xAI: Grok 4 Fast
x-ai/grok-4-fast
Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens) Prompts and completions may be used by xAI or OpenRouter to improve future models.
Byx-aiInput typeOutput type
Recent activity on Grok 4 Fast
Tokens processed per day
Thoughput
(tokens/s)
ProvidersMin (tokens/s)Max (tokens/s)Avg (tokens/s)
OpenAIChatCompletionAdapter0.374.731.04
First Token Latency
(ms)
ProvidersMin (ms)Max (ms)Avg (ms)
OpenAIChatCompletionAdapter121014531295.00
Providers for Grok 4 Fast
ZenMux Provider to the best providers that are able to handle your prompt size and parameters, with fallbacks to maximize uptime.
OpenAIChatCompletionAdapter
Latency
1.30
s
Throughput
0.42
tps
Uptime
100.00
%
Recent uptime
Oct 10,2025 - 3 PM100.00%
Price
Tiered pricing
0 <= Input < 128k
Input
$ 0.2
/ M tokens
Output
$ 0.5
/ M tokens
Cache read
$ 0.05
/ M tokens
Cache write 5m
-
Cache write 1h
-
Cache write
-
Web search
$ 0.025
/ request
Model limitation
Context
2.00M
Max output
30.00K
Supported Parameters
max_completion_tokens
temperature
top_p
frequency_penalty
-
presence_penalty
seed
logit_bias
-
logprobs
top_logprobs
response_format
stop
-
tools
tool_choice
-
parallel_tool_calls
Model Protocol Compatibility
openai
anthropic
-
Data policy
Prompt training
false
Prompt Logging
Zero retention
Moderation
Responsibility of developer
Sample code and API for Grok 4 Fast
ZenMux normalizes requests and responses across providers for you.
OpenAI-PythonPythonTypeScriptOpenAI-TypeScriptcURL
python
from openai import OpenAI

client = OpenAI(
  base_url="https://zenmux.ai/api/v1",
  api_key="<ZenMux_API_KEY>",
)

completion = client.chat.completions.create(
  model="x-ai/grok-4-fast",
  messages=[
    {
      "role": "user",
      "content": [
        {
          "type": "text",
          "text": "What is in this image?"
        }
      ]
    }
  ]
)
print(completion.choices[0].message.content)