Available Models

Open-weight LLMs available through the Telnyx Inference API, hosted on Telnyx GPUs and accessible via OpenAI-compatible endpoints.

Open-weight LLMs hosted on Telnyx GPU infrastructure. All chat models are accessible via the Chat Completions API (OpenAI-compatible); embedding models are served on the embeddings endpoints.

For supported Flex, Default, and Priority options, see Service tiers.

Not every model here is available to AI Assistants, and of the assistant models only a subset is verified for voice calls — see Voice AI models.

Chat Models

Model ID	Parameters	Context Length	Best For	Voice AI
zai-org/GLM-5.3-Flash	320B	1M	Efficient multimodal coding and agentic workflows (Recommended)	Not available for assistants
zai-org/GLM-5.3	753.9B	1M	Complex coding and long-horizon agent tasks	Not available for assistants
deepseek-ai/DeepSeek-V4.1-Flash	552B backbone	1M	Low-latency multimodal inference	Not available for assistants
moonshotai/Kimi-K3	2.8T	1M	State-of-the-art open-weight intelligence for coding, reasoning, and multimodal work	Not available for assistants
moonshotai/Kimi-K2.6	1.0T	256K	Voice AI	Verified — default
zai-org/GLM-5.2	753.9B	1M	Coding, reasoning, 1M context window	Verified
MiniMaxAI/MiniMax-M3-MXFP8	428B	1M	Cheapest while maintaining high intelligence	Not available for assistants
deepseek-ai/DeepSeek-V4-Flash-0731	304B	1M	Advanced coding, tool use, and long-horizon agentic workflows	Not available for assistants
Qwen/Qwen3.8-27B	27B	256K	Multimodal coding and visual understanding across documents, diagrams, and video	Not supported

Reasoning (thinking) behavior differs by surface: reasoning models return their chain-of-thought in a separate reasoning_content field on chat completions (see getting started), but reasoning is always disabled on voice calls and cannot be enabled there — see Reasoning on voice calls.

Embedding Models

Model ID	Dimensions	Context Length	Best For
Qwen/Qwen3-Embedding-8B	4096	8,192 tokens	Multilingual and code retrieval; supports custom output dimensions via the dimensions parameter
thenlper/gte-large	1024	512 tokens	Text embeddings
intfloat/multilingual-e5-large	1024	512 tokens	Multilingual text embeddings

All three models are available on the OpenAI-compatible Create embeddings endpoint (POST /v2/ai/openai/embeddings); List embedding models returns the current list programmatically.

When you embed a Telnyx Storage bucket for AI use — via the Embed documents endpoint or the portal’s Embed for AI Use button (see Embeddings) — the embedding_model field accepts thenlper/gte-large and intfloat/multilingual-e5-large only, and defaults to intfloat/multilingual-e5-large. Qwen/Qwen3-Embedding-8B is available on the OpenAI-compatible embeddings endpoint only.

Inputs longer than the model’s context length are rejected with a 400 error on the OpenAI-compatible endpoint.