Grok: Code Fast 1 API

xAI's Grok: Code Fast 1, through an OpenAI-compatible API. Providers quote it on an open exchange, and each request goes to the offer with the lowest estimated charge that meets your rules.

Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send grok-code-fast-1 as the model.
Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.

Facts

Model name: grok-code-fast-1
Maker: xAI
Context window: 256K tokens
Input price: $0.200 per million tokens
Output price: $1.498 per million tokens
Providers: 1 independent provider
Regions: us

Providers

Architect: us, $0.200 input and $1.498 output per million tokens, $0.020 cache read per million tokens, 256K tokens of context

Scores

HLE: 8.0, #169 of 273
GPQA: 72.7, #145 of 250
AA-LCR: 53.0, #150 of 237
Terminal-Bench Hard: 17.4, #102 of 166
LiveCodeBench: 65.7, #34 of 130
AIME 2025: 43.3, #54 of 100
MMLU-Pro: 79.3, #50 of 133
τ²-Bench: 75.7, #68 of 169
IFBench: 41.4, #111 of 178

Scores: Artificial Analysis (https://artificialanalysis.ai/)

Request

curl https://router.inference.ai.exchange/v1/chat/completions \
  -H "Authorization: Bearer $LIQUID_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-code-fast-1",
    "messages": [{"role":"user","content":"Say hello."}]
  }'

Questions

What is Grok: Code Fast 1?: Served by intent-router: each job goes to the cheapest healthy upstream for this model.
How much does Grok: Code Fast 1 cost?: Offers now ask $0.200 per million input tokens and $1.498 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
What is the context length of Grok: Code Fast 1?: The largest offer takes 256,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
What can Grok: Code Fast 1 do?: Its providers list Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
What inputs and outputs does Grok: Code Fast 1 support?: Text → Text.
Which providers serve Grok: Code Fast 1?: 1 independent provider quote it now, with 1 offer. The table above ranks them by the cost of a typical job.
How do I call Grok: Code Fast 1?: Send "grok-code-fast-1" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
When was Grok: Code Fast 1 listed?: The exchange first listed it on 10/8/2026. This is not its release date.