@bastani/pi-ai 0.9.19-alpha.8 → 0.9.19
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.
- package/CHANGELOG.md +19 -0
- package/dist/providers/data/.manifest.json +1 -1
- package/dist/providers/data/nvidia.json +1 -1
- package/dist/providers/data/openrouter.json +1 -1
- package/dist/providers/data/together.json +1 -1
- package/dist/providers/data/vercel-ai-gateway.json +1 -1
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -4,6 +4,25 @@ This package is a Bastani fork of `@earendil-works/pi-ai`. Upstream history at t
|
|
|
4
4
|
|
|
5
5
|
## [Unreleased]
|
|
6
6
|
|
|
7
|
+
## [0.9.19] - 2026-09-13
|
|
8
|
+
|
|
9
|
+
Cumulative release of the `0.9.19-alpha.2` through `0.9.19-alpha.4` prereleases. Per-change details remain in the unchanged prerelease sections below.
|
|
10
|
+
|
|
11
|
+
### Added
|
|
12
|
+
|
|
13
|
+
- Enabled native deferred tool loading for Fireworks Messages models through `ToolSearch` or `tool_search` ([#9323](https://github.com/earendil-works/pi/issues/9323)).
|
|
14
|
+
|
|
15
|
+
### Fixed
|
|
16
|
+
|
|
17
|
+
- Fixed Anthropic object-union tool schemas, including own property names such as `__proto__` and explicitly nonobject branches, without changing authored schemas or local validation ([#2190](https://github.com/bastani-inc/atomic/pull/2190) by [@elefthei](https://github.com/elefthei), [#2189](https://github.com/bastani-inc/atomic/issues/2189)).
|
|
18
|
+
- Capped shared assistant and summary retry backoff with `RetryPolicy.maxAgentDelayMs`, defaulting to 60 seconds ([#8826](https://github.com/earendil-works/pi/issues/8826)).
|
|
19
|
+
- Updated Anthropic, Bedrock, Google and HTTP proxy SDKs; Google's consecutive tool-call limit now returns an error stop reason. GitHub Copilot GPT models use the Responses API ([#9209](https://github.com/earendil-works/pi/issues/9209)).
|
|
20
|
+
- Fixed quadratic CPU usage when draining buffered `EventStream` events ([#9055](https://github.com/earendil-works/pi/issues/9055)).
|
|
21
|
+
- Fixed OpenAI Codex Off reasoning requests and removed unavailable GPT-5.4 and GPT-5.4 mini catalog entries ([#9191](https://github.com/earendil-works/pi/issues/9191), [#9394](https://github.com/earendil-works/pi/issues/9394)).
|
|
22
|
+
- Fixed Fireworks unsigned thinking replay and catalog-based reasoning selection, including DeepSeek V4 and Qwen3.8 fallbacks. Refreshed DeepSeek V4.1 Flash identity and pricing ([#9323](https://github.com/earendil-works/pi/issues/9323), [#9423](https://github.com/earendil-works/pi/issues/9423)).
|
|
23
|
+
- Fixed OpenRouter prompt-cached requests sending `x-session-id` for Chat Completions and Anthropic Messages ([#9102](https://github.com/earendil-works/pi/issues/9102)).
|
|
24
|
+
- Fixed Mistral Medium aliases and Mistral-hosted GLM-5.2 using `reasoning_effort` instead of unsupported or ignored `prompt_mode` ([#8700](https://github.com/earendil-works/pi/issues/8700), [#9375](https://github.com/earendil-works/pi/issues/9375)).
