Models

Use GET /models to discover the exact model IDs accepted by the public API. Only models returned by this endpoint can be used in /chat/completions.

GET/models

Returns the curated model list available through GLM 5.

curl https://glm5.app/api/v1/models \
  -H "Authorization: Bearer $GLM5_API_KEY"

{
  "object": "list",
  "data": [
    {
      "id": "glm-5.2",
      "object": "model",
      "created": 0,
      "owned_by": "glm5"
    }
  ]
}

Model List

Model	Best for	Tools	Input	Output
`glm-5.2`	Coding, reasoning, agents, long-form work	Yes	$2.50 / 1M	$7.50 / 1M
`glm-5`	General chat and lower-cost GLM workloads	Yes	$1.50 / 1M	$5.00 / 1M
`kimi-k3`	Premium alternative reasoning workloads	Yes	$15.00 / 1M	$75.00 / 1M
`kimi-k2`	Cost-efficient alternative general chat	Yes	$1.50 / 1M	$6.00 / 1M
`deepseek-r1`	Text reasoning without function tools	No	$1.75 / 1M	$6.50 / 1M
`deepseek-v4-pro`	DeepSeek flagship reasoning and tool workflows	Yes	$2.25 / 1M	$4.50 / 1M
`deepseek-v4-flash`	Fast, low-cost DeepSeek V4 chat	Yes	$0.70 / 1M	$1.40 / 1M

Prices are shown in USD per one million tokens. API calls spend the same GLM 5 credits used by Chat. See Billing for reservation, settlement, and refund behavior.

GET /models does not publish synthetic context_length or max_completion_tokens values. GLM 5 does not impose one global token window; the selected upstream provider applies its current model-specific limits.

Model IDs

OpenRouter model IDs often include provider namespaces and routing choices. GLM 5 uses stable public IDs instead. Send one of these exact values:

Model ID	Tools	Limits	Notes
`glm-5.2`	Yes	Provider-managed	Recommended default for new integrations.
`glm-5`	Yes	Provider-managed	Lower-cost GLM model for general work.
`kimi-k3`	Yes	Provider-managed	Premium alternative reasoning/chat model.
`kimi-k2`	Yes	Provider-managed	Cost-efficient alternative chat model.
`deepseek-r1`	No	Provider-managed	Reasoning text model without tool support.
`deepseek-v4-pro`	Yes	Provider-managed	DeepSeek V4 flagship reasoning/chat model.
`deepseek-v4-flash`	Yes	Provider-managed	Fast, low-cost DeepSeek V4 chat model.

Provider-prefixed names such as z-ai/glm-5.2, moonshotai/kimi-k2, deepseek/deepseek-r1, or deepseek/deepseek-v4-flash are internal upstream IDs and are rejected by the public API with 404 model_not_found.

GLM-5.2

glm-5.2 is the recommended default for new API users. It is the best fit for coding, structured reasoning, agent workflows, function calling, and longer technical conversations.

{
  "model": "glm-5.2",
  "messages": [
    {
      "role": "user",
      "content": "Review this deployment plan for missing rollback steps."
    }
  ],
  "max_completion_tokens": 1200
}

Use it when quality matters more than using the lowest-cost model.

GLM-5

glm-5 is a lower-cost GLM option for general chat, summarization, structured answers, and lighter application workflows. It supports the same text endpoint, streaming, and function-calling shape as glm-5.2.

{
  "model": "glm-5",
  "messages": [
    {
      "role": "user",
      "content": "Turn these notes into a concise customer support reply."
    }
  ],
  "max_completion_tokens": 700
}

Kimi K3

kimi-k3 is a premium alternative model exposed through the same Chat Completions API. Use it when you want to compare behavior against GLM models for reasoning-heavy or high-value text workflows.

{
  "model": "kimi-k3",
  "messages": [
    {
      "role": "user",
      "content": "Compare these two architecture options and choose one."
    }
  ],
  "max_completion_tokens": 1500
}

Kimi K2

kimi-k2 is a cost-efficient alternative for general chat, summaries, extraction, and tool-capable workflows.

{
  "model": "kimi-k2",
  "messages": [
    {
      "role": "user",
      "content": "Summarize the trade-offs in this architecture."
    }
  ],
  "max_completion_tokens": 800
}

DeepSeek R1

deepseek-r1 is available for reasoning-oriented text generation. It does not support function calling in the GLM 5 public API. If you send tools with this model, the API returns 400 unsupported_parameter.

{
  "model": "deepseek-r1",
  "messages": [
    {
      "role": "user",
      "content": "Reason through this production incident timeline."
    }
  ],
  "max_completion_tokens": 1200
}

DeepSeek V4 Pro

deepseek-v4-pro exposes DeepSeek V4 Pro through the GLM 5 public API. Use it for higher-value reasoning, coding, extraction, and tool-capable text workflows.

{
  "model": "deepseek-v4-pro",
  "messages": [
    {
      "role": "user",
      "content": "Find the risky assumptions in this migration plan."
    }
  ],
  "max_completion_tokens": 1200
}

DeepSeek V4 Flash

deepseek-v4-flash is the cheaper DeepSeek V4 option for fast everyday chat, summaries, and tool-capable application workflows.

{
  "model": "deepseek-v4-flash",
  "messages": [
    {
      "role": "user",
      "content": "Summarize these customer notes into action items."
    }
  ],
  "max_completion_tokens": 800
}

Model Not Found

Unknown model IDs return:

{
  "error": {
    "message": "The requested model was not found.",
    "type": "invalid_request_error",
    "code": "model_not_found",
    "param": null
  }
}

The HTTP status is 404.

On this page