Skip to content

Conversation

@hkd987
Copy link

@hkd987 hkd987 commented Jan 5, 2026

Adds LlamaGate (https://llamagate.dev) as a new provider with:

  • 3 embedding models (Nomic, EmbeddingGemma, Qwen3 Embedding)
  • 8 general purpose models (Llama 3.1/3.2, Mistral, Qwen, etc.)
  • 6 code models (DeepSeek Coder, CodeLlama, Qwen Coder, etc.)
  • 3 reasoning models (DeepSeek R1, OpenThinker)
  • 5 vision models (Qwen VL, LLaVA, olmOCR, UI-TARS, Gemma 3)
  • 1 tool calling model (FunctionGemma)

Provider details:

  • API: OpenAI-compatible (@ai-sdk/openai-compatible)
  • Base URL: https://api.llamagate.dev/v1
  • Auth: Bearer token via LLAMAGATE_API_KEY
  • Pricing: $0.02-$0.55 per 1M tokens
  • All models are open-weights (Apache 2.0, MIT, Llama, Gemma)

hkd987 and others added 2 commits January 5, 2026 18:45
Adds LlamaGate (https://llamagate.dev) as a new provider with:
- 3 embedding models (Nomic, EmbeddingGemma, Qwen3 Embedding)
- 8 general purpose models (Llama 3.1/3.2, Mistral, Qwen, etc.)
- 6 code models (DeepSeek Coder, CodeLlama, Qwen Coder, etc.)
- 3 reasoning models (DeepSeek R1, OpenThinker)
- 5 vision models (Qwen VL, LLaVA, olmOCR, UI-TARS, Gemma 3)
- 1 tool calling model (FunctionGemma)

Provider details:
- API: OpenAI-compatible (@ai-sdk/openai-compatible)
- Base URL: https://api.llamagate.dev/v1
- Auth: Bearer token via LLAMAGATE_API_KEY
- Pricing: $0.02-$0.55 per 1M tokens
- All models are open-weights (Apache 2.0, MIT, Llama, Gemma)
- Add output cost (0.00) for embedding models
- Add output limit (embedding dimension) for each model
- Change modalities.output from "embedding" to "text" (valid schema value)

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant