Skip to content

chore(sync): review Deep Infra model catalog notices #3068

Description

@github-actions

Updates model TOMLs for the deepinfra sync target.

Provider Status Created Updated Deleted
Deep Infra unchanged 0 0 0

Notices

Deep Infra

  • 138 Deep Infra models were not created because they lacked provider-agnostic metadata to inherit (no models/ entry) and the API does not supply the required curated fields, or because they are already deprecated.
  • Skipped remote IDs: meta-llama/Llama-2-13b-chat-hf, ByteDance/Seed-2.0-code, Gryphe/MythoMax-L2-13b, cognitivecomputations/dolphin-2.6-mixtral-8x7b, Sao10K/L3-8B-Lunaris-v1, meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo, microsoft/WizardLM-2-8x22B, mistralai/Mistral-Small-3.1-24B-Instruct-2503, allenai/olmOCR-7B-1025, MiniMaxAI/MiniMax-M2.7-Turbo, meta-llama/Llama-3.2-1B-Instruct, openai/gpt-oss-120b-Turbo, mistralai/Mistral-7B-Instruct-v0.2, Qwen/Qwen3-VL-8B-Thinking, Sao10K/L3-70B-Euryale-v2.1, Qwen/Qwen3-30B-A3B, allenai/olmOCR-2, moonshotai/Kimi-K2-Instruct-0905, meta-llama/Llama-Guard-3-8B, deepseek-ai/DeepSeek-R1-Distill-Qwen-32B, nvidia/NVIDIA-Nemotron-Nano-12B-v2-VL, moonshotai/Kimi-K2.5-Turbo, microsoft/Phi-4-multimodal-instruct, mistralai/Mistral-7B-Instruct-v0.3, allenai/olmOCR-7B-0725-FP8, Qwen/Qwen3-VL-4B-Instruct, Qwen/Qwen3-235B-A22B-Instruct-2507, allenai/olmOCR-2-7B-1025, meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo, Qwen/Qwen3-VL-4B-Thinking, ByteDance/Seed-2.0-pro, meta-llama/Llama-3.2-90B-Vision-Instruct, deepseek-ai/DeepSeek-R1, nvidia/Nemotron-4-340B-Instruct, PaddlePaddle/PaddleOCR-VL-0.9B, mistralai/Mistral-Nemo-Instruct-2407, deepseek-ai/DeepSeek-V3.2-Exp, google/gemma-1.1-7b-it, mistralai/Mistral-Small-24B-Instruct-2501, deepseek-ai/DeepSeek-V3-0324-Turbo, deepseek-ai/DeepSeek-V3, microsoft/phi-4, nvidia/Llama-3.1-Nemotron-70B-Instruct, google/gemma-2-9b-it, meta-llama/Meta-Llama-3.1-70B-Instruct, deepseek-ai/DeepSeek-V3-0324, Qwen/Qwen3-14B, google/gemma-3-4b-it, stepfun-ai/Step-3.5-Flash, Qwen/Qwen2.5-VL-32B-Instruct, mistralai/Mixtral-8x22B-Instruct-v0.1, Qwen/Qwen3-VL-8B-Instruct, nvidia/Nemotron-Content-Safety-3.5, google/codegemma-7b-it, deepseek-ai/DeepSeek-R1-0528-Turbo, deepinfra/airoboros-70b, Qwen/Qwen3-VL-30B-A3B-Thinking, zai-org/GLM-4.5-Air, mistralai/Devstral-Small-2507, meta-llama/Llama-2-70b-chat-hf, microsoft/Phi-3-medium-4k-instruct, Qwen/Qwen2.5-Coder-7B, Qwen/Qwen3.5-4B, Qwen/Qwen3-235B-A22B-Thinking-2507, google/gemma-3-27b-it, mistralai/Mistral-Small-3.2-24B-Instruct-2506, meta-llama/Meta-Llama-3.1-8B-Instruct, allenai/Olmo-3.1-32B-Instruct, Qwen/Qwen3-VL-235B-A22B-Instruct, google/gemma-2-27b-it, nvidia/NVIDIA-Nemotron-3-Super-120B-A12B, meta-llama/Llama-Guard-4-12B, cognitivecomputations/dolphin-2.9.1-llama-3-70b, Qwen/Qwen2-72B-Instruct, openchat/openchat-3.6-8b, KoboldAI/LLaMA2-13B-Tiefighter, Qwen/Qwen2-7B-Instruct, MiniMaxAI/MiniMax-M2.1, microsoft/WizardLM-2-7B, ByteDance/Seed-2.0-mini, meta-llama/Meta-Llama-3.1-405B-Instruct, zai-org/GLM-4.5, Qwen/Qwen3-VL-30B-A3B-Instruct, deepseek-ai/DeepSeek-R1-Turbo, mistralai/Mistral-7B-Instruct-v0.1, nvidia/NVIDIA-Nemotron-Nano-9B-v2, ByteDance/Seed-1.8, meta-llama/Llama-3.2-3B-Instruct, zai-org/GLM-4.6V, deepseek-ai/DeepSeek-V3.1, lizpreciatior/lzlv_70b_fp16_hf, openbmb/MiniCPM-Llama3-V-2_5, NovaSky-AI/Sky-T1-32B-Preview, meta-llama/Meta-Llama-3-70B-Instruct, google/gemma-3-12b-it, Qwen/Qwen2.5-72B-Instruct, Qwen/QwQ-32B-Preview, deepseek-ai/DeepSeek-OCR, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16, Sao10K/L3.1-70B-Euryale-v2.2, meta-llama/Llama-3.3-70B-Instruct, NousResearch/Hermes-3-Llama-3.1-70B, Qwen/Qwen3-235B-A22B, mistralai/Devstral-Small-2505, NousResearch/Hermes-3-Llama-3.1-405B, Phind/Phind-CodeLlama-34B-v2, Qwen/Qwen3.5-2B, Qwen/Qwen3-Max-Thinking, meta-llama/Meta-Llama-3-8B-Instruct, Gryphe/MythoMax-L2-13b-turbo, Qwen/Qwen3-VL-235B-A22B-Thinking, mattshumer/Reflection-Llama-3.1-70B, google/gemma-4-31B-it-turbo, stepfun-ai/Step-3.7-Flash, Sao10K/L3-8B-Lunaris-v1-Turbo, allenai/olmOCR-7B-0825, nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B, openchat/openchat_3.5, moonshotai/Kimi-K2-Instruct, Qwen/Qwen2.5-7B-Instruct, deepseek-ai/DeepSeek-Prover-V2-671B, meta-llama/Llama-4-Maverick-17B-128E-Instruct-Turbo, MiniMaxAI/MiniMax-M2, Qwen/QwQ-32B, Austism/chronos-hermes-13b-v2, deepseek-ai/DeepSeek-V3.1-Terminus, mistralai/Mixtral-8x7B-Instruct-v0.1, meta-llama/Llama-3.2-11B-Vision-Instruct, Qwen/Qwen3.5-0.8B, deepseek-ai/DeepSeek-R1-Distill-Llama-70B, Sao10K/L3.3-70B-Euryale-v2.3, Qwen/Qwen3-Coder-480B-A35B-Instruct, bigcode/starcoder2-15b-instruct-v0.1, Qwen/QVQ-72B-Preview, microsoft/phi-4-reasoning-plus, Qwen/Qwen2.5-Coder-32B-Instruct, moonshotai/Kimi-K2-Thinking, Qwen/Qwen3-Coder-30B-A3B-Instruct
  • Add a models/<provider>/<model>.toml entry (or a full provider TOML) to include them in the next sync.

This PR was created automatically by the daily model sync workflow.

Metadata

Metadata

Assignees

No one assigned

    Labels

    automationAutomated model catalog syncmodel-syncAutomated model catalog syncprovider:deepinfraAutomated model catalog sync

    Type

    No type

    Fields

    No fields configured for issues without a type.

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions