LiteLLMModels

GLM 5.1 Nvfp4 Mtp API Pricing

As of October 10, 2026, GLM 5.1 Nvfp4 Mtp costs $1.40 per 1M input tokens and $4.40 per 1M output tokens on Tensormesh, with cache reads at $0 per 1M tokens. It has a 202,752-token context window and returns up to 202,752 tokens per response.

By Z.aiModel ID tensormesh/lukealonso/GLM-5.1-NVFP4-MTPPrices updated Checked
Input
$1.40 / 1M tokens
Output
$4.40 / 1M tokens
Cache read
$0 / 1M tokens
Context window
202,752 tokens
Max output
202,752 tokens
Providers
1
Added to LiteLLM
June 2026

GLM 5.1 Nvfp4 Mtp pricing by provider

1 listing across 1 provider. Token prices are in US dollars per 1M tokens. The highlighted row is the price quoted above.

ProviderModel name in LiteLLMInputOutputCache readContext
Tensormeshtensormesh/lukealonso/GLM-5.1-NVFP4-MTP$1.40$4.40$0198K

What GLM 5.1 Nvfp4 Mtp costs in practice

1,000 requests with 2,000 input and 500 output tokens each

Tensormesh$5.00

100 long-document requests with 100,000 input and 2,000 output tokens each

Tensormesh$14.88

GLM 5.1 Nvfp4 Mtp features

Use GLM 5.1 Nvfp4 Mtp with LiteLLM

Call GLM 5.1 Nvfp4 Mtp through the LiteLLM Python SDK, or put it behind the LiteLLM proxy and send OpenAI-format requests to /v1/chat/completions. LiteLLM tracks the cost of every request at these prices.

Python SDK
from litellm import completion

response = completion(
    model="tensormesh/lukealonso/GLM-5.1-NVFP4-MTP",
    messages=[{"role": "user", "content": "Hello!"}],
)
Proxy config.yaml
model_list:
  - model_name: glm-5.1-nvfp4-mtp
    litellm_params:
      model: tensormesh/lukealonso/GLM-5.1-NVFP4-MTP
      # credentials: see the provider's LiteLLM docs page
Call the proxy
curl http://0.0.0.0:4000/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-1234" \
  -d '{
    "model": "glm-5.1-nvfp4-mtp",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

GLM 5.1 Nvfp4 Mtp FAQ

How much does GLM 5.1 Nvfp4 Mtp cost?

GLM 5.1 Nvfp4 Mtp costs $1.40 per 1M input tokens and $4.40 per 1M output tokens on Tensormesh, with cache reads at $0 per 1M tokens.

What is the context window of GLM 5.1 Nvfp4 Mtp?

GLM 5.1 Nvfp4 Mtp has a 202,752-token context window and returns up to 202,752 tokens per response.

Which providers offer GLM 5.1 Nvfp4 Mtp?

GLM 5.1 Nvfp4 Mtp is available from Tensormesh through LiteLLM, using the model name tensormesh/lukealonso/GLM-5.1-NVFP4-MTP.

How do I call GLM 5.1 Nvfp4 Mtp with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="tensormesh/lukealonso/GLM-5.1-NVFP4-MTP", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

What features does GLM 5.1 Nvfp4 Mtp support?

GLM 5.1 Nvfp4 Mtp supports function calling, structured output, reasoning and prompt caching.

When did LiteLLM add GLM 5.1 Nvfp4 Mtp?

GLM 5.1 Nvfp4 Mtp was added to LiteLLM's model price file in June 2026.

Sources

Prices come from LiteLLM's open-source model_prices_and_context_window.json, which LiteLLM uses to calculate the cost of every request. Provider pricing pages:

LiteLLM docs: Tensormesh.

Provider pages: Tensormesh.