From da1032a1cb5abdd941e4db43b1535605c5f42fb0 Mon Sep 17 00:00:00 2001 From: Aiden Cline Date: Wed, 10 Jun 2026 19:46:52 -0500 Subject: [PATCH] [venice] Fix synced model metadata --- models/venice/aion-labs-aion-2-0.toml | 17 -------- .../venice/arcee-trinity-large-thinking.toml | 21 --------- models/venice/deepseek-v3.2.toml | 22 ---------- models/venice/e2ee-gemma-3-27b-p.toml | 20 --------- .../e2ee-gemma-4-26b-a4b-uncensored-p.toml | 17 -------- models/venice/e2ee-gemma-4-31b.toml | 20 --------- models/venice/e2ee-gpt-oss-120b-p.toml | 20 --------- models/venice/e2ee-gpt-oss-20b-p.toml | 20 --------- models/venice/e2ee-qwen-2-5-7b-p.toml | 20 --------- models/venice/e2ee-qwen3-30b-a3b-p.toml | 20 --------- .../e2ee-qwen3-6-35b-a3b-uncensored-p.toml | 17 -------- models/venice/e2ee-qwen3-6-35b-a3b.toml | 20 --------- models/venice/e2ee-qwen3-vl-30b-a3b-p.toml | 20 --------- .../venice/e2ee-venice-uncensored-24b-p.toml | 20 --------- models/venice/gemma-4-uncensored.toml | 21 --------- models/venice/google-gemma-3-27b-it.toml | 22 ---------- models/venice/grok-4-20-multi-agent.toml | 18 -------- models/venice/grok-4-20.toml | 18 -------- models/venice/hermes-3-llama-3.1-405b.toml | 21 --------- models/venice/llama-3.2-3b.toml | 21 --------- models/venice/llama-3.3-70b.toml | 21 --------- models/venice/mercury-2.toml | 18 -------- .../mistral-small-3-2-24b-instruct.toml | 21 --------- .../olafangensan-glm-4.7-flash-heretic.toml | 21 --------- models/venice/openai-gpt-oss-120b.toml | 21 --------- .../venice/qwen3-235b-a22b-instruct-2507.toml | 22 ---------- .../venice/qwen3-235b-a22b-thinking-2507.toml | 22 ---------- models/venice/qwen3-5-9b.toml | 21 --------- .../qwen3-coder-480b-a35b-instruct-turbo.toml | 21 --------- models/venice/qwen3-next-80b.toml | 22 ---------- models/venice/qwen3-vl-235b-a22b.toml | 21 --------- models/venice/venice-uncensored-1-2.toml | 21 --------- .../venice/venice-uncensored-role-play.toml | 21 --------- packages/core/src/sync/index.ts | 5 ++- packages/core/src/sync/providers/venice.ts | 43 ++++--------------- packages/core/test/venice-sync.test.ts | 30 +++++++++++-- providers/venice/README.md | 6 +-- .../venice/models/aion-labs-aion-2-0.toml | 16 ++++++- .../models/arcee-trinity-large-thinking.toml | 18 +++++++- providers/venice/models/claude-fable-5.toml | 3 +- providers/venice/models/claude-opus-4-5.toml | 2 +- .../venice/models/claude-opus-4-6-fast.toml | 2 +- providers/venice/models/claude-opus-4-6.toml | 2 +- .../venice/models/claude-opus-4-7-fast.toml | 3 +- providers/venice/models/claude-opus-4-7.toml | 3 +- .../venice/models/claude-opus-4-8-fast.toml | 3 +- providers/venice/models/claude-opus-4-8.toml | 3 +- .../venice/models/claude-sonnet-4-5.toml | 2 +- .../venice/models/claude-sonnet-4-6.toml | 2 +- providers/venice/models/deepseek-v3.2.toml | 18 +++++++- .../venice/models/deepseek-v4-flash.toml | 2 +- providers/venice/models/deepseek-v4-pro.toml | 2 +- .../venice/models/e2ee-gemma-3-27b-p.toml | 6 --- .../e2ee-gemma-4-26b-a4b-uncensored-p.toml | 6 --- providers/venice/models/e2ee-gemma-4-31b.toml | 7 --- .../venice/models/e2ee-glm-4-7-flash-p.toml | 18 -------- providers/venice/models/e2ee-glm-4-7-p.toml | 17 -------- providers/venice/models/e2ee-glm-5-1.toml | 13 ------ .../venice/models/e2ee-gpt-oss-120b-p.toml | 9 ---- .../venice/models/e2ee-gpt-oss-20b-p.toml | 9 ---- .../venice/models/e2ee-qwen-2-5-7b-p.toml | 6 --- .../venice/models/e2ee-qwen3-30b-a3b-p.toml | 6 --- .../e2ee-qwen3-6-35b-a3b-uncensored-p.toml | 6 --- .../venice/models/e2ee-qwen3-6-35b-a3b.toml | 7 --- .../models/e2ee-qwen3-vl-30b-a3b-p.toml | 6 --- .../models/e2ee-venice-uncensored-24b-p.toml | 6 --- .../venice/models/gemini-3-1-pro-preview.toml | 2 +- providers/venice/models/gemini-3-5-flash.toml | 2 +- .../venice/models/gemini-3-flash-preview.toml | 2 +- .../venice/models/gemma-4-uncensored.toml | 18 +++++++- .../venice/models/google-gemma-3-27b-it.toml | 18 +++++++- .../models/google-gemma-4-26b-a4b-it.toml | 2 +- .../venice/models/google-gemma-4-31b-it.toml | 2 +- .../venice/models/grok-4-20-multi-agent.toml | 18 +++++++- providers/venice/models/grok-4-20.toml | 18 +++++++- providers/venice/models/grok-4-3.toml | 2 +- providers/venice/models/grok-build-0-1.toml | 2 +- .../models/hermes-3-llama-3.1-405b.toml | 17 +++++++- providers/venice/models/kimi-k2-5.toml | 3 +- providers/venice/models/kimi-k2-6.toml | 2 +- providers/venice/models/llama-3.2-3b.toml | 17 +++++++- providers/venice/models/llama-3.3-70b.toml | 17 +++++++- providers/venice/models/mercury-2.toml | 18 +++++++- providers/venice/models/minimax-m25.toml | 2 +- providers/venice/models/minimax-m27.toml | 2 +- providers/venice/models/minimax-m3.toml | 2 +- .../venice/models/mistral-small-2603.toml | 2 +- .../mistral-small-3-2-24b-instruct.toml | 18 +++++++- .../nvidia-nemotron-3-nano-30b-a3b.toml | 2 +- .../nvidia-nemotron-3-ultra-550b-a55b.toml | 2 +- .../nvidia-nemotron-cascade-2-30b-a3b.toml | 2 +- .../olafangensan-glm-4.7-flash-heretic.toml | 18 +++++++- .../models/openai-gpt-4o-2024-11-20.toml | 2 +- .../models/openai-gpt-4o-mini-2024-07-18.toml | 2 +- .../venice/models/openai-gpt-52-codex.toml | 3 +- providers/venice/models/openai-gpt-52.toml | 3 +- .../venice/models/openai-gpt-53-codex.toml | 3 +- .../venice/models/openai-gpt-54-mini.toml | 3 +- .../venice/models/openai-gpt-54-pro.toml | 3 +- providers/venice/models/openai-gpt-54.toml | 3 +- .../venice/models/openai-gpt-55-pro.toml | 3 +- providers/venice/models/openai-gpt-55.toml | 3 +- .../venice/models/openai-gpt-oss-120b.toml | 17 +++++++- providers/venice/models/qwen-3-6-plus.toml | 2 +- providers/venice/models/qwen-3-7-max.toml | 2 +- providers/venice/models/qwen-3-7-plus.toml | 2 +- .../models/qwen3-235b-a22b-instruct-2507.toml | 18 +++++++- .../models/qwen3-235b-a22b-thinking-2507.toml | 18 +++++++- providers/venice/models/qwen3-5-35b-a3b.toml | 2 +- .../venice/models/qwen3-5-397b-a17b.toml | 2 +- providers/venice/models/qwen3-5-9b.toml | 18 +++++++- providers/venice/models/qwen3-6-27b.toml | 2 +- .../qwen3-coder-480b-a35b-instruct-turbo.toml | 18 +++++++- providers/venice/models/qwen3-next-80b.toml | 18 +++++++- .../venice/models/qwen3-vl-235b-a22b.toml | 17 +++++++- .../venice/models/tencent-hy3-preview.toml | 2 +- .../venice/models/venice-uncensored-1-2.toml | 18 +++++++- .../models/venice-uncensored-role-play.toml | 18 +++++++- providers/venice/models/z-ai-glm-5-turbo.toml | 2 +- .../venice/models/z-ai-glm-5v-turbo.toml | 2 +- providers/venice/models/zai-org-glm-4.6.toml | 2 +- .../venice/models/zai-org-glm-4.7-flash.toml | 2 +- providers/venice/models/zai-org-glm-4.7.toml | 2 +- providers/venice/models/zai-org-glm-5-1.toml | 2 +- providers/venice/models/zai-org-glm-5.toml | 2 +- 125 files changed, 461 insertions(+), 920 deletions(-) delete mode 100644 models/venice/aion-labs-aion-2-0.toml delete mode 100644 models/venice/arcee-trinity-large-thinking.toml delete mode 100644 models/venice/deepseek-v3.2.toml delete mode 100644 models/venice/e2ee-gemma-3-27b-p.toml delete mode 100644 models/venice/e2ee-gemma-4-26b-a4b-uncensored-p.toml delete mode 100644 models/venice/e2ee-gemma-4-31b.toml delete mode 100644 models/venice/e2ee-gpt-oss-120b-p.toml delete mode 100644 models/venice/e2ee-gpt-oss-20b-p.toml delete mode 100644 models/venice/e2ee-qwen-2-5-7b-p.toml delete mode 100644 models/venice/e2ee-qwen3-30b-a3b-p.toml delete mode 100644 models/venice/e2ee-qwen3-6-35b-a3b-uncensored-p.toml delete mode 100644 models/venice/e2ee-qwen3-6-35b-a3b.toml delete mode 100644 models/venice/e2ee-qwen3-vl-30b-a3b-p.toml delete mode 100644 models/venice/e2ee-venice-uncensored-24b-p.toml delete mode 100644 models/venice/gemma-4-uncensored.toml delete mode 100644 models/venice/google-gemma-3-27b-it.toml delete mode 100644 models/venice/grok-4-20-multi-agent.toml delete mode 100644 models/venice/grok-4-20.toml delete mode 100644 models/venice/hermes-3-llama-3.1-405b.toml delete mode 100644 models/venice/llama-3.2-3b.toml delete mode 100644 models/venice/llama-3.3-70b.toml delete mode 100644 models/venice/mercury-2.toml delete mode 100644 models/venice/mistral-small-3-2-24b-instruct.toml delete mode 100644 models/venice/olafangensan-glm-4.7-flash-heretic.toml delete mode 100644 models/venice/openai-gpt-oss-120b.toml delete mode 100644 models/venice/qwen3-235b-a22b-instruct-2507.toml delete mode 100644 models/venice/qwen3-235b-a22b-thinking-2507.toml delete mode 100644 models/venice/qwen3-5-9b.toml delete mode 100644 models/venice/qwen3-coder-480b-a35b-instruct-turbo.toml delete mode 100644 models/venice/qwen3-next-80b.toml delete mode 100644 models/venice/qwen3-vl-235b-a22b.toml delete mode 100644 models/venice/venice-uncensored-1-2.toml delete mode 100644 models/venice/venice-uncensored-role-play.toml delete mode 100644 providers/venice/models/e2ee-gemma-3-27b-p.toml delete mode 100644 providers/venice/models/e2ee-gemma-4-26b-a4b-uncensored-p.toml delete mode 100644 providers/venice/models/e2ee-gemma-4-31b.toml delete mode 100644 providers/venice/models/e2ee-glm-4-7-flash-p.toml delete mode 100644 providers/venice/models/e2ee-glm-4-7-p.toml delete mode 100644 providers/venice/models/e2ee-glm-5-1.toml delete mode 100644 providers/venice/models/e2ee-gpt-oss-120b-p.toml delete mode 100644 providers/venice/models/e2ee-gpt-oss-20b-p.toml delete mode 100644 providers/venice/models/e2ee-qwen-2-5-7b-p.toml delete mode 100644 providers/venice/models/e2ee-qwen3-30b-a3b-p.toml delete mode 100644 providers/venice/models/e2ee-qwen3-6-35b-a3b-uncensored-p.toml delete mode 100644 providers/venice/models/e2ee-qwen3-6-35b-a3b.toml delete mode 100644 providers/venice/models/e2ee-qwen3-vl-30b-a3b-p.toml delete mode 100644 providers/venice/models/e2ee-venice-uncensored-24b-p.toml diff --git a/models/venice/aion-labs-aion-2-0.toml b/models/venice/aion-labs-aion-2-0.toml deleted file mode 100644 index e68111efc..000000000 --- a/models/venice/aion-labs-aion-2-0.toml +++ /dev/null @@ -1,17 +0,0 @@ -name = "Aion 2.0" -family = "o" -release_date = "2026-03-24" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = false -temperature = true -open_weights = false - -[limit] -context = 128000 -output = 32768 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/models/venice/arcee-trinity-large-thinking.toml b/models/venice/arcee-trinity-large-thinking.toml deleted file mode 100644 index fc3c4b6eb..000000000 --- a/models/venice/arcee-trinity-large-thinking.