bc0621e2894676a","qwen-token-plan.json":"e59b0a45e238578f80d0eea937a093b9cec7cb93751ae20a9e88b16c09eb5cdd","radius.json":"94ccbe953edd3ee194cacab98dbb92c4db99d26f190fe491384aa57a526fd659","together.json":"a68b8386a2f28f9e1570d296223fdbdc0ebcca8a322ade5b999212c0e60b772c","typesafe.json":"83409437dbf4c353ac413c0db4e7cf29902fc35e0e0197bdb4eeda2d7f3b07cd","venice.json":"cf6b67c0e15d62a126317e92897634c394f7aeefb5f6c5f99f7c885dbe963aab","vercel-ai-gateway.json":"88b219393d32f306d47008beb9b1b7344151d4ee096a263a0e2b76bdd61634a6","xai.json":"cf3f475fe5a13625f858171900ba3456c4d95ebb0bac5060cc25e29bb31d3457","xiaomi-token-plan-ams.json":"7fa339ba5675460b1ff4e5bca9e8ad0aa60b0277d75a989b1c196aa6ca2af34d","xiaomi-token-plan-cn.json":"ef7917c6ea0d3edc655c8a52082ee5f1330658aa6f10199d8f164eb4605ef0a0","xiaomi-token-plan-sgp.json":"addda93f6b70ba879db97e3cfd2e4f2efc7cda47d7daa78c23c5b0e51162de5c","xiaomi.json":"5a42caf49d3e4d7946d60386e9899c2146bf8e3cbaff4c576ee4f49b398cc11c","zai-coding-cn.json":"2b6f85e04b5c568e320b1bde25b1c1614af9342e4c1ba0e1d5bb248aaf50cfe9","zai.json":"e9cc408e1756de8abc70148d63d89d11a63c65b7ef06ad0661cd1328e4209ba3"}}
1
+ {"schemaVersion":6,"generatedAt":"2026-11-06T22:47:38.763Z","structureHash":"1b92d824b741a85982f6b2f4733c3c63f2248a1a53e317fc27bd9376ab23cc7c","files":{"alibaba-token-plan.json":"9f4d42cc765b2a875bcdcaa392bfdc1323c88968309baf9db9f611a26c595c73","amazon-bedrock.json":"a7e20838b095788cb9d5acbde49664b7f2868fad9b10fb4bbbd66635085bca2d","ant-ling.json":"628feab3ef6c7d80ce96f75999804e1d9f05fec3851e5302e30fff3b69db90f6","anthropic.json":"111384e9f5845e0247bd34edf2400ef7720fcbdac140b944cf8878192d8bd6ab","azure-openai-responses.json":"fd64c6a2a99fa87d768ed2f75f5c7813876df1dbe2f0d1776f7d9bd7ce2e61e4","bai.json":"7e6861aaf27d8af34e1771c6092602194fcec0a0046e6adfab9c3ee54d32b99f","baseten.json":"47d10c8050601eb88757def4fc957cdba769dacec4aeb3b0c3f39c41e442330e","cerebras.json":"2eb969b2956844f9a641d3de52c19f1791293c58f607282fb3b0ebfe85ff66f8","chatgpt-subscription.json":"98320f1d51709d26ca047b3d6e3191cfe2f192f1b27897cbb492f47b0e5a5030","cloudflare-ai-gateway.json":"ac281b8cc18eb84ba61f215eff3234d14732cd66239617fb59d6812b13d6473f","cloudflare-workers-ai.json":"1b9ad4360bde817f0ea358431020308f1052840e2278a57a93629f1790072d2e","deepseek.json":"10a296fb3e898f7715c80890c8af0af4f5fd58f22dbcd6612fdc5d762157ccdc","fireworks.json":"56c557eb97573028e871c211cb17e1d60665eb12d67a712615db4bb255bc9253","github-copilot.json":"474fa92eb88ef242208ca93709ebe6d7f21754917d0cad6210bd1edf2b99a87e","google-vertex.json":"8f986b4aca8c685b0f3481bd252bda21e4858bf9015ad37fc5bcc44b7f01d076","google.json":"d25613a7377e81d785d571be514d67b35436511ce6946247dc66f8674e2a5035","groq.json":"087df37206e9eed8b10f1e558e4c496289bef60074b7e8afba4f20fb102b4ec2","huggingface.json":"209cdcf205961ef2ff203486da614232a86a069ebe0e98266189a14a235fac8f","meta.json":"563f5ec07973f52ab8c3eb26ef91a36ad8a79e950b37174935666cdcb624bf35","minimax-cn.json":"70df757e95e9ea2275bf451956b58a746020835f6cbcbd1a644d7fad5b9941d3","minimax.json":"747038b05f4fc24e41405e8bc810f893d7d5121e214e35e6f812f775769a3806","mistral.json":"aafecc66686645b1baa8c90e81c02856115f09999ff507f9bee004d2e1c77a28","moonshotai-cn.json":"a953eace729ef96c91195d477c63c776a1c40aa36085b61236ca1be0fe5b9337","moonshotai.json":"0435f9dc4e532c0764b6d33d8dfa83ce5fccdbcab54224c5ae74ec2d965290f5","nvidia.json":"078fae404fc622ca6461f16a74791fedafe44976a6c3323b6ba779729823d4ff","openai.json":"80845240dd2e4cac670f8040ea7bdda867ca84cc0e4943b6b1b88a1676c0dbc7","opencode-go.json":"ae86439dff010c7ff156c4941aed5db6c1aa817c36dcbfbe893a3600bd4564f0","opencode.json":"eea89feb28a3230195dff414a6aff36970e42e32f5408bc5da31c6f2f2fea7d0","opengateway.json":"c39301d5db2d88aee71705143a6039ebfce2513ef4648979125def43ef409d49","openrouter.json":"e04d53add5c3f1337d80c44a228eab8f4a8b1e8e3abddc20286e904002c7d553","qwen-token-plan-cn.json":"751b18bd443fceb16659ea33013fed90fbf3bbdb4e0ffd7607c93cee2b4cf40d","qwen-token-plan-individual.json":"35ffb0ba1a1ce3f68fc73262dd5e07fbcb5bf5911ad1e6e17bc0621e2894676a","qwen-token-plan.json":"e59b0a45e238578f80d0eea937a093b9cec7cb93751ae20a9e88b16c09eb5cdd","radius.json":"1e4868b8cef7b63d822584e7b8634111891fd6746983a758660ee8f44fad3400","together.json":"8b241bf22b25d8a4bf6d8effe45cebadd193a25a9f0ecc68039d395bf8c6e3bf","typesafe.json":"83409437dbf4c353ac413c0db4e7cf29902fc35e0e0197bdb4eeda2d7f3b07cd","venice.json":"effaccc60f0447ee95e1195623448777c9f26a003c36aea69648c6b7971a2df7","vercel-ai-gateway.json":"b1ec1a1317f329c10973a4589b07c5c98678697c247c0e844a2791bb4e2fdc1b","xai.json":"cf3f475fe5a13625f858171900ba3456c4d95ebb0bac5060cc25e29bb31d3457","xiaomi-token-plan-ams.json":"7fa339ba5675460b1ff4e5bca9e8ad0aa60b0277d75a989b1c196aa6ca2af34d","xiaomi-token-plan-cn.json":"ef7917c6ea0d3edc655c8a52082ee5f1330658aa6f10199d8f164eb4605ef0a0","xiaomi-token-plan-sgp.json":"addda93f6b70ba879db97e3cfd2e4f2efc7cda47d7daa78c23c5b0e51162de5c","xiaomi.json":"5a42caf49d3e4d7946d60386e9899c2146bf8e3cbaff4c576ee4f49b398cc11c","zai-coding-cn.json":"2b6f85e04b5c568e320b1bde25b1c1614af9342e4c1ba0e1d5bb248aaf50cfe9","zai.json":"e9cc408e1756de8abc70148d63d89d11a63c65b7ef06ad0661cd1328e4209ba3"}}
@@ -1 +1 @@
1
- {"openai-completions":{"chat:deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":0.13,"output":0.26,"cacheRead":0.028,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":384000,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.32,"output":3.96,"cacheRead":0.132,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","name":"DeepSeek V4.1 Flash 1017 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","name":"DeepSeek V4.1 Flash Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":3,"output":15,"cacheRead":0.3,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron Ultra","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},"input":["text"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.12,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":202800,"maxTokens":202800,"type":"chat"},"chat:openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT 120B","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},"input":["text"],"cost":{"input":0.1,"output":0.5,"cacheRead":0.1,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":128072,"maxTokens":128072,"type":"chat"},"chat:zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.2-Fast":{"id":"zai-org/GLM-5.2-Fast","name":"GLM 5.2 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.3":{"id":"zai-org/GLM-5.3","name":"GLM 5.3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Fast":{"id":"zai-org/GLM-5.3-Fast","name":"GLM 5.3 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Flash":{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.15,"output":0.5,"cacheRead":0.03,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}
1
+ {"openai-completions":{"chat:deepseek-ai/DeepSeek-V4-Flash-0731":{"id":"deepseek-ai/DeepSeek-V4-Flash-0731","name":"DeepSeek V4 Flash 0731","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":0.13,"output":0.26,"cacheRead":0.028,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":384000,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4-Pro-0813":{"id":"deepseek-ai/DeepSeek-V4-Pro-0813","name":"DeepSeek V4 Pro 0813","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.32,"output":3.96,"cacheRead":0.132,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash":{"id":"deepseek-ai/DeepSeek-V4.1-Flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017","name":"DeepSeek V4.1 Flash 1017","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.3,"output":1.2,"cacheRead":0.007,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-1017-Fast","name":"DeepSeek V4.1 Flash 1017 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":"medium","high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:deepseek-ai/DeepSeek-V4.1-Flash-Fast":{"id":"deepseek-ai/DeepSeek-V4.1-Flash-Fast","name":"DeepSeek V4.1 Flash Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.014,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3":{"id":"moonshotai/Kimi-K3","name":"Kimi K3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":3,"output":15,"cacheRead":0.3,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:moonshotai/Kimi-K3.1-Pro":{"id":"moonshotai/Kimi-K3.1-Pro","name":"Kimi K3.1 Pro","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"input":["text","image"],"cost":{"input":2,"output":10,"cacheRead":0.2,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false},"contextWindow":1000000,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B":{"id":"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B","name":"Nemotron 