|
|
25
|
+
|
|
7
26
|
## [0.9.19-alpha.4] - 2026-09-10
|
|
8
27
|
|
|
9
28
|
### Added
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"schemaVersion":3,"generatedAt":"2026-09-
|
|
1
|
+
{"schemaVersion":3,"generatedAt":"2026-09-14T04:42:12.142Z","structureHash":"ebfac51d9122caefc796e02f92b23e524b4f4b5755dca67426073295b107df2f","files":{"amazon-bedrock.json":"3b23459bc003201086ea17a3ea55f092ea4def8758b1bef285cf4d93f38c79b7","ant-ling.json":"4979fe79d99ed97382d7ce40170c6132e932e77906de1eb54464c042e7d63633","anthropic.json":"555550f3c8957edeb3018e08688b2db1b58191d8a17236c5fdcf53acdce7037a","azure-openai-responses.json":"37d12c5cbfc29bfd9a802a0516f5d3209320bd4aa8ef9cd7c219af208244afa3","baseten.json":"d155c434294b5167244cffb6dea6793f9669e91e8ab65b564f9510d81b330e37","cerebras.json":"9eaa554e1b02f3665f8f63e6432d253bf81351af7c72001054dd8108aa528a52","cloudflare-ai-gateway.json":"82dc8959837dfbd3bbc1b6d5180d45edf800ee47477f12fb19a7ec32ef2b105c","cloudflare-workers-ai.json":"07ef63208ff7517fd1a80962f18143e21de399640423329490b157f459ccf995","deepseek.json":"b5f9693ec641e9a957dc5f7a22042b3bb928bac3d7268406619b6f18e21c4b83","fireworks.json":"ca63c457081a97673e60a9f47221a1710c4e2295df3021a274ec27786b699dd7","github-copilot.json":"dae38668d5d351d28f96181bb01b462b93be1e4b450b859ab7e3da6880f203e6","google-vertex.json":"2cde4c73c7c9bd0ec232f6295a16c1d1780391320e35301b77d710dfdd11cf93","google.json":"54e1dfdd53ea1f9f86a83d3f81b21845eb7e1540c72ecee5255c0e97085d7fc3","groq.json":"e4728fd72e358cd8f25e9a518e9b49a521ef44523d3debe38a7db9e0663c4077","huggingface.json":"a488b6f175b382277ccf7d487f877ef0c698994576bb55d2410838bf9c8c7c41","kimi-coding.json":"5e28e32e5b16df506a3a1c620ed7870fa7e5e57d8ede4a2aa44dbb24ecf1ba2f","minimax-cn.json":"65d37e55a6d9585855f94b3fb7739308d107fe248ebd9e1001d1c5d4606ad2c4","minimax.json":"c7dc5765995ae77242916430929c7cc9a782589f7e483e13f7e01663190d028e","mistral.json":"e3a109306644bf2f2fa38fece50b2d3ce1dbe3b87b1f1b9e2d70cce7eb5c0ea1","moonshotai-cn.json":"63f77de8782dce6a8d4649b6075ee04c9732863ae85561e0867871220c558bde","moonshotai.json":"2a8dfb97eb905e991c22081dc09bd4a61c05b7fa9ac0d5c72d6930f601f490f1","nvidia.json":"d9fbf18e811fcf04521c3dad7bd8a31c6716938611de392548319acc560c1e0c","openai-codex.json":"b1456bc167ff46942e11c91abbb4b2807187678ae91a677ddd36f22129baf4b8","openai.json":"775d3b7d95d14b741d0b287b1153d40f051a9ea03035a82b487889acc7fa69e2","opencode-go.json":"274c4fb1a4e99c286860174700b0b38997df62839efd2b76a8884db1d8dc331a","opencode.json":"7923dc100adae40eb48ba864c43c21dab8ff69448cdeda0200399dd92fda4f2c","openrouter.json":"ec24ab94d31720f75eeb39b77e96dcf5cee82cee2cba033018d72f492145bbd8","qwen-token-plan-cn.json":"d24c5318361ae5395866faaaffde5e52341be58e607def0cc219cae49326492a","qwen-token-plan-individual.json":"eb040e78595853e980011308b1bf9caacae6dc8a91abbac5ffebd402515dd2a6","qwen-token-plan.json":"0545c9881decb710a9535f67960174089b04f607c1200335cdad9de4670ec92a","together.json":"927c707d06f2236cdab13f14c870fb58bce0614ba7287bbcd57cc9fd66d191ed","vercel-ai-gateway.json":"937ac84d8ea485c812b2c7043afe32a5e216b71de993b932078cb788483a199a","xai.json":"037bde3de5ea72814c3f0b79da8b244c89feb708cc0cbf8596cdfac7682477b6","xiaomi-token-plan-ams.json":"a36446cb9e3cb4f7054617676fd711092245a74f703ba89573f21d2673b85fa8","xiaomi-token-plan-cn.json":"c295dadf4097b5d86af15e924fb2a1a6342bae9e0a9a5839c9fca216308c51e5","xiaomi-token-plan-sgp.json":"93d359575c2348c97d79a2b14e1e9437199bd4aee948d58611b3fbab75cd9fb3","xiaomi.json":"f06f1011d606d22311b1f4c50eb36d38b8cd99abf5760faee657d5559e87452b","zai-coding-cn.json":"d3c969020a7ab978497837a3301c7bca364d704082832221cfe61e6596333e56","zai.json":"f42790c77fb4681a656897a9d860b939916c0ddf979a5f16856bce9573cdf64e"}}
|
|
@@ -1 +1 @@
|
|
|
1
|
-
