xAI · in Borg
xAIGrok 4.3
GrokGrok 4.3 is the less expensive, fast-response option among these Grok generations, positioned by xAI for dependable tool calls and instruction following rather than exclusively deep technical work.
Reasoning1,000,000 tokenstext, image
Included in Borg
Download Borg Borg for BusinessAt a glance
| Specification | Value |
|---|---|
| Provider | xAI |
| Family | Grok |
| Context window | 1,000,000 tokens Vendor source |
| Input modalities | text, image |
| Output modalities | text |
| Reasoning | Yes |
| Open weights | No |
| Borg lane ids | grok-4.3, x-ai/grok-4.3 |
| Versions in Borg | Grok 4.3 · Grok 4.5 · Grok 4.6 · Grok 4.7 |
| Median time to first token (gateway proxy) on Borg | 1457 ms |
| Median tokens per second (end to end) on Borg | 31.9 output tokens per second |
Not published by the vendor: release date, thinking modes, knowledge cutoff, fusion roles.
What Grok 4.3 is good for
Grok 4.3 is the less expensive, fast-response option among these Grok generations, positioned by xAI for dependable tool calls and instruction following rather than exclusively deep technical work. Unlike the later 4.5, 4.6 and 4.7 models, it can be run with reasoning disabled, or with adjustable reasoning effort when a request calls for more deliberation. Its large input window makes it useful for reading lengthy records or following multi-step conversations; image input also allows questions about screenshots and diagrams. Pick it for workflows where response cost and consistent structured output matter more than the newest frontier coding performance. Borg includes this model in its subscription: choose its lane for a predictable model choice, or let Borg Fusion route suitable requests to it.
- high-volume instruction-following tasks
- tool calls with structured outputs
- long document triage
- image-assisted question answering
How Borg uses it
Grok 4.3 is available as a subscription catalog lane in Borg. The catalog does not publish which Fusion profiles route to this model, so no routing role is claimed here. You can pick it directly by setting the OpenAI-compatible gateway model field to a listed lane id. Check the current catalog for availability before building a workflow around a lane.
OpenAImodel: "grok-4.3"Measured on Borg
| Metric | Median | 95th percentile | Samples |
|---|---|---|---|
| Time to first token (gateway proxy) | 1457 ms | 8349 ms | 2452 |
| Tokens per second (end to end) | 31.9 output tokens per second | 82.9 output tokens per second | 64469 |
Time to first token (gateway proxy)
Output tokens per second (whole turn)
- Time to first token (gateway proxy): time until the first streamed response event reaches the gateway; our closest available measure of time to first token
- Tokens per second (end to end): tokens per second, end to end: provider-reported output tokens divided by the whole turn's elapsed time, including queueing and reasoning; not a streaming per-token rate
Completion speed covers the whole turn including queueing and reasoning time; it is not a streaming tokens-per-second figure.
Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 87770 requests. Minimum 100 samples per published request metric.
Pricing
Included in Borg subscription. Vendor API list price: $1.25 input / $2.5 output per 1M tokens. Vendor price source.
Global rates for prompts below 200,000 input tokens. At 200,000 input tokens or more, all tokens use long-context rates: $2.5 input / $5 output / $0.4 cached input per 1M tokens. US regional inference costs 1.1× the global rate. Vendor pricing terms
Compare subscription and API pricing · Cost Savings Calculator
FAQ
What is Grok 4.3?
Grok 4.3 is listed in Borg's subscription catalog as grok-4.3. Grok 4.3 is the less expensive, fast-response option among these Grok generations, positioned by xAI for dependable tool calls and instruction following rather than exclusively deep technical work.
Is Grok 4.3 in Borg?
Yes. Grok 4.3 is listed in Borg's subscription catalog under the lane grok-4.3. You can choose the lane directly, or explore the available Fusion profiles. Availability and model details can change; check the current catalog before deployment.
What context window does Grok 4.3 have?
The published context window is 1,000,000 tokens. Consult the cited sources for details and current limits. Vendor source
Is Grok 4.3 good for coding?
No vendor-published coding evaluation is listed here. Its listed uses include high-volume instruction-following tasks, tool calls with structured outputs, long document triage, image-assisted question answering. Try the lane for your own tasks, and compare the output with your requirements before choosing a default.
How fast is Grok 4.3 on Borg?
Measured on Borg: SearchAtlas AI Gateway production request logs. 30-day window ending 2026-10-08; 87770 requests. Minimum 100 samples per published request metric.
How much does Grok 4.3 cost on Borg vs the API?
This model is included in the Borg subscription. The vendor API list prices appear below with a source link. See the pricing explainer and cost savings calculator to compare billing approaches.
Sources
Related
Other versions of Grok: Grok 4.5 · Grok 4.6 · Grok 4.7
Other xAI models: Grok 4.5 · Grok 4.6 · Grok 4.7
Models sharing a Fusion role: Not published