3 Ultra","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":null},"input":["text"],"cost":{"input":0.6,"output":2.4,"cacheRead":0.12,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":202800,"maxTokens":202800,"type":"chat"},"chat:openai/gpt-oss-120b":{"id":"openai/gpt-oss-120b","name":"OpenAI GPT 120B","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":"minimal","low":"low","medium":"medium","high":"high","xhigh":"xhigh","max":"max"},"input":["text"],"cost":{"input":0.1,"output":0.5,"cacheRead":0.1,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":128072,"maxTokens":128072,"type":"chat"},"chat:zai-org/GLM-5.2":{"id":"zai-org/GLM-5.2","name":"GLM 5.2","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.2-Fast":{"id":"zai-org/GLM-5.2-Fast","name":"GLM 5.2 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":"none","minimal":null,"low":null,"medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"baseten","chatTemplateArgs":{"enable_thinking":{"$var":"thinking.enabled"}}},"contextWindow":1048576,"maxTokens":262144,"type":"chat"},"chat:zai-org/GLM-5.3":{"id":"zai-org/GLM-5.3","name":"GLM 5.3","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":1.4,"output":4.4,"cacheRead":0.14,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Fast":{"id":"zai-org/GLM-5.3-Fast","name":"GLM 5.3 Fast","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":2.1,"output":6.6,"cacheRead":0.21,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:zai-org/GLM-5.3-Flash":{"id":"zai-org/GLM-5.3-Flash","name":"GLM 5.3 Flash","api":"openai-completions","provider":"baseten","baseUrl":"https://inference.baseten.co/v1","reasoning":true,"thinkingLevelMap":{"off":null,"minimal":null,"low":"low","medium":null,"high":"high","xhigh":null,"max":"max"},"input":["text","image"],"cost":{"input":0.15,"output":0.5,"cacheRead":0.03,"cacheWrite":0},"compat":{"supportsStrictMode":true,"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":true,"supportsUsageInStreaming":true,"maxTokensField":"max_tokens","sendSessionAffinityHeaders":true,"supportsLongCacheRetention":false,"thinkingFormat":"openai"},"contextWindow":1048576,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}
@@ -1 +1 @@
1
- {"openai-completions":{"chat:deepseek-ai/deepseek-v4.1-flash":{"id":"deepseek-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"},"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/diffusiongemma-26b-a4b-it":{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":250000,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/llama-3.2-11b-vision-instruct":{"id":"meta/llama-3.2-11b-vision-instruct","name":"Llama 3.2 11b Vision Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":4096,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/llama-3.2-90b-vision-instruct":{"id":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:minimaxai/minimax-m3.1-flash":{"id":"minimaxai/minimax-m3.1-flash","name":"MiniMax-M3.1-Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:mistralai/mistral-7b-instruct-v0.3":{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":65536,"maxTokens":65536,"type":"chat"},"chat:moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/cosmos-reason2-8b":{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/llama-3.1-nemotron-70b-instruct":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"type":"chat"},"chat:nvidia/llama-3.1-nemotron-ultra-253b-v1":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":16384,"type":"chat"},"chat:nvidia/nemotron-3-nano-omni-30b-a3b-reasoning":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":256000,"maxTokens":65536,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":65536,"type":"chat"},"chat:nvidia/nemotron-3.5-lightning-30b-a3b":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"type":"chat"},"chat:nvidia/nemotron-3.5-super-vl-120b-a12b":{"id":"nvidia/nemotron-3.5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1048576,"maxTokens":8192,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":32768,"type":"chat"},"chat:poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":16384,"type":"chat"},"chat:stepfun-ai/step-5-preview":{"id":"stepfun-ai/step-5-preview","name":"Step 5 Preview","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1048576,"maxTokens":1048576,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:z-ai/glm-5.3-flash":{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}
1
+ {"openai-completions":{"chat:deepseek-ai/deepseek-v4.1-flash":{"id":"deepseek-ai/deepseek-v4.1-flash","name":"DeepSeek V4.1 Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"},"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/diffusiongemma-26b-a4b-it":{"id":"google/diffusiongemma-26b-a4b-it","name":"DiffusionGemma 26B A4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":250000,"maxTokens":32768,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-12b-it":{"id":"google/gemma-3-12b-it","name":"Gemma 3 12B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:google/gemma-3-4b-it":{"id":"google/gemma-3-4b-it","name":"Gemma 3 4B IT","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/llama-3.2-90b-vision-instruct":{"id":"meta/llama-3.2-90b-vision-instruct","name":"Llama-3.2-90B-Vision-Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:meta/muse-glimmer-30b":{"id":"meta/muse-glimmer-30b","name":"Muse Glimmer 30B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:minimaxai/minimax-m3.1-flash":{"id":"minimaxai/minimax-m3.1-flash","name":"MiniMax-M3.1-Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:mistralai/mistral-7b-instruct-v0.3":{"id":"mistralai/mistral-7b-instruct-v0.3","name":"Mistral-7B-Instruct-v0.3","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":65536,"maxTokens":65536,"type":"chat"},"chat:moonshotai/kimi-k2.6":{"id":"moonshotai/kimi-k2.6","name":"Kimi K2.6","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/cosmos-reason2-8b":{"id":"nvidia/cosmos-reason2-8b","name":"Cosmos Reason2 8B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":16384,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/llama-3.1-nemotron-70b-instruct":{"id":"nvidia/llama-3.1-nemotron-70b-instruct","name":"Llama 3.1 Nemotron 70B Instruct","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":false,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":8192,"type":"chat"},"chat:nvidia/llama-3.1-nemotron-ultra-253b-v1":{"id":"nvidia/llama-3.1-nemotron-ultra-253b-v1","name":"Llama 3.1 Nemotron Ultra 253B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":128000,"maxTokens":16384,"type":"chat"},"chat:nvidia/nemotron-3-nano-omni-30b-a3b-reasoning":{"id":"nvidia/nemotron-3-nano-omni-30b-a3b-reasoning","name":"Nemotron 3 Nano Omni","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":256000,"maxTokens":65536,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:nvidia/nemotron-3-ultra-550b-a55b":{"id":"nvidia/nemotron-3-ultra-550b-a55b","name":"Nemotron 3 Ultra 550B A55B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":65536,"type":"chat"},"chat:nvidia/nemotron-3.5-lightning-30b-a3b":{"id":"nvidia/nemotron-3.5-lightning-30b-a3b","name":"Nemotron 3.5 Lightning 30B A3B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":262144,"type":"chat"},"chat:nvidia/nemotron-3.5-super-vl-120b-a12b":{"id":"nvidia/nemotron-3.5-super-vl-120b-a12b","name":"Nemotron 3.5 Super VL 120B A12B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1048576,"maxTokens":8192,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:openai/gpt-oss-20b":{"id":"openai/gpt-oss-20b","name":"GPT OSS 20B","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":131072,"maxTokens":32768,"type":"chat"},"chat:poolside/laguna-xs-2.1":{"id":"poolside/laguna-xs-2.1","name":"Laguna XS 2.1","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":262144,"maxTokens":16384,"type":"chat"},"chat:stepfun-ai/step-5-preview":{"id":"stepfun-ai/step-5-preview","name":"Step 5 Preview","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1048576,"maxTokens":1048576,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"},"chat:z-ai/glm-5.3-flash":{"id":"z-ai/glm-5.3-flash","name":"GLM-5.3-Flash","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text","image"],"cost":{"input":0,"output":0,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsLongCacheRetention":false,"supportsStrictMode":false},"contextWindow":1000000,"maxTokens":131072,"inputLimits":{"images":{"resize":{"maxWidth":2000,"maxHeight":2000,"maxBytes":4718592,"jpegQuality":80}}},"type":"chat"}}}