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Trinity Large Thinking" -family = "trinity" -release_date = "2026-04-02" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = true - -[limit] -context = 256000 -output = 65536 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/arcee-ai/Trinity-Large-Thinking-FP8-Block" diff --git a/models/venice/deepseek-v3.2.toml b/models/venice/deepseek-v3.2.toml deleted file mode 100644 index 27a86d344..000000000 --- a/models/venice/deepseek-v3.2.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "DeepSeek V3.2" -family = "deepseek" -release_date = "2025-12-04" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -knowledge = "2025-10" -open_weights = true - -[limit] -context = 160000 -output = 32768 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/deepseek-ai/DeepSeek-V3.2" diff --git a/models/venice/e2ee-gemma-3-27b-p.toml b/models/venice/e2ee-gemma-3-27b-p.toml deleted file mode 100644 index 1c085a939..000000000 --- a/models/venice/e2ee-gemma-3-27b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Gemma 3 27B" -family = "gemma" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = false -reasoning = false -tool_call = false -temperature = true -open_weights = true - -[limit] -context = 40000 -output = 4096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/google/gemma-3-27b-it" diff --git a/models/venice/e2ee-gemma-4-26b-a4b-uncensored-p.toml b/models/venice/e2ee-gemma-4-26b-a4b-uncensored-p.toml deleted file mode 100644 index 887bef60b..000000000 --- a/models/venice/e2ee-gemma-4-26b-a4b-uncensored-p.toml +++ /dev/null @@ -1,17 +0,0 @@ -name = "Gemma 4 26B A4B Uncensored" -family = "gemma" -release_date = "2026-05-24" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = false -open_weights = false - -[limit] -context = 64_000 -output = 4_096 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/models/venice/e2ee-gemma-4-31b.toml b/models/venice/e2ee-gemma-4-31b.toml deleted file mode 100644 index a4f6646c4..000000000 --- a/models/venice/e2ee-gemma-4-31b.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Gemma 4 31B Instruct" -family = "gemma" -release_date = "2026-05-20" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = false -temperature = true -open_weights = true - -[limit] -context = 32000 -output = 4096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/google/gemma-4-31B-it" diff --git a/models/venice/e2ee-gpt-oss-120b-p.toml b/models/venice/e2ee-gpt-oss-120b-p.toml deleted file mode 100644 index c997238ce..000000000 --- a/models/venice/e2ee-gpt-oss-120b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "GPT OSS 120B" -family = "gpt-oss" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = false -temperature = true -open_weights = true - -[limit] -context = 128000 -output = 32768 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/openai/gpt-oss-120b" diff --git a/models/venice/e2ee-gpt-oss-20b-p.toml b/models/venice/e2ee-gpt-oss-20b-p.toml deleted file mode 100644 index f02dd9591..000000000 --- a/models/venice/e2ee-gpt-oss-20b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "GPT OSS 20B" -family = "gpt-oss" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = false -temperature = true -open_weights = true - -[limit] -context = 128000 -output = 32768 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/openai/gpt-oss-20b" diff --git a/models/venice/e2ee-qwen-2-5-7b-p.toml b/models/venice/e2ee-qwen-2-5-7b-p.toml deleted file mode 100644 index 0c7ed2c5e..000000000 --- a/models/venice/e2ee-qwen-2-5-7b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Qwen 2.5 7B" -family = "qwen" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = false -reasoning = false -tool_call = false -temperature = true -open_weights = true - -[limit] -context = 32000 -output = 4096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen2.5-7B-Instruct" diff --git a/models/venice/e2ee-qwen3-30b-a3b-p.toml b/models/venice/e2ee-qwen3-30b-a3b-p.toml deleted file mode 100644 index f645a657f..000000000 --- a/models/venice/e2ee-qwen3-30b-a3b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Qwen3 30B A3B" -family = "qwen" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = false -reasoning = false -tool_call = true -temperature = true -open_weights = true - -[limit] -context = 256000 -output = 32768 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-30B-A3B-Instruct-2507" diff --git a/models/venice/e2ee-qwen3-6-35b-a3b-uncensored-p.toml b/models/venice/e2ee-qwen3-6-35b-a3b-uncensored-p.toml deleted file mode 100644 index 30894d2cc..000000000 --- a/models/venice/e2ee-qwen3-6-35b-a3b-uncensored-p.toml +++ /dev/null @@ -1,17 +0,0 @@ -name = "Qwen3.6 35B A3B Uncensored" -family = "qwen3.6" -release_date = "2026-05-24" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = false -open_weights = false - -[limit] -context = 128_000 -output = 4_096 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/models/venice/e2ee-qwen3-6-35b-a3b.toml b/models/venice/e2ee-qwen3-6-35b-a3b.toml deleted file mode 100644 index 48b177a19..000000000 --- a/models/venice/e2ee-qwen3-6-35b-a3b.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Qwen 3.6 35B A3B FP8" -family = "qwen" -release_date = "2026-05-20" -last_updated = "2026-06-10" -attachment = false -reasoning = true -temperature = true -tool_call = true -open_weights = true - -[limit] -context = 32_000 -output = 4_096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3.6-35B-A3B-FP8" diff --git a/models/venice/e2ee-qwen3-vl-30b-a3b-p.toml b/models/venice/e2ee-qwen3-vl-30b-a3b-p.toml deleted file mode 100644 index 099a96e21..000000000 --- a/models/venice/e2ee-qwen3-vl-30b-a3b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Qwen3 VL 30B A3B" -family = "qwen" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = true -reasoning = false -tool_call = true -temperature = true -open_weights = true - -[limit] -context = 128000 -output = 4096 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-VL-30B-A3B-Instruct" diff --git a/models/venice/e2ee-venice-uncensored-24b-p.toml b/models/venice/e2ee-venice-uncensored-24b-p.toml deleted file mode 100644 index e3a6b9724..000000000 --- a/models/venice/e2ee-venice-uncensored-24b-p.toml +++ /dev/null @@ -1,20 +0,0 @@ -name = "Venice Uncensored 1.1" -family = "venice" -release_date = "2026-03-18" -last_updated = "2026-06-10" -attachment = false -reasoning = false -tool_call = false -temperature = true -open_weights = true - -[limit] -context = 32000 -output = 4096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition" diff --git a/models/venice/gemma-4-uncensored.toml b/models/venice/gemma-4-uncensored.toml deleted file mode 100644 index 76d4690ff..000000000 --- a/models/venice/gemma-4-uncensored.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Gemma 4 Uncensored" -family = "gemma" -release_date = "2026-04-13" -last_updated = "2026-06-10" -attachment = true -reasoning = false -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 256_000 -output = 8_192 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Jiunsong/supergemma4-26b-uncensored-gguf-v2" diff --git a/models/venice/google-gemma-3-27b-it.toml b/models/venice/google-gemma-3-27b-it.toml deleted file mode 100644 index 97009e227..000000000 --- a/models/venice/google-gemma-3-27b-it.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Google Gemma 3 27B Instruct" -family = "gemma" -release_date = "2025-11-04" -last_updated = "2026-06-10" -attachment = true -reasoning = false -temperature = true -tool_call = true -structured_output = true -knowledge = "2025-07" -open_weights = true - -[limit] -context = 198_000 -output = 16_384 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/google/gemma-3-27b-it" diff --git a/models/venice/grok-4-20-multi-agent.toml b/models/venice/grok-4-20-multi-agent.toml deleted file mode 100644 index 33681812c..000000000 --- a/models/venice/grok-4-20-multi-agent.toml +++ /dev/null @@ -1,18 +0,0 @@ -name = "Grok 4.20 Multi-Agent" -family = "grok" -release_date = "2026-03-12" -last_updated = "2026-06-10" -attachment = true -reasoning = true -temperature = true -tool_call = false -structured_output = true -open_weights = false - -[limit] -context = 2_000_000 -output = 128_000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/models/venice/grok-4-20.toml b/models/venice/grok-4-20.toml deleted file mode 100644 index a9640ad97..000000000 --- a/models/venice/grok-4-20.toml +++ /dev/null @@ -1,18 +0,0 @@ -name = "Grok 4.20" -family = "grok" -release_date = "2026-03-12" -last_updated = "2026-06-10" -attachment = true -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = false - -[limit] -context = 2000000 -output = 128000 - -[modalities] -input = ["text", "image"] -output = ["text"] diff --git a/models/venice/hermes-3-llama-3.1-405b.toml b/models/venice/hermes-3-llama-3.1-405b.toml deleted file mode 100644 index dad87001a..000000000 --- a/models/venice/hermes-3-llama-3.1-405b.