{"openai-completions":{"deepseek-ai/deepseek-v4-flash-0731":{"id":"deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","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","supportsStrictMode":false,"supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"}},"deepseek-ai/deepseek-v4-pro-0813":{"id":"deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","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","supportsStrictMode":false,"supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"}},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":4096},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":8192},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":131072},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":65536,"maxTokens":65536},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":262144},"moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":1048576,"maxTokens":131072},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":8192},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":256000,"maxTokens":65536},"nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0.2,"output":0.8,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":262144},"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":0.5,"output":2.5,"cacheRead":0.15,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":1000000,"maxTokens":65536},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":262144},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":32768},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":16384}}}
|
|
1
|
+
{"openai-completions":{"deepseek-ai/deepseek-v4-flash-0731":{"id":"deepseek-ai/deepseek-v4-flash-0731","name":"DeepSeek V4 Flash 0731","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","supportsStrictMode":false,"supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"}},"deepseek-ai/deepseek-v4-pro-0813":{"id":"deepseek-ai/deepseek-v4-pro-0813","name":"DeepSeek V4 Pro 0813","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","supportsStrictMode":false,"supportsLongCacheRetention":false,"requiresReasoningContentOnAssistantMessages":true,"thinkingFormat":"deepseek"},"contextWindow":1000000,"maxTokens":384000,"thinkingLevelMap":{"minimal":null,"low":null,"medium":null,"high":"high","max":"max"}},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":4096},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":8192},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":131072},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":65536,"maxTokens":65536},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":262144},"moonshotai/kimi-k3":{"id":"moonshotai/kimi-k3","name":"Kimi K3","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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":1048576,"maxTokens":131072},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":8192},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":128000,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":256000,"maxTokens":65536},"nvidia/nemotron-3-super-120b-a12b":{"id":"nvidia/nemotron-3-super-120b-a12b","name":"Nemotron 3 Super","api":"openai-completions","provider":"nvidia","baseUrl":"https://integrate.api.nvidia.com/v1","headers":{"NVCF-POLL-SECONDS":"3600"},"reasoning":true,"input":["text"],"cost":{"input":0.2,"output":0.8,"cacheRead":0,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":262144},"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":0.5,"output":2.5,"cacheRead":0.15,"cacheWrite":0},"compat":{"supportsStore":false,"supportsDeveloperRole":false,"supportsReasoningEffort":false,"maxTokensField":"max_tokens","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":1000000,"maxTokens":65536},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":262144},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":131072,"maxTokens":32768},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":262144,"maxTokens":16384},"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","supportsStrictMode":false,"supportsLongCacheRetention":false},"contextWindow":1000000,"maxTokens":131072}}}
|