SpaceXAI: Grok 4.6
x-ai/grok-4-6Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by [Grok 4.7](/x-ai/grok-4.7).
Modalities
In / out per 1M$2.00 / $6.00
Context488K
ReleasedAug 12, 2026
Providers
6 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $2.00 | $6.00 | $0.50 | 3.13s | 54 tps | 100% | |
| $2.00 | $6.00 | $0.50 | 4.16s | 51 tps | 100% | |
| $2.20 | $6.60 | $0.55 | 2.99s | 52 tps | 100% | |
 Amazon Bedrockus-west-2 | $2.20 | $6.60 | $0.55 | 4.98s | 56 tps | 22.32% |
| $4.00 | $12 | $1.00 | 4.29s | 57 tps | — | |
| $4.00 | $12 | $1.00 | 1.63s | 48 tps | — |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Grok 4.6 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Grok 4.6 costs pay-as-you-go elsewhere, not what you pay here.
Input
$2.00
per 1M tokens
Output
$6.00
per 1M tokens
Cache read
$0.50
per 1M cached tokens
Included in every pass
Grok 4.6 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s100.0s200.0s300.0s400.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
SpaceXAI SpaceXAI Amazon Bedrock (us-west-2) SpaceXAI (us)
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
SpaceXAI SpaceXAI Amazon Bedrock (us-west-2) SpaceXAI (us)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 98.9%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.72%
100% 97% 93% 90%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Grok 4.6, by tokens this week.
Activity
900.7B tokens processed market-wide in the last month.
020.0B40.0B60.0B80.0B
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens
FAQ
Which model id do I use for Grok 4.6?
x-ai/grok-4.6. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Grok 4.6 hold?
500,000 tokens per request, of which up to 450,000 can be the response.
What can it accept and return?
Input: text, image, file. Output: text.
What does Grok 4.6 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $2.00 per 1M input tokens and $6.00 per 1M output tokens.
Who built Grok 4.6?
SpaceXAI, in the Grok family.
Explore
Other models your pass can call.
