Models
Use the model ID in the model field of your request.
| Model ID | Name | Made by | Good for | Context |
|---|---|---|---|---|
glm-5.2 | Analyst (GLM-5.2) | Z.ai, China | Complex reasoning, analysis and agents | To be confirmed |
kimi-k2.6 | Agent (Kimi K2.6) | Moonshot AI, China | Long tasks and working with tools | 256K tokens (about 380 pages) |
gpt-oss-120b | Generalist (GPT-OSS 120B) | OpenAI, United States | General business work, United States origin | 128K tokens (about 190 pages) |
mistral-medium-3.5 | Writer (Mistral Medium 3.5) | Mistral AI, France | Long documents, writing and many languages, European origin | 256K tokens (about 380 pages) |
qwen3-coder-30b | Coder (Qwen3 Coder 30B) | Alibaba, China | Fast, low-cost coding at high volume | 256K tokens (about 380 pages) |
gemma-4-26b | Assistant (Gemma 4 26B) | Google, United States | Everyday tasks at low cost | 256K tokens (about 380 pages) |
Embedding models, for /v1/embeddings:
| Model ID | Name | Made by | Good for | Context |
|---|---|---|---|---|
qwen3-embedding-8b | Librarian (Qwen3 Embedding 8B) | Alibaba, China | Search across your documents, in over 100 languages | 32K tokens per input |
bge-m3 | Indexer (BGE-M3) | BAAI, China | Fast, low-cost search over large collections | 8K tokens per input |
Context is the most text a model can work with in one request, counting both what you send and its reply. 1,000 tokens is roughly 750 words.
List the models available to your key
bash
curl https://api.continuumlabs.ai/v1/modelsjson
{"object": "list", "data": [{"id": "glm-5.2", "object": "model", "owned_by": "continuum"}]}Choosing a model
- For hard analysis and agents, start with the largest models.
- For high-volume, simple work such as classification and extraction, a smaller model is faster and cheaper. Test it on your own examples first.
- For a particular country of origin, filter by origin on the models page. Some organisations prefer or require models from particular countries.
Try any model on your own prompt in the playground.
Prices
Prices per million tokens are on the pricing page. You pay for the tokens you send and the tokens the model writes, at the rates for the model you choose.