grok/grok-4.3

grok/grok-4.3
FlagshipFeatured
VisionToolsJSONReasoning
by grok

grok/grok-4.3: flagship 1M-context, text+image model from grok on OrcaRouter at provider direct pricing

ctx1M tokens
Inputtext + image
Outputtext
p50 TTFT1.85 s
INPUT$1.25/ 1M tokens
OUTPUT$2.50/ 1M tokens
p50 TTFT1.85 s7d
p95 TTFT8.13 s7d
TRAFFIC5.2Mtokens / 7d

grok/grok-4.3 is a flagship model from grok, offered on OrcaRouter at the provider's direct pricing with no markup. It supports a context window of 1 million tokens – significantly larger than many…

What is grok/grok-4.3 and who is it for?

How does the 1M token context window work?

What input modalities does grok-4.3 support?

Code samples

Call from any SDK

OpenAI-compatible — keep the SDK you already use

  • OpenAI SDKhttps://api.orcarouter.ai/v1
from openai import OpenAI

client = OpenAI(
    base_url="https://api.orcarouter.ai/v1",
    api_key="$ORCAROUTER_API_KEY",
)

response = client.chat.completions.create(
    model="grok/grok-4.3",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Supported parameters

  • include_reasoning
  • logprobs
  • max_completion_tokens
  • max_tokens
  • n
  • parallel_tool_calls
  • reasoning
  • reasoning_effort
  • response_format
  • search_parameters
  • seed
  • stream
  • stream_options
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_logprobs
  • top_p
  • user
  • web_search_options

Pricing

Input / 1M tokens$1.25
Output / 1M tokens$2.50
Cache read / 1M$0.200
CurrencyUSD

Cost calculator

Tokens / month10MM
Input share70%%
Estimated / month $16.25 · With prompt caching $12.58

Estimate based on list price

Token & cost estimator

Input tokens: 20Cost per request: $0.001275

Estimate only — actual token counts depend on the provider's tokenizer.

Performance

p50 TTFT
1.85 s
Output speed
119 tok/s
p95 TTFT
8.13 s
Error rate
0%

Public benchmarks

Source: Design Arena

How it compares

grok/grok-4.3Grok 4.5
Input $/M$1.25$2.00
Output $/M$2.50$6.00
Context1.0M500K
Quality10/109/10
Compare side-by-sideCompare side-by-side

FAQ

What is the cost of using grok/grok-4.3 on OrcaRouter?
The cost is $1.25 per million input tokens and $2.50 per million output tokens, billed at the provider's rate with zero markup. There are no extra fees.
What is the context window size of grok-4.3?
The context window is 1,000,000 tokens (1 million). This includes both input and output tokens.
What are the main strengths of grok-4.3?
Its main strengths are the 1M token context window and support for image input. It is a flagship model intended for high-complexity tasks requiring large context or visual understanding.
How does grok-4.3 compare to other models on OrcaRouter?
It offers one of the largest context windows and supports images. Without specific benchmark data, direct quality comparisons are not possible. Users should test with their own tasks.
How does OrcaRouter handle data privacy for grok-4.3?
OrcaRouter acts as a proxy; data is sent to grok's servers for inference. Data handling is governed by grok's privacy policy. OrcaRouter does not store prompts or outputs beyond what is necessary for billing and logging. Contact OrcaRouter for details.
Can I call grok-4.3 using an OpenAI-compatible API?
Yes. Use base URL https://api.orcarouter.ai/v1 with model ID 'grok/grok-4.3'. The API is fully OpenAI-compatible for chat completions.
Does grok-4.3 support streaming?
Yes, the API supports streaming via the 'stream' parameter. Set stream: true to receive tokens as they are generated.
What parameter should I use for image input?
Include an image_url in the content array. For example: {"type":"image_url","image_url":{"url":"..."}}. The model will process the image as part of the input context.
Are there any discounts or caching options?
The catalog does not mention discounts or caching. Pricing is per-token pay-as-you-go. Contact OrcaRouter for any unpublished offers.
What is the maximum output length for grok-4.3?
The maximum output length is limited by the context window. You can set max_tokens up to 1,000,000 minus the input token count. Practical limits depend on provider settings.

Embed this badge

grok/grok-4.3$1.25/M in1852ms p50via OrcaRouter
HTML <a href="https://www.orcarouter.ai/models/grok/grok-4.3" target="_blank"> <img src="https://www.orcarouter.ai/embed/grok/grok-4.3.svg" alt="grok/grok-4.3 on OrcaRouter" /> </a>
Markdown [![grok/grok-4.3](https://www.orcarouter.ai/embed/grok/grok-4.3.svg)](https://www.orcarouter.ai/models/grok/grok-4.3)

Model card as data

GET /api/public/models/grok/grok-4.3Open
Machine-readable:/llms.txt/llms-full.txt