impulse

Grok 3 Mini Fast

Frontier lab
API id xai.grok-3-mini-fast
Input / 1M
$0.60
at Oracle OCI
Output / 1M
$4.00
at Oracle OCI
Context window
131K
tokens
Max output
131K
tokens per reply
Hosts
2
2 listings
Released
-
date not published

Pricing

List prices at Oracle OCI, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.60$4.00

What it costs a month

At Oracle OCI list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$480
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$432
  • Coding agent1,000 requests a day, 40K in / 2K out$960
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$2,400
Use your own numbers

Where to run it

2 hosts serve Grok 3 Mini Fast. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
xai.grok-3-mini-fast
$0.60 / $4.00
grok-3-mini-fast
$0.60 / $4.00

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than Oracle OCI.

Smaller xAI models

  • Grok Build 0.1
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    14% less
  • Grok Code Fast
    xAI · on xAI
    $1.00 / $2.00
    Has every key capability
    14% less

Other frontier labs

  • Gemini 3.5 Flash Lite
    Google · on Google AI Studio
    $0.30 / $2.50
    Has every key capability
    41% less
  • GPT-5.4 Nano
    OpenAI · on OpenAI
    $0.20 / $1.25
    Has every key capability
    68% less
  • Claude Haiku 5.5
    Anthropic · on Anthropic
    $0.10 / $0.50
    Has every key capability
    86% less
  • GPT-6 Luna
    OpenAI · on OpenAI
    $0.10 / $0.50
    Has every key capability
    86% less

Open-weight picks

  • Motif 3
    Independent · on ai&
    $0.50 / $2.00
    Has every key capability
    40% less
  • GLM 5.3
    Zhipu AI · on CLF AI Gateway
    $0.56 / $1.76
    Has every key capability
    41% less
  • Nemotron 3 Ultra 550B A55B
    NVIDIA · on Perplexity
    $0.25 / $2.50
    Has every key capability
    44% less
  • DeepSeek V4 Pro
    DeepSeek · on CLF AI Gateway
    $0.528 / $1.58
    Has every key capability
    45% less

Call it

Using Oracle OCI's API.

Python
from litellm import completion

response = completion(
    model="oci/xai.grok-3-mini-fast",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Grok 3 Mini Fast cost?

On Oracle OCI, Grok 3 Mini Fast costs $0.60 per million input tokens and $4.00 per million output tokens.

Which APIs offer Grok 3 Mini Fast?

Grok 3 Mini Fast runs on 2 APIs: Oracle OCI and Vercel AI Gateway.

What is Grok 3 Mini Fast's context window?

131K tokens, with up to 131K tokens in one reply.

Is Grok 3 Mini Fast being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Grok 3 Mini Fast?

Models that cost less and keep most of what it can do: Grok Build 0.1 on xAI (14% less), Gemini 3.5 Flash Lite on Google AI Studio (41% less), GPT-5.4 Nano on OpenAI (68% less) and Motif 3 on ai& (40% less). Savings are on a mix of 3 input tokens to 1 output token.

What is Grok 3 Mini Fast's API model id?

Use xai.grok-3-mini-fast with Oracle OCI. Other hosts use their own ids: grok-3-mini-fast on Vercel AI Gateway.

Sources

Raw catalog entry for xai.grok-3-mini-fast on Oracle OCI
{
  "input_cost_per_token": 6e-7,
  "litellm_provider": "oci",
  "max_input_tokens": 131072,
  "max_output_tokens": 131072,
  "mode": "chat",
  "output_cost_per_token": 0.000004,
  "source": "https://www.oracle.com/artificial-intelligence/generative-ai/generative-ai-service/pricing",
  "supports_function_calling": true,
  "supports_response_schema": false,
  "supports_native_streaming": true
}