Models

All models are available on every plan. Rate limits (RPM and TPM) are set at the key level, not per model.

List models

Query the live model list:

curl https://api.cheapestinference.com/v1/models \
  -H "Authorization: Bearer YOUR_API_KEY"

Each model object includes an id, owned_by, and a type field ("chat" or "embedding") so you can filter programmatically:

{
  "id": "deepseek-ai/DeepSeek-V3.2",
  "object": "model",
  "created": 1677610602,
  "owned_by": "cheapestinference",
  "type": "chat"
}

To get details about a specific model:

curl https://api.cheapestinference.com/v1/models/deepseek-chat \
  -H "Authorization: Bearer YOUR_API_KEY"

Available models

Qwen

Model ID	Type
Qwen/Qwen3.5-397B-A17B	chat
Qwen/Qwen3.5-122B-A10B	chat
Qwen/Qwen3.5-35B-A3B	chat
Qwen/Qwen3-235B-A22B-Instruct-2507	chat
Qwen/Qwen3-Next-80B-A3B-Instruct	chat
Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo	chat
Qwen/Qwen3-Coder-480B-A35B-Instruct	chat
Qwen/Qwen3-235B-A22B-Thinking-2507	chat
Qwen/Qwen3-VL-235B-A22B-Instruct	chat
Qwen/Qwen3-VL-30B-A3B-Instruct	chat

DeepSeek

Model ID	Type
deepseek-ai/DeepSeek-V3.2	chat
deepseek-ai/DeepSeek-R1-0528	chat
deepseek-ai/DeepSeek-R1-0528-Turbo	chat
deepseek-ai/DeepSeek-R1-Distill-Llama-70B	chat
deepseek-ai/DeepSeek-OCR	chat

Meta

Model ID	Type
meta-llama/Llama-4-Scout-17B-16E-Instruct	chat
meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8	chat
meta-llama/Llama-Guard-4-12B	chat

Moonshot

Model ID	Type
moonshotai/Kimi-K2.5	chat
moonshotai/Kimi-K2.5-Turbo	chat
moonshotai/Kimi-K2-Thinking	chat

MiniMax

Model ID	Type
MiniMaxAI/MiniMax-M2.5	chat

Zhipu (GLM)

Model ID	Type
zai-org/GLM-5	chat
zai-org/GLM-4.7-Flash	chat

Embeddings

Model ID	Type
Qwen/Qwen3-Embedding-8B	embedding
Qwen/Qwen3-Embedding-0.6B-batch	embedding
BAAI/bge-m3	embedding
intfloat/multilingual-e5-large-instruct	embedding
nvidia/llama-nemotron-embed-vl-1b-v2	embedding
google/embeddinggemma-300m	embedding

Note

The model list above is a snapshot. The authoritative list comes from GET /v1/models. Models may be added or updated without notice. You can also browse models at cheapestinference.com/models.

Using models

Specify the model ID in your request:

# OpenAI SDK — any model
response = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3.2",  # or "Qwen/Qwen3.5-397B-A17B", etc.
    messages=[{"role": "user", "content": "Hello"}]
)

All models work through the OpenAI endpoint (/v1/chat/completions) and the Anthropic-compatible endpoint (/anthropic/v1/messages). The API handles format translation automatically.