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Hermes 3 Llama 3.1 405b" -family = "hermes" -release_date = "2025-09-25" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = false -knowledge = "2024-04" -open_weights = true - -[limit] -context = 128_000 -output = 16_384 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/NousResearch/Hermes-3-Llama-3.1-405B" diff --git a/models/venice/llama-3.2-3b.toml b/models/venice/llama-3.2-3b.toml deleted file mode 100644 index 5a1f77e10..000000000 --- a/models/venice/llama-3.2-3b.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Llama 3.2 3B" -family = "llama" -release_date = "2024-10-03" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = true -knowledge = "2023-12" -open_weights = true - -[limit] -context = 128_000 -output = 4_096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/meta-llama/Llama-3.2-3B" diff --git a/models/venice/llama-3.3-70b.toml b/models/venice/llama-3.3-70b.toml deleted file mode 100644 index bf68f1dfe..000000000 --- a/models/venice/llama-3.3-70b.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Llama 3.3 70B" -family = "llama" -release_date = "2025-04-06" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = true -knowledge = "2023-12" -open_weights = true - -[limit] -context = 128_000 -output = 4_096 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/meta-llama/Llama-3.3-70B-Instruct" diff --git a/models/venice/mercury-2.toml b/models/venice/mercury-2.toml deleted file mode 100644 index 1bb1daf2c..000000000 --- a/models/venice/mercury-2.toml +++ /dev/null @@ -1,18 +0,0 @@ -name = "Mercury 2" -family = "mercury" -release_date = "2026-02-20" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = true -structured_output = true -temperature = true -open_weights = false - -[limit] -context = 128000 -output = 50000 - -[modalities] -input = ["text"] -output = ["text"] diff --git a/models/venice/mistral-small-3-2-24b-instruct.toml b/models/venice/mistral-small-3-2-24b-instruct.toml deleted file mode 100644 index 804f80363..000000000 --- a/models/venice/mistral-small-3-2-24b-instruct.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Mistral Small 3.2 24B Instruct" -family = "mistral-small" -release_date = "2026-01-15" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 256_000 -output = 16_384 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/mistralai/Mistral-Small-3.2-24B-Instruct-2506" diff --git a/models/venice/olafangensan-glm-4.7-flash-heretic.toml b/models/venice/olafangensan-glm-4.7-flash-heretic.toml deleted file mode 100644 index 175470367..000000000 --- a/models/venice/olafangensan-glm-4.7-flash-heretic.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "GLM 4.7 Flash Heretic" -family = "glm" -release_date = "2026-02-04" -last_updated = "2026-06-10" -attachment = false -reasoning = true -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 200_000 -output = 24_000 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Olafangensan/GLM-4.7-Flash-heretic" diff --git a/models/venice/openai-gpt-oss-120b.toml b/models/venice/openai-gpt-oss-120b.toml deleted file mode 100644 index ada4b6da0..000000000 --- a/models/venice/openai-gpt-oss-120b.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "OpenAI GPT OSS 120B" -family = "gpt-oss" -release_date = "2025-11-06" -last_updated = "2026-06-10" -attachment = false -reasoning = true -tool_call = true -temperature = true -knowledge = "2025-07" -open_weights = true - -[limit] -context = 128000 -output = 16384 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/openai/gpt-oss-120b" diff --git a/models/venice/qwen3-235b-a22b-instruct-2507.toml b/models/venice/qwen3-235b-a22b-instruct-2507.toml deleted file mode 100644 index 2a916b230..000000000 --- a/models/venice/qwen3-235b-a22b-instruct-2507.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Qwen 3 235B A22B Instruct 2507" -family = "qwen" -release_date = "2025-04-29" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = true -structured_output = true -knowledge = "2025-07" -open_weights = true - -[limit] -context = 128_000 -output = 16_384 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-235B-A22B-Instruct-2507-FP8" diff --git a/models/venice/qwen3-235b-a22b-thinking-2507.toml b/models/venice/qwen3-235b-a22b-thinking-2507.toml deleted file mode 100644 index 8c6a5dd0e..000000000 --- a/models/venice/qwen3-235b-a22b-thinking-2507.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Qwen 3 235B A22B Thinking 2507" -family = "qwen" -release_date = "2025-04-29" -last_updated = "2026-06-10" -attachment = false -reasoning = true -temperature = true -tool_call = true -structured_output = true -knowledge = "2025-07" -open_weights = true - -[limit] -context = 128_000 -output = 16_384 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-235B-A22B-Thinking-2507-FP8" diff --git a/models/venice/qwen3-5-9b.toml b/models/venice/qwen3-5-9b.toml deleted file mode 100644 index 6d53123a3..000000000 --- a/models/venice/qwen3-5-9b.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Qwen 3.5 9B" -family = "qwen" -release_date = "2026-03-05" -last_updated = "2026-06-10" -attachment = true -reasoning = true -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 256_000 -output = 32_768 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3.5-9B" diff --git a/models/venice/qwen3-coder-480b-a35b-instruct-turbo.toml b/models/venice/qwen3-coder-480b-a35b-instruct-turbo.toml deleted file mode 100644 index a1532c72f..000000000 --- a/models/venice/qwen3-coder-480b-a35b-instruct-turbo.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Qwen 3 Coder 480B Turbo" -family = "qwen" -release_date = "2026-01-27" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 256_000 -output = 65_536 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo" diff --git a/models/venice/qwen3-next-80b.toml b/models/venice/qwen3-next-80b.toml deleted file mode 100644 index ba3a702ab..000000000 --- a/models/venice/qwen3-next-80b.toml +++ /dev/null @@ -1,22 +0,0 @@ -name = "Qwen 3 Next 80b" -family = "qwen" -release_date = "2025-04-29" -last_updated = "2026-06-10" -attachment = false -reasoning = false -temperature = true -tool_call = true -structured_output = true -knowledge = "2025-07" -open_weights = true - -[limit] -context = 256_000 -output = 16_384 - -[modalities] -input = ["text"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-Next-80B-A3B-Instruct" diff --git a/models/venice/qwen3-vl-235b-a22b.toml b/models/venice/qwen3-vl-235b-a22b.toml deleted file mode 100644 index 73d122694..000000000 --- a/models/venice/qwen3-vl-235b-a22b.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Qwen3 VL 235B" -family = "qwen3.5" -release_date = "2026-01-16" -last_updated = "2026-06-10" -attachment = true -reasoning = false -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 256_000 -output = 16_384 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/Qwen/Qwen3-VL-235B-A22B-Instruct" diff --git a/models/venice/venice-uncensored-1-2.toml b/models/venice/venice-uncensored-1-2.toml deleted file mode 100644 index 1e108df18..000000000 --- a/models/venice/venice-uncensored-1-2.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Venice Uncensored 1.2" -family = "venice" -release_date = "2026-04-01" -last_updated = "2026-06-10" -attachment = true -reasoning = false -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 128_000 -output = 8_192 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/cognitivecomputations/Dolphin-Mistral-24B-Venice-Edition" diff --git a/models/venice/venice-uncensored-role-play.toml b/models/venice/venice-uncensored-role-play.toml deleted file mode 100644 index 8bfa5d404..000000000 --- a/models/venice/venice-uncensored-role-play.toml +++ /dev/null @@ -1,21 +0,0 @@ -name = "Venice Role Play Uncensored" -family = "venice" -release_date = "2026-02-20" -last_updated = "2026-06-10" -attachment = true -reasoning = false -temperature = true -tool_call = true -structured_output = true -open_weights = true - -[limit] -context = 128_000 -output = 4_096 - -[modalities] -input = ["text", "image"] -output = ["text"] - -[[weights]] -url = "https://huggingface.co/dphnAI/24B-3.2-RP-K2-final" diff --git a/packages/core/src/sync/index.ts b/packages/core/src/sync/index.ts index 8bd27c9b2..4cb51a923 100644 --- a/packages/core/src/sync/index.ts +++ b/packages/core/src/sync/index.ts @@ -51,6 +51,7 @@ export interface SyncProvider { skipCreates?: boolean; deleteMissing?: boolean; preserveSymlinks?: boolean; + preserveBaseModels?: boolean; sameModel?(current: ExistingModel, desired: SyncedModel): boolean; missingNotice?(paths: string[]): string[]; sourceID?(model: SourceModel): string; @@ -165,7 +166,9 @@ export async function syncProvider( const parsed = SyncedAuthoredModel.safeParse(stripUndefined({ id: translated.id, ...preserveReasoningOptions( - preserveBaseModel(translated.model, existing.get(relativePath)?.authored), + provider.preserveBaseModels === false + ? translated.model + : preserveBaseModel(translated.model, existing.get(relativePath)?.authored), existing.get(relativePath)?.authored, ), })); diff --git a/packages/core/src/sync/providers/venice.ts b/packages/core/src/sync/providers/venice.ts index c4867192a..10a3db10a 100644 --- a/packages/core/src/sync/providers/venice.ts +++ b/packages/core/src/sync/providers/venice.ts @@ -3,7 +3,7 @@ import path from "node:path"; import { z } from "zod"; import { ModelFamilyValues } from "../../family.js"; -import type { ExistingModel, SyncProvider, SyncedFullModel, SyncedMetadata, SyncedModel } from "../index.js"; +import type { ExistingModel, SyncProvider, SyncedFullModel, SyncedModel } from "../index.js"; import { factorBaseModel } from "./openrouter.js"; const API_ENDPOINT = "https://api.venice.ai/api/v1/models?type=text"; @@ -11,6 +11,7 @@ const MODELS_DIR = path.join(import.meta.dirname, "..", "..", "..", "..", "..", const Capabilities = z.object({ supportsAudioInput: z.boolean().optional(), + supportsE2EE: z.boolean().optional(), supportsFunctionCalling: z.boolean().optional(), supportsReasoning: z.boolean().optional(), supportsReasoningEffort: z.boolean().optional(), @@ -82,7 +83,7 @@ export const venice = { id: "venice", name: "Venice", modelsDir: "providers/venice/models", - metadataNamespace: "venice", + preserveBaseModels: false, async fetchModels() { const headers = process.env.VENICE_API_KEY ? { Authorization: `Bearer ${process.env.VENICE_API_KEY}` } @@ -97,20 +98,14 @@ export const venice = { return VeniceResponse.parse(raw).data; }, translateModel(model, context) { + if (model.model_spec.capabilities.supportsE2EE === true) return undefined; const id = model.id.replaceAll("/", "-"); const existing = context.existing(id); - const resolvedBase = existing?.base_model ?? resolveVeniceBaseModel(model.id, model.model_spec.name); - const baseModel = resolvedBase ?? `venice/${id}`; - const full = buildVeniceModel(model, existing, null); - const metadata = baseModel.startsWith("venice/") - ? { id: baseModel, model: buildVeniceMetadata(full, model.model_spec.modelSource) } - : undefined; + const existingBase = existing?.base_model?.startsWith("venice/") === false ? existing.base_model : undefined; + const resolvedBase = existingBase ?? resolveVeniceBaseModel(model.id, model.model_spec.name); return { id, - model: resolvedBase === undefined - ? factorNewMetadata(baseModel, full) - : buildVeniceModel(model, existing, baseModel), - metadata, + model: buildVeniceModel(model, existing, resolvedBase ?? null), }; }, } satisfies SyncProvider; @@ -166,7 +161,7 @@ export function buildVeniceModel( reasoning_options: reasoningOptions, tool_call: capabilities.supportsFunctionCalling === true, structured_output: capabilities.supportsResponseSchema === true ? true : undefined, - temperature: true, + temperature: undefined, cost, limit, modalities: { input: [...new Set(input)], output: ["text" as const] }, @@ -245,28 +240,6 @@ function inferFamily(id: string, name: string) { }); } -function buildVeniceMetadata(model: SyncedModel, source: string | undefined): SyncedMetadata { - if ("base_model" in model) throw new Error("Cannot build Venice metadata from a factored model"); - const { cost: _cost, reasoning_options: _reasoningOptions, interleaved: _interleaved, status: _status, ...metadata } = model; - return { - ...metadata, - weights: model.open_weights && source?.startsWith("https://huggingface.co/") - ? [{ url: source }] - : undefined, - }; -} - -function factorNewMetadata(baseModel: string, model: SyncedModel): SyncedModel { - if ("base_model" in model) return model; - return { - base_model: baseModel, - reasoning_options: model.reasoning_options, - cost: model.cost, - status: model.status, - interleaved: model.interleaved, - }; -} - function stable(value: unknown): string { if (Array.isArray(value)) return `[${value.map(stable).sort().join(",")}]`; if (value !== null && typeof value === "object") { diff --git a/packages/core/test/venice-sync.test.ts b/packages/core/test/venice-sync.test.ts index 3e0511a6b..74718623f 100644 --- a/packages/core/test/venice-sync.test.ts +++ b/packages/core/test/venice-sync.test.ts @@ -5,6 +5,7 @@ import path from "node:path"; import { buildVeniceModel, resolveVeniceBaseModel, + venice, VeniceResponse, type VeniceModel, } from "../src/sync/providers/venice.js"; @@ -61,6 +62,25 @@ test("Venice emits empty reasoning options when efforts are unavailable", () => expect(synced).toMatchObject({ reasoning: true, reasoning_options: [] }); }); +test("Venice does not infer temperature support", () => { + const synced = buildVeniceModel(catalogModel, undefined, null, "2026-06-10"); + + expect(synced.temperature).toBeUndefined(); +}); + +test("Venice skips E2EE models", () => { + const translated = venice.translateModel({ + ...catalogModel, + id: "e2ee-test-model", + model_spec: { + ...catalogModel.model_spec, + capabilities: { ...catalogModel.model_spec.capabilities, supportsE2EE: true }, + }, + }, { existing: () => undefined }); + + expect(translated).toBeUndefined(); +}); + test("Venice uses boundary-aware family matching", () => { const synced = buildVeniceModel({ ...catalogModel, @@ -108,6 +128,7 @@ test("Venice maps API fields and keeps inherited models compact", () => { expect(synced).not.toHaveProperty("release_date"); expect(synced).not.toHaveProperty("open_weights"); expect(synced).not.toHaveProperty("modalities"); + expect(synced).not.toHaveProperty("temperature"); }); test("Venice preserves last_updated when authoritative data is unchanged", () => { @@ -127,7 +148,7 @@ test("Venice rejects malformed responses", () => { expect(() => VeniceResponse.parse({ data: [{ id: "broken" }] })).toThrow(); }); -test("all Venice models use metadata inheritance and declare reasoning options", async () => { +test("Venice models use only canonical metadata and declare reasoning options", async () => { const root = path.join(import.meta.dirname, "..", "..", ".."); const modelsDir = path.join(root, "providers", "venice", "models"); @@ -136,8 +157,11 @@ test("all Venice models use metadata inheritance and declare reasoning options", base_model?: string; reasoning_options?: unknown[]; }; - expect(model.base_model, file).toBeDefined(); expect(model.reasoning_options, file).toBeDefined(); - expect(await Bun.file(path.join(root, "models", `${model.base_model}.toml`)).exists(), file).toBe(true); + if (model.base_model !== undefined) { + expect(model.base_model.startsWith("venice/"), file).toBe(false); + expect(await Bun.file(path.join(root, "models", `${model.base_model}.toml`)).exists(), file).toBe(true); + } + expect(file.startsWith("e2ee-"), file).toBe(false); } }); diff --git a/providers/venice/README.md b/providers/venice/README.md index 92f7d0374..52486b12d 100644 --- a/providers/venice/README.md +++ b/providers/venice/README.md @@ -17,7 +17,7 @@ Provide the key through the `VENICE_API_KEY` environment variable. Details - Source endpoint: `https://api.venice.ai/api/v1/models?type=text` -- Output paths: `providers/venice/models/.toml` and generated metadata under `models/venice/` +- Output path: `providers/venice/models/.toml` - Merge behavior: Updates API-sourced fields, preserves manual fields - Dates: `release_date`/`last_updated` use `YYYY-MM-DD`; `knowledge` uses `YYYY-MM` - Output limit: Sourced from `maxCompletionTokens` in the API response (falls back to `context / 4` if absent) @@ -30,6 +30,6 @@ Preserved Fields (manual input) - PDF in `modalities.input`: Not auto-added, preserved if exists Notes -- The sync updates existing files and creates metadata for new models -- Provider files and generated Venice metadata missing from the API are deleted +- The sync updates existing files and skips E2EE models, which require unsupported client-side encryption +- Provider files missing from the API are deleted - Run with `--dry-run` to preview changes before applying diff --git a/providers/venice/models/aion-labs-aion-2-0.toml b/providers/venice/models/aion-labs-aion-2-0.toml index ce341d965..bb1fc1b40 100644 --- a/providers/venice/models/aion-labs-aion-2-0.toml +++ b/providers/venice/models/aion-labs-aion-2-0.toml @@ -1,4 +1,10 @@ -base_model = "venice/aion-labs-aion-2-0" +name = "Aion 2.0" +release_date = "2026-03-24" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = false +open_weights = false [[reasoning_options]] type = "effort" @@ -8,3 +14,11 @@ values = ["low", "medium", "high"] input = 1 output = 2 cache_read = 0.25 + +[limit] +context = 128_000 +output = 32_768 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/arcee-trinity-large-thinking.toml b/providers/venice/models/arcee-trinity-large-thinking.toml index 31ed7efaf..0b40caf89 100644 --- a/providers/venice/models/arcee-trinity-large-thinking.toml +++ b/providers/venice/models/arcee-trinity-large-thinking.toml @@ -1,4 +1,12 @@ -base_model = "venice/arcee-trinity-large-thinking" +name = "Trinity Large Thinking" +family = "trinity" +release_date = "2026-04-02" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = true +structured_output = true +open_weights = true [[reasoning_options]] type = "effort" @@ -11,3 +19,11 @@ field = "reasoning_content" input = 0.3125 output = 1.125 cache_read = 0.075 + +[limit] +context = 256_000 +output = 65_536 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/claude-fable-5.toml b/providers/venice/models/claude-fable-5.toml index 216bbf20d..67103c85f 100644 --- a/providers/venice/models/claude-fable-5.toml +++ b/providers/venice/models/claude-fable-5.toml @@ -1,7 +1,6 @@ base_model = "anthropic/claude-fable-5" release_date = "2026-06-10" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-5.toml