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"

This returns the full list of available models. The response follows the OpenAI /v1/models format.

To get details about a specific model:

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

Available models

Meta

Model ID	Name
llama-3.3-70b	Llama 3.3 70B
llama-3.1-8b	Llama 3.1 8B
llama-3.2-3b	Llama 3.2 3B

DeepSeek

Model ID	Name
deepseek-chat	DeepSeek V3.2
deepseek-reasoner	DeepSeek R1

Qwen

Model ID	Name
qwen3-235b	Qwen3 235B
qwen3-30b	Qwen3 30B
qwen3-coder	Qwen3 Coder

Google (Gemma)

Model ID	Name
gemma-3-27b	Gemma 3 27B
gemma-3-12b	Gemma 3 12B
gemma-3-4b	Gemma 3 4B

Moonshot

Model ID	Name
kimi-2.5	Kimi 2.5

Embeddings

Model ID	Name
BAAI/bge-large-en-v1.5	BGE Large
BAAI/bge-base-en-v1.5	BGE Base

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-chat",  # or "llama-3.3-70b", "kimi-2.5", 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.