b/providers/venice/models/claude-opus-4-5.toml index ede0dd9da..4214b6ea7 100644 --- a/providers/venice/models/claude-opus-4-5.toml +++ b/providers/venice/models/claude-opus-4-5.toml @@ -1,7 +1,7 @@ base_model = "anthropic/claude-opus-4-5" name = "Claude Opus 4.5" release_date = "2025-12-06" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-6-fast.toml b/providers/venice/models/claude-opus-4-6-fast.toml index bb0024ea4..f6da87c51 100644 --- a/providers/venice/models/claude-opus-4-6-fast.toml +++ b/providers/venice/models/claude-opus-4-6-fast.toml @@ -1,7 +1,7 @@ base_model = "anthropic/claude-opus-4-6" name = "Claude Opus 4.6 Fast" release_date = "2026-04-08" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-6.toml b/providers/venice/models/claude-opus-4-6.toml index 15befb412..f44bb5903 100644 --- a/providers/venice/models/claude-opus-4-6.toml +++ b/providers/venice/models/claude-opus-4-6.toml @@ -1,5 +1,5 @@ base_model = "anthropic/claude-opus-4-6" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-7-fast.toml b/providers/venice/models/claude-opus-4-7-fast.toml index 9fe1bfb4d..d3ec897a5 100644 --- a/providers/venice/models/claude-opus-4-7-fast.toml +++ b/providers/venice/models/claude-opus-4-7-fast.toml @@ -1,8 +1,7 @@ base_model = "anthropic/claude-opus-4-7" name = "Claude Opus 4.7 Fast" release_date = "2026-05-14" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-7.toml b/providers/venice/models/claude-opus-4-7.toml index 008cfb838..b1647e8d5 100644 --- a/providers/venice/models/claude-opus-4-7.toml +++ b/providers/venice/models/claude-opus-4-7.toml @@ -1,6 +1,5 @@ base_model = "anthropic/claude-opus-4-7" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-8-fast.toml b/providers/venice/models/claude-opus-4-8-fast.toml index ab5a6baf7..800effef9 100644 --- a/providers/venice/models/claude-opus-4-8-fast.toml +++ b/providers/venice/models/claude-opus-4-8-fast.toml @@ -1,7 +1,6 @@ base_model = "anthropic/claude-opus-4-8" name = "Claude Opus 4.8 Fast" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-opus-4-8.toml b/providers/venice/models/claude-opus-4-8.toml index 0f4ce5ad3..f21a63789 100644 --- a/providers/venice/models/claude-opus-4-8.toml +++ b/providers/venice/models/claude-opus-4-8.toml @@ -1,6 +1,5 @@ base_model = "anthropic/claude-opus-4-8" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-sonnet-4-5.toml b/providers/venice/models/claude-sonnet-4-5.toml index 5f2ea4d2e..56abf44b9 100644 --- a/providers/venice/models/claude-sonnet-4-5.toml +++ b/providers/venice/models/claude-sonnet-4-5.toml @@ -1,7 +1,7 @@ base_model = "anthropic/claude-sonnet-4-5" name = "Claude Sonnet 4.5" release_date = "2025-01-15" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/claude-sonnet-4-6.toml b/providers/venice/models/claude-sonnet-4-6.toml index aa1af4f26..d1ff07091 100644 --- a/providers/venice/models/claude-sonnet-4-6.toml +++ b/providers/venice/models/claude-sonnet-4-6.toml @@ -1,5 +1,5 @@ base_model = "anthropic/claude-sonnet-4-6" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true reasoning_options = [] diff --git a/providers/venice/models/deepseek-v3.2.toml b/providers/venice/models/deepseek-v3.2.toml index d51369dde..3154ddc0a 100644 --- a/providers/venice/models/deepseek-v3.2.toml +++ b/providers/venice/models/deepseek-v3.2.toml @@ -1,4 +1,12 @@ -base_model = "venice/deepseek-v3.2" +name = "DeepSeek V3.2" +family = "deepseek" +release_date = "2025-12-04" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = true +structured_output = true +open_weights = true [[reasoning_options]] type = "effort" @@ -8,3 +16,11 @@ values = ["none", "low", "medium", "high"] input = 0.33 output = 0.48 cache_read = 0.16 + +[limit] +context = 160_000 +output = 32_768 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/deepseek-v4-flash.toml b/providers/venice/models/deepseek-v4-flash.toml index 3a24a5064..e2387b66a 100644 --- a/providers/venice/models/deepseek-v4-flash.toml +++ b/providers/venice/models/deepseek-v4-flash.toml @@ -1,6 +1,6 @@ base_model = "deepseek/deepseek-v4-flash" family = "deepseek" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [interleaved] diff --git a/providers/venice/models/deepseek-v4-pro.toml b/providers/venice/models/deepseek-v4-pro.toml index 673e8fb35..dae00a559 100644 --- a/providers/venice/models/deepseek-v4-pro.toml +++ b/providers/venice/models/deepseek-v4-pro.toml @@ -1,6 +1,6 @@ base_model = "deepseek/deepseek-v4-pro" family = "deepseek" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [interleaved] diff --git a/providers/venice/models/e2ee-gemma-3-27b-p.toml b/providers/venice/models/e2ee-gemma-3-27b-p.toml deleted file mode 100644 index e8cc1aaa3..000000000 --- a/providers/venice/models/e2ee-gemma-3-27b-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-gemma-3-27b-p" -reasoning_options = [] - -[cost] -input = 0.14 -output = 0.5 diff --git a/providers/venice/models/e2ee-gemma-4-26b-a4b-uncensored-p.toml b/providers/venice/models/e2ee-gemma-4-26b-a4b-uncensored-p.toml deleted file mode 100644 index c61027242..000000000 --- a/providers/venice/models/e2ee-gemma-4-26b-a4b-uncensored-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-gemma-4-26b-a4b-uncensored-p" -reasoning_options = [] - -[cost] -input = 0.19 -output = 0.88 diff --git a/providers/venice/models/e2ee-gemma-4-31b.toml b/providers/venice/models/e2ee-gemma-4-31b.toml deleted file mode 100644 index e04540484..000000000 --- a/providers/venice/models/e2ee-gemma-4-31b.toml +++ /dev/null @@ -1,7 +0,0 @@ -base_model = "venice/e2ee-gemma-4-31b" -reasoning_options = [] - -[cost] -input = 0.139 -output = 0.43 -cache_read = 0.028 diff --git a/providers/venice/models/e2ee-glm-4-7-flash-p.toml b/providers/venice/models/e2ee-glm-4-7-flash-p.toml deleted file mode 100644 index 52d3605b5..000000000 --- a/providers/venice/models/e2ee-glm-4-7-flash-p.toml +++ /dev/null @@ -1,18 +0,0 @@ -base_model = "zhipuai/glm-4.7-flash" -name = "GLM 4.7 Flash" -family = "glm" -release_date = "2026-03-18" -last_updated = "2026-06-10" -tool_call = false - -[[reasoning_options]] -type = "effort" -values = ["none", "low", "medium", "high"] - -[cost] -input = 0.13 -output = 0.55 - -[limit] -context = 198_000 -output = 4_096 diff --git a/providers/venice/models/e2ee-glm-4-7-p.toml b/providers/venice/models/e2ee-glm-4-7-p.toml deleted file mode 100644 index 0c4fb0e73..000000000 --- a/providers/venice/models/e2ee-glm-4-7-p.toml +++ /dev/null @@ -1,17 +0,0 @@ -base_model = "zhipuai/glm-4.7" -name = "GLM 4.7" -release_date = "2026-03-18" -last_updated = "2026-06-10" -tool_call = false - -[[reasoning_options]] -type = "effort" -values = ["none", "low", "medium", "high"] - -[cost] -input = 1.1 -output = 4.15 - -[limit] -context = 128_000 -output = 32_768 diff --git a/providers/venice/models/e2ee-glm-5-1.toml b/providers/venice/models/e2ee-glm-5-1.toml deleted file mode 100644 index 33a3cc971..000000000 --- a/providers/venice/models/e2ee-glm-5-1.toml +++ /dev/null @@ -1,13 +0,0 @@ -base_model = "zhipuai/glm-5.1" -name = "GLM 5.1" -release_date = "2026-04-24" -last_updated = "2026-06-10" -tool_call = false -reasoning_options = [] - -[cost] -input = 1.1 -output = 4.15 - -[limit] -output = 32_768 diff --git a/providers/venice/models/e2ee-gpt-oss-120b-p.toml b/providers/venice/models/e2ee-gpt-oss-120b-p.toml deleted file mode 100644 index 8918c4390..000000000 --- a/providers/venice/models/e2ee-gpt-oss-120b-p.toml +++ /dev/null @@ -1,9 +0,0 @@ -base_model = "venice/e2ee-gpt-oss-120b-p" - -[[reasoning_options]] -type = "effort" -values = ["none", "low", "medium", "high"] - -[cost] -input = 0.13 -output = 0.65 diff --git a/providers/venice/models/e2ee-gpt-oss-20b-p.toml b/providers/venice/models/e2ee-gpt-oss-20b-p.toml deleted file mode 100644 index b5c1e956b..000000000 --- a/providers/venice/models/e2ee-gpt-oss-20b-p.toml +++ /dev/null @@ -1,9 +0,0 @@ -base_model = "venice/e2ee-gpt-oss-20b-p" - -[[reasoning_options]] -type = "effort" -values = ["none", "low", "medium", "high"] - -[cost] -input = 0.05 -output = 0.19 diff --git a/providers/venice/models/e2ee-qwen-2-5-7b-p.toml b/providers/venice/models/e2ee-qwen-2-5-7b-p.toml deleted file mode 100644 index 4546aca28..000000000 --- a/providers/venice/models/e2ee-qwen-2-5-7b-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-qwen-2-5-7b-p" -reasoning_options = [] - -[cost] -input = 0.05 -output = 0.13 diff --git a/providers/venice/models/e2ee-qwen3-30b-a3b-p.toml b/providers/venice/models/e2ee-qwen3-30b-a3b-p.toml deleted file mode 100644 index e1847929f..000000000 --- a/providers/venice/models/e2ee-qwen3-30b-a3b-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-qwen3-30b-a3b-p" -reasoning_options = [] - -[cost] -input = 0.19 -output = 0.69 diff --git a/providers/venice/models/e2ee-qwen3-6-35b-a3b-uncensored-p.toml b/providers/venice/models/e2ee-qwen3-6-35b-a3b-uncensored-p.toml deleted file mode 100644 index 03f1299e1..000000000 --- a/providers/venice/models/e2ee-qwen3-6-35b-a3b-uncensored-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-qwen3-6-35b-a3b-uncensored-p" -reasoning_options = [] - -[cost] -input = 0.38 -output = 1.88 diff --git a/providers/venice/models/e2ee-qwen3-6-35b-a3b.toml b/providers/venice/models/e2ee-qwen3-6-35b-a3b.toml deleted file mode 100644 index 7daa3d46e..000000000 --- a/providers/venice/models/e2ee-qwen3-6-35b-a3b.toml +++ /dev/null @@ -1,7 +0,0 @@ -base_model = "venice/e2ee-qwen3-6-35b-a3b" -reasoning_options = [] - -[cost] -input = 0.182 -output = 1.18 -cache_read = 0.06 diff --git a/providers/venice/models/e2ee-qwen3-vl-30b-a3b-p.toml b/providers/venice/models/e2ee-qwen3-vl-30b-a3b-p.toml deleted file mode 100644 index 20642bdfb..000000000 --- a/providers/venice/models/e2ee-qwen3-vl-30b-a3b-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-qwen3-vl-30b-a3b-p" -reasoning_options = [] - -[cost] -input = 0.25 -output = 0.9 diff --git a/providers/venice/models/e2ee-venice-uncensored-24b-p.toml b/providers/venice/models/e2ee-venice-uncensored-24b-p.toml deleted file mode 100644 index f7cf41ffe..000000000 --- a/providers/venice/models/e2ee-venice-uncensored-24b-p.toml +++ /dev/null @@ -1,6 +0,0 @@ -base_model = "venice/e2ee-venice-uncensored-24b-p" -reasoning_options = [] - -[cost] -input = 0.25 -output = 1.15 diff --git a/providers/venice/models/gemini-3-1-pro-preview.toml b/providers/venice/models/gemini-3-1-pro-preview.toml index d2bbca7f3..3b5e8c760 100644 --- a/providers/venice/models/gemini-3-1-pro-preview.toml +++ b/providers/venice/models/gemini-3-1-pro-preview.toml @@ -1,6 +1,6 @@ base_model = "google/gemini-3.1-pro-preview" family = "gemini" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/gemini-3-5-flash.toml b/providers/venice/models/gemini-3-5-flash.toml index 6b19cf5b7..d8139f77c 100644 --- a/providers/venice/models/gemini-3-5-flash.toml +++ b/providers/venice/models/gemini-3-5-flash.toml @@ -1,7 +1,7 @@ base_model = "google/gemini-3.5-flash" family = "gemini" release_date = "2026-05-22" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/gemini-3-flash-preview.toml b/providers/venice/models/gemini-3-flash-preview.toml index 41e99383b..1e5eedd40 100644 --- a/providers/venice/models/gemini-3-flash-preview.toml +++ b/providers/venice/models/gemini-3-flash-preview.toml @@ -1,7 +1,7 @@ base_model = "google/gemini-3-flash-preview" family = "gemini" release_date = "2025-12-19" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/gemma-4-uncensored.toml b/providers/venice/models/gemma-4-uncensored.toml index bd9dbf524..affc4e914 100644 --- a/providers/venice/models/gemma-4-uncensored.toml +++ b/providers/venice/models/gemma-4-uncensored.toml @@ -1,6 +1,22 @@ -base_model = "venice/gemma-4-uncensored" +name = "Gemma 4 Uncensored" +family = "gemma" +release_date = "2026-04-13" +last_updated = "2026-06-11" +attachment = true +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.1625 output = 0.5 + +[limit] +context = 256_000 +output = 8_192 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/google-gemma-3-27b-it.toml b/providers/venice/models/google-gemma-3-27b-it.toml index 7cc5715f4..0717c8b0d 100644 --- a/providers/venice/models/google-gemma-3-27b-it.toml +++ b/providers/venice/models/google-gemma-3-27b-it.toml @@ -1,6 +1,22 @@ -base_model = "venice/google-gemma-3-27b-it" +name = "Google Gemma 3 27B Instruct" +family = "gemma" +release_date = "2025-11-04" +last_updated = "2026-06-11" +attachment = true +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.12 output = 0.2 + +[limit] +context = 198_000 +output = 16_384 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/google-gemma-4-26b-a4b-it.toml b/providers/venice/models/google-gemma-4-26b-a4b-it.toml index 9e0dfea47..ea28dba64 100644 --- a/providers/venice/models/google-gemma-4-26b-a4b-it.toml +++ b/providers/venice/models/google-gemma-4-26b-a4b-it.toml @@ -1,6 +1,6 @@ base_model = "google/gemma-4-26b-a4b-it" name = "Google Gemma 4 26B A4B Instruct" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/google-gemma-4-31b-it.toml b/providers/venice/models/google-gemma-4-31b-it.toml index 65d3e2cd0..ee0e46734 100644 --- a/providers/venice/models/google-gemma-4-31b-it.toml +++ b/providers/venice/models/google-gemma-4-31b-it.toml @@ -1,7 +1,7 @@ base_model = "google/gemma-4-31b-it" name = "Google Gemma 4 31B Instruct" release_date = "2026-04-03" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/grok-4-20-multi-agent.toml b/providers/venice/models/grok-4-20-multi-agent.toml index ed7801eb6..6a96c8018 100644 --- a/providers/venice/models/grok-4-20-multi-agent.toml +++ b/providers/venice/models/grok-4-20-multi-agent.toml @@ -1,4 +1,12 @@ -base_model = "venice/grok-4-20-multi-agent" +name = "Grok 4.20 Multi-Agent" +family = "grok" +release_date = "2026-03-12" +last_updated = "2026-06-11" +attachment = true +reasoning = true +tool_call = false +structured_output = true +open_weights = false reasoning_options = [] [cost] @@ -11,3 +19,11 @@ tier = { type = "context", size = 200_000 } input = 2.83 output = 5.67 cache_read = 0.45 + +[limit] +context = 2_000_000 +output = 128_000 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/grok-4-20.toml b/providers/venice/models/grok-4-20.toml index d7f541db3..b8f505d5a 100644 --- a/providers/venice/models/grok-4-20.toml +++ b/providers/venice/models/grok-4-20.toml @@ -1,4 +1,12 @@ -base_model = "venice/grok-4-20" +name = "Grok 4.20" +family = "grok" +release_date = "2026-03-12" +last_updated = "2026-06-11" +attachment = true +reasoning = true +tool_call = true +structured_output = true +open_weights = false reasoning_options = [] [cost] @@ -11,3 +19,11 @@ tier = { type = "context", size = 200_000 } input = 2.83 output = 5.67 cache_read = 0.45 + +[limit] +context = 2_000_000 +output = 128_000 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/grok-4-3.toml b/providers/venice/models/grok-4-3.toml index c2f11899d..7847883fe 100644 --- a/providers/venice/models/grok-4-3.toml +++ b/providers/venice/models/grok-4-3.toml @@ -1,6 +1,6 @@ base_model = "xai/grok-4.3" release_date = "2026-04-18" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [cost] diff --git a/providers/venice/models/grok-build-0-1.toml b/providers/venice/models/grok-build-0-1.toml index 6ce4d8ecd..1934415d0 100644 --- a/providers/venice/models/grok-build-0-1.toml +++ b/providers/venice/models/grok-build-0-1.toml @@ -1,6 +1,6 @@ base_model = "xai/grok-build-0.1" release_date = "2026-05-21" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [cost] diff --git a/providers/venice/models/hermes-3-llama-3.1-405b.toml b/providers/venice/models/hermes-3-llama-3.1-405b.toml index 600c37d50..dfdcc6d80 100644 --- a/providers/venice/models/hermes-3-llama-3.1-405b.toml +++ b/providers/venice/models/hermes-3-llama-3.1-405b.toml @@ -1,6 +1,21 @@ -base_model = "venice/hermes-3-llama-3.1-405b" +name = "Hermes 3 Llama 3.1 405b" +family = "hermes" +release_date = "2025-09-25" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = false +open_weights = true reasoning_options = [] [cost] input = 1.1 output = 3 + +[limit] +context = 128_000 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/kimi-k2-5.toml b/providers/venice/models/kimi-k2-5.toml index 6b9227acc..5fbe6047e 100644 --- a/providers/venice/models/kimi-k2-5.toml +++ b/providers/venice/models/kimi-k2-5.toml @@ -1,9 +1,8 @@ base_model = "moonshotai/kimi-k2.5" family = "kimi" release_date = "2026-01-27" -last_updated = "2026-06-10" +last_updated = "2026-06-11" attachment = true -temperature = true knowledge = "2024-04" open_weights = false diff --git a/providers/venice/models/kimi-k2-6.toml b/providers/venice/models/kimi-k2-6.toml index 0f0fd8dec..049728906 100644 --- a/providers/venice/models/kimi-k2-6.toml +++ b/providers/venice/models/kimi-k2-6.toml @@ -1,7 +1,7 @@ base_model = "moonshotai/kimi-k2.6" family = "kimi" release_date = "2026-04-20" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/llama-3.2-3b.toml b/providers/venice/models/llama-3.2-3b.toml index 890034f27..32e374971 100644 --- a/providers/venice/models/llama-3.2-3b.toml +++ b/providers/venice/models/llama-3.2-3b.toml @@ -1,6 +1,21 @@ -base_model = "venice/llama-3.2-3b" +name = "Llama 3.2 3B" +family = "llama" +release_date = "2024-10-03" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = true +open_weights = true reasoning_options = [] [cost] input = 0.15 output = 0.6 + +[limit] +context = 128_000 +output = 4_096 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/llama-3.3-70b.toml b/providers/venice/models/llama-3.3-70b.toml index 5078a4fe2..6f3d1e105 100644 --- a/providers/venice/models/llama-3.3-70b.toml +++ b/providers/venice/models/llama-3.3-70b.toml @@ -1,6 +1,21 @@ -base_model = "venice/llama-3.3-70b" +name = "Llama 3.3 70B" +family = "llama" +release_date = "2025-04-06" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = true +open_weights = true reasoning_options = [] [cost] input = 0.7 output = 2.8 + +[limit] +context = 128_000 +output = 4_096 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/mercury-2.toml b/providers/venice/models/mercury-2.toml index 74a06541b..6853ce6ad 100644 --- a/providers/venice/models/mercury-2.toml +++ b/providers/venice/models/mercury-2.toml @@ -1,4 +1,12 @@ -base_model = "venice/mercury-2" +name = "Mercury 2" +family = "mercury" +release_date = "2026-02-20" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = true +structured_output = true +open_weights = false [[reasoning_options]] type = "effort" @@ -8,3 +16,11 @@ values = ["none", "low", "medium", "high"] input = 0.3125 output = 0.9375 cache_read = 0.03125 + +[limit] +context = 128_000 +output = 50_000 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/minimax-m25.toml b/providers/venice/models/minimax-m25.toml index a94ba1894..0f1c7b306 100644 --- a/providers/venice/models/minimax-m25.toml +++ b/providers/venice/models/minimax-m25.toml @@ -1,6 +1,6 @@ base_model = "minimax/MiniMax-M2.5" name = "MiniMax M2.5" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/minimax-m27.toml b/providers/venice/models/minimax-m27.toml index e860718dd..061f0a920 100644 --- a/providers/venice/models/minimax-m27.toml +++ b/providers/venice/models/minimax-m27.toml @@ -1,6 +1,6 @@ base_model = "minimax/MiniMax-M2.7" name = "MiniMax M2.7" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/minimax-m3.toml b/providers/venice/models/minimax-m3.toml index 25bda94d8..1925593b7 100644 --- a/providers/venice/models/minimax-m3.toml +++ b/providers/venice/models/minimax-m3.toml @@ -1,7 +1,7 @@ base_model = "minimax/MiniMax-M3" name = "MiniMax M3" family = "minimax-m3" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [cost] diff --git a/providers/venice/models/mistral-small-2603.toml b/providers/venice/models/mistral-small-2603.toml index 3157a8fac..58a3e7d71 100644 --- a/providers/venice/models/mistral-small-2603.toml +++ b/providers/venice/models/mistral-small-2603.toml @@ -1,5 +1,5 @@ base_model = "mistral/mistral-small-2603" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/mistral-small-3-2-24b-instruct.toml b/providers/venice/models/mistral-small-3-2-24b-instruct.toml index fffbf7054..3dc6559cf 100644 --- a/providers/venice/models/mistral-small-3-2-24b-instruct.toml +++ b/providers/venice/models/mistral-small-3-2-24b-instruct.toml @@ -1,6 +1,22 @@ -base_model = "venice/mistral-small-3-2-24b-instruct" +name = "Mistral Small 3.2 24B Instruct" +family = "mistral-small" +release_date = "2026-01-15" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.09375 output = 0.25 + +[limit] +context = 256_000 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml b/providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml index e7c361b33..ebf419887 100644 --- a/providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml +++ b/providers/venice/models/nvidia-nemotron-3-nano-30b-a3b.toml @@ -1,7 +1,7 @@ base_model = "nvidia/nemotron-3-nano-30b-a3b" name = "NVIDIA Nemotron 3 Nano 30B" release_date = "2026-01-27" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning = false structured_output = true reasoning_options = [] diff --git a/providers/venice/models/nvidia-nemotron-3-ultra-550b-a55b.toml b/providers/venice/models/nvidia-nemotron-3-ultra-550b-a55b.toml index 8e9525133..32e06cb95 100644 --- a/providers/venice/models/nvidia-nemotron-3-ultra-550b-a55b.toml +++ b/providers/venice/models/nvidia-nemotron-3-ultra-550b-a55b.toml @@ -1,6 +1,6 @@ base_model = "nvidia/nemotron-3-ultra-550b-a55b" name = "NVIDIA Nemotron 3 Ultra" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/nvidia-nemotron-cascade-2-30b-a3b.toml b/providers/venice/models/nvidia-nemotron-cascade-2-30b-a3b.toml index d93727c4e..ac227bdf2 100644 --- a/providers/venice/models/nvidia-nemotron-cascade-2-30b-a3b.toml +++ b/providers/venice/models/nvidia-nemotron-cascade-2-30b-a3b.toml @@ -1,6 +1,6 @@ base_model = "nvidia/nemotron-cascade-2-30b-a3b" +last_updated = "2026-06-11" structured_output = true -last_updated = "2026-06-10" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/olafangensan-glm-4.7-flash-heretic.toml b/providers/venice/models/olafangensan-glm-4.7-flash-heretic.toml index e4141e034..9c774ff09 100644 --- a/providers/venice/models/olafangensan-glm-4.7-flash-heretic.toml +++ b/providers/venice/models/olafangensan-glm-4.7-flash-heretic.toml @@ -1,4 +1,12 @@ -base_model = "venice/olafangensan-glm-4.7-flash-heretic" +name = "GLM 4.7 Flash Heretic" +family = "glm" +release_date = "2026-02-04" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = true +structured_output = true +open_weights = true [[reasoning_options]] type = "effort" @@ -7,3 +15,11 @@ values = ["none", "low", "medium", "high"] [cost] input = 0.14 output = 0.8 + +[limit] +context = 200_000 +output = 24_000 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/openai-gpt-4o-2024-11-20.toml b/providers/venice/models/openai-gpt-4o-2024-11-20.toml index 36304d45a..5358ea1a2 100644 --- a/providers/venice/models/openai-gpt-4o-2024-11-20.toml +++ b/providers/venice/models/openai-gpt-4o-2024-11-20.toml @@ -1,7 +1,7 @@ base_model = "openai/gpt-4o-2024-11-20" name = "GPT-4o" release_date = "2026-02-28" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [cost] diff --git a/providers/venice/models/openai-gpt-4o-mini-2024-07-18.toml b/providers/venice/models/openai-gpt-4o-mini-2024-07-18.toml index 7bd2f6e4a..9842f5bd0 100644 --- a/providers/venice/models/openai-gpt-4o-mini-2024-07-18.toml +++ b/providers/venice/models/openai-gpt-4o-mini-2024-07-18.toml @@ -2,7 +2,7 @@ base_model = "openai/gpt-4o-mini" name = "GPT-4o Mini" family = "gpt" release_date = "2026-02-28" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [cost] diff --git a/providers/venice/models/openai-gpt-52-codex.toml b/providers/venice/models/openai-gpt-52-codex.toml index c312741d3..b19daba97 100644 --- a/providers/venice/models/openai-gpt-52-codex.toml +++ b/providers/venice/models/openai-gpt-52-codex.toml @@ -1,8 +1,7 @@ base_model = "openai/gpt-5.2-codex" family = "gpt" release_date = "2025-01-15" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" knowledge = "2025-08" [[reasoning_options]] diff --git a/providers/venice/models/openai-gpt-52.toml b/providers/venice/models/openai-gpt-52.toml index bc988b25f..0ccced99d 100644 --- a/providers/venice/models/openai-gpt-52.toml +++ b/providers/venice/models/openai-gpt-52.toml @@ -1,8 +1,7 @@ base_model = "openai/gpt-5.2" release_date = "2025-12-13" -last_updated = "2026-06-10" +last_updated = "2026-06-11" attachment = false -temperature = true [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/openai-gpt-53-codex.toml b/providers/venice/models/openai-gpt-53-codex.toml index a66976186..db55e2f61 100644 --- a/providers/venice/models/openai-gpt-53-codex.toml +++ b/providers/venice/models/openai-gpt-53-codex.toml @@ -1,8 +1,7 @@ base_model = "openai/gpt-5.3-codex" family = "gpt" release_date = "2026-02-24" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/openai-gpt-54-mini.toml b/providers/venice/models/openai-gpt-54-mini.toml index a72ca5fa6..d4f5e975b 100644 --- a/providers/venice/models/openai-gpt-54-mini.toml +++ b/providers/venice/models/openai-gpt-54-mini.toml @@ -2,8 +2,7 @@ base_model = "openai/gpt-5.4-mini" name = "GPT-5.4 Mini" family = "gpt" release_date = "2026-03-27" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/openai-gpt-54-pro.toml b/providers/venice/models/openai-gpt-54-pro.toml index 4b417e4a0..2254bd9c2 100644 --- a/providers/venice/models/openai-gpt-54-pro.toml +++ b/providers/venice/models/openai-gpt-54-pro.toml @@ -1,7 +1,6 @@ base_model = "openai/gpt-5.4-pro" family = "gpt" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/openai-gpt-54.toml b/providers/venice/models/openai-gpt-54.toml index d0f361a00..af80be27d 100644 --- a/providers/venice/models/openai-gpt-54.toml +++ b/providers/venice/models/openai-gpt-54.toml @@ -1,6 +1,5 @@ base_model = "openai/gpt-5.4" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/openai-gpt-55-pro.toml b/providers/venice/models/openai-gpt-55-pro.toml index bfb810167..d84cd0bcd 100644 --- a/providers/venice/models/openai-gpt-55-pro.toml +++ b/providers/venice/models/openai-gpt-55-pro.toml @@ -1,8 +1,7 @@ base_model = "openai/gpt-5.5-pro" family = "gpt" release_date = "2026-04-24" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/openai-gpt-55.toml b/providers/venice/models/openai-gpt-55.toml index 231320fca..83dddec05 100644 --- a/providers/venice/models/openai-gpt-55.toml +++ b/providers/venice/models/openai-gpt-55.toml @@ -1,6 +1,5 @@ base_model = "openai/gpt-5.5" -last_updated = "2026-06-10" -temperature = true +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/openai-gpt-oss-120b.toml b/providers/venice/models/openai-gpt-oss-120b.toml index 2329b1443..0585815e6 100644 --- a/providers/venice/models/openai-gpt-oss-120b.toml +++ b/providers/venice/models/openai-gpt-oss-120b.toml @@ -1,4 +1,11 @@ -base_model = "venice/openai-gpt-oss-120b" +name = "OpenAI GPT OSS 120B" +family = "gpt-oss" +release_date = "2025-11-06" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = true +open_weights = true [[reasoning_options]] type = "effort" @@ -7,3 +14,11 @@ values = ["none", "low", "medium", "high"] [cost] input = 0.07 output = 0.3 + +[limit] +context = 128_000 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/qwen-3-6-plus.toml b/providers/venice/models/qwen-3-6-plus.toml index 7001f2c3e..96de594ad 100644 --- a/providers/venice/models/qwen-3-6-plus.toml +++ b/providers/venice/models/qwen-3-6-plus.toml @@ -1,7 +1,7 @@ base_model = "alibaba/qwen3.6-plus" name = "Qwen 3.6 Plus Uncensored" release_date = "2026-04-06" -last_updated = "2026-06-10" +last_updated = "2026-06-11" attachment = true structured_output = true reasoning_options = [] diff --git a/providers/venice/models/qwen-3-7-max.toml b/providers/venice/models/qwen-3-7-max.toml index 802b0358b..1cc419c5c 100644 --- a/providers/venice/models/qwen-3-7-max.toml +++ b/providers/venice/models/qwen-3-7-max.toml @@ -1,7 +1,7 @@ base_model = "alibaba/qwen3.7-max" name = "Qwen 3.7 Max" release_date = "2026-05-22" -last_updated = "2026-06-10" +last_updated = "2026-06-11" reasoning_options = [] [cost] diff --git a/providers/venice/models/qwen-3-7-plus.toml b/providers/venice/models/qwen-3-7-plus.toml index d9126c4fc..6d184e71d 100644 --- a/providers/venice/models/qwen-3-7-plus.toml +++ b/providers/venice/models/qwen-3-7-plus.toml @@ -1,6 +1,6 @@ base_model = "alibaba/qwen3.7-plus" name = "Qwen 3.7 Plus" -last_updated = "2026-06-10" +last_updated = "2026-06-11" attachment = true structured_output = true reasoning_options = [] diff --git a/providers/venice/models/qwen3-235b-a22b-instruct-2507.toml b/providers/venice/models/qwen3-235b-a22b-instruct-2507.toml index 40ef59835..1e0313312 100644 --- a/providers/venice/models/qwen3-235b-a22b-instruct-2507.toml +++ b/providers/venice/models/qwen3-235b-a22b-instruct-2507.toml @@ -1,6 +1,22 @@ -base_model = "venice/qwen3-235b-a22b-instruct-2507" +name = "Qwen 3 235B A22B Instruct 2507" +family = "qwen" +release_date = "2025-04-29" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.15 output = 0.75 + +[limit] +context = 128_000 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/qwen3-235b-a22b-thinking-2507.toml b/providers/venice/models/qwen3-235b-a22b-thinking-2507.toml index c0dc7660e..bf0661f0a 100644 --- a/providers/venice/models/qwen3-235b-a22b-thinking-2507.toml +++ b/providers/venice/models/qwen3-235b-a22b-thinking-2507.toml @@ -1,4 +1,12 @@ -base_model = "venice/qwen3-235b-a22b-thinking-2507" +name = "Qwen 3 235B A22B Thinking 2507" +family = "qwen" +release_date = "2025-04-29" +last_updated = "2026-06-11" +attachment = false +reasoning = true +tool_call = true +structured_output = true +open_weights = true [[reasoning_options]] type = "effort" @@ -10,3 +18,11 @@ field = "reasoning_content" [cost] input = 0.45 output = 3.5 + +[limit] +context = 128_000 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/qwen3-5-35b-a3b.toml b/providers/venice/models/qwen3-5-35b-a3b.toml index a336a7dfb..978faa836 100644 --- a/providers/venice/models/qwen3-5-35b-a3b.toml +++ b/providers/venice/models/qwen3-5-35b-a3b.toml @@ -1,7 +1,7 @@ base_model = "alibaba/qwen3.5-35b-a3b" name = "Qwen 3.5 35B A3B" release_date = "2026-02-25" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/qwen3-5-397b-a17b.toml b/providers/venice/models/qwen3-5-397b-a17b.toml index 3e34b12b0..2a6f2d292 100644 --- a/providers/venice/models/qwen3-5-397b-a17b.toml +++ b/providers/venice/models/qwen3-5-397b-a17b.toml @@ -1,7 +1,7 @@ base_model = "alibaba/qwen3.5-397b-a17b" name = "Qwen 3.5 397B" release_date = "2026-02-16" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/qwen3-5-9b.toml b/providers/venice/models/qwen3-5-9b.toml index 65a8208ef..342da54b5 100644 --- a/providers/venice/models/qwen3-5-9b.toml +++ b/providers/venice/models/qwen3-5-9b.toml @@ -1,4 +1,12 @@ -base_model = "venice/qwen3-5-9b" +name = "Qwen 3.5 9B" +family = "qwen" +release_date = "2026-03-05" +last_updated = "2026-06-11" +attachment = true +reasoning = true +tool_call = true +structured_output = true +open_weights = true [[reasoning_options]] type = "effort" @@ -7,3 +15,11 @@ values = ["none", "low", "medium", "high"] [cost] input = 0.1 output = 0.15 + +[limit] +context = 256_000 +output = 32_768 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/qwen3-6-27b.toml b/providers/venice/models/qwen3-6-27b.toml index 0925f3a0b..7279dce8e 100644 --- a/providers/venice/models/qwen3-6-27b.toml +++ b/providers/venice/models/qwen3-6-27b.toml @@ -1,7 +1,7 @@ base_model = "alibaba/qwen3.6-27b" name = "Qwen 3.6 27B" release_date = "2026-04-24" -last_updated = "2026-06-10" +last_updated = "2026-06-11" open_weights = false [[reasoning_options]] diff --git a/providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml b/providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml index 1702c8162..b2325301d 100644 --- a/providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml +++ b/providers/venice/models/qwen3-coder-480b-a35b-instruct-turbo.toml @@ -1,7 +1,23 @@ -base_model = "venice/qwen3-coder-480b-a35b-instruct-turbo" +name = "Qwen 3 Coder 480B Turbo" +family = "qwen" +release_date = "2026-01-27" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.35 output = 1.5 cache_read = 0.04 + +[limit] +context = 256_000 +output = 65_536 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/qwen3-next-80b.toml b/providers/venice/models/qwen3-next-80b.toml index 1da9efbd7..ef241aded 100644 --- a/providers/venice/models/qwen3-next-80b.toml +++ b/providers/venice/models/qwen3-next-80b.toml @@ -1,6 +1,22 @@ -base_model = "venice/qwen3-next-80b" +name = "Qwen 3 Next 80b" +family = "qwen" +release_date = "2025-04-29" +last_updated = "2026-06-11" +attachment = false +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.35 output = 1.9 + +[limit] +context = 256_000 +output = 16_384 + +[modalities] +input = ["text"] +output = ["text"] diff --git a/providers/venice/models/qwen3-vl-235b-a22b.toml b/providers/venice/models/qwen3-vl-235b-a22b.toml index 33c0d472d..13671a8f7 100644 --- a/providers/venice/models/qwen3-vl-235b-a22b.toml +++ b/providers/venice/models/qwen3-vl-235b-a22b.toml @@ -1,6 +1,21 @@ -base_model = "venice/qwen3-vl-235b-a22b" +name = "Qwen3 VL 235B" +release_date = "2026-01-16" +last_updated = "2026-06-11" +attachment = true +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.25 output = 1.5 + +[limit] +context = 256_000 +output = 16_384 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/tencent-hy3-preview.toml b/providers/venice/models/tencent-hy3-preview.toml index 912e03052..dce52811a 100644 --- a/providers/venice/models/tencent-hy3-preview.toml +++ b/providers/venice/models/tencent-hy3-preview.toml @@ -2,7 +2,7 @@ base_model = "tencent/hy3-preview" name = "Hy3 Preview" family = "hy3" release_date = "2026-06-08" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/venice-uncensored-1-2.toml b/providers/venice/models/venice-uncensored-1-2.toml index e7439c046..c688f5e89 100644 --- a/providers/venice/models/venice-uncensored-1-2.toml +++ b/providers/venice/models/venice-uncensored-1-2.toml @@ -1,6 +1,22 @@ -base_model = "venice/venice-uncensored-1-2" +name = "Venice Uncensored 1.2" +family = "venice" +release_date = "2026-04-01" +last_updated = "2026-06-11" +attachment = true +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.2 output = 0.9 + +[limit] +context = 128_000 +output = 8_192 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/venice-uncensored-role-play.toml b/providers/venice/models/venice-uncensored-role-play.toml index 43d75e895..28d77b311 100644 --- a/providers/venice/models/venice-uncensored-role-play.toml +++ b/providers/venice/models/venice-uncensored-role-play.toml @@ -1,6 +1,22 @@ -base_model = "venice/venice-uncensored-role-play" +name = "Venice Role Play Uncensored" +family = "venice" +release_date = "2026-02-20" +last_updated = "2026-06-11" +attachment = true +reasoning = false +tool_call = true +structured_output = true +open_weights = true reasoning_options = [] [cost] input = 0.5 output = 2 + +[limit] +context = 128_000 +output = 4_096 + +[modalities] +input = ["text", "image"] +output = ["text"] diff --git a/providers/venice/models/z-ai-glm-5-turbo.toml b/providers/venice/models/z-ai-glm-5-turbo.toml index 9f809598a..9e188f51c 100644 --- a/providers/venice/models/z-ai-glm-5-turbo.toml +++ b/providers/venice/models/z-ai-glm-5-turbo.toml @@ -1,7 +1,7 @@ base_model = "zhipuai/glm-5-turbo" name = "GLM 5 Turbo" release_date = "2026-03-15" -last_updated = "2026-06-10" +last_updated = "2026-06-11" open_weights = true [[reasoning_options]] diff --git a/providers/venice/models/z-ai-glm-5v-turbo.toml b/providers/venice/models/z-ai-glm-5v-turbo.toml index 7638ca4e2..5b8df4237 100644 --- a/providers/venice/models/z-ai-glm-5v-turbo.toml +++ b/providers/venice/models/z-ai-glm-5v-turbo.toml @@ -1,6 +1,6 @@ base_model = "zhipuai/glm-5v-turbo" name = "GLM 5V Turbo" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/zai-org-glm-4.6.toml b/providers/venice/models/zai-org-glm-4.6.toml index e80aeb642..e7c8b977d 100644 --- a/providers/venice/models/zai-org-glm-4.6.toml +++ b/providers/venice/models/zai-org-glm-4.6.toml @@ -1,7 +1,7 @@ base_model = "zhipuai/glm-4.6" name = "GLM 4.6" release_date = "2024-04-01" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/zai-org-glm-4.7-flash.toml b/providers/venice/models/zai-org-glm-4.7-flash.toml index 9d80b4907..a2014abec 100644 --- a/providers/venice/models/zai-org-glm-4.7-flash.toml +++ b/providers/venice/models/zai-org-glm-4.7-flash.toml @@ -2,7 +2,7 @@ base_model = "zhipuai/glm-4.7-flash" name = "GLM 4.7 Flash" family = "glm" release_date = "2026-01-29" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/zai-org-glm-4.7.toml b/providers/venice/models/zai-org-glm-4.7.toml index 1391b8ce4..2f6cd98c4 100644 --- a/providers/venice/models/zai-org-glm-4.7.toml +++ b/providers/venice/models/zai-org-glm-4.7.toml @@ -1,7 +1,7 @@ base_model = "zhipuai/glm-4.7" name = "GLM 4.7" release_date = "2025-12-24" -last_updated = "2026-06-10" +last_updated = "2026-06-11" structured_output = true [[reasoning_options]] diff --git a/providers/venice/models/zai-org-glm-5-1.toml b/providers/venice/models/zai-org-glm-5-1.toml index df5ff8a4d..f8f3fe862 100644 --- a/providers/venice/models/zai-org-glm-5-1.toml +++ b/providers/venice/models/zai-org-glm-5-1.toml @@ -1,7 +1,7 @@ base_model = "zhipuai/glm-5.1" name = "GLM 5.1" release_date = "2026-04-07" -last_updated = "2026-06-10" +last_updated = "2026-06-11" [[reasoning_options]] type = "effort" diff --git a/providers/venice/models/zai-org-glm-5.toml b/providers/venice/models/zai-org-glm-5.toml index 1896a9aa7..b2493e2d3 100644 --- a/providers/venice/models/zai-org-glm-5.toml +++ b/providers/venice/models/zai-org-glm-5.toml @@ -1,7 +1,7 @@ base_model = "zhipuai/glm-5" name = "GLM 5" +last_updated = "2026-06-11" structured_output = true -last_updated = "2026-06-10" [[reasoning_options]] type = "effort"