Grok Build 0.1
LivexAI256K context · Text, ToolsBenchmark price · $1 input / $2 output per 1M tokens
Best discount now25.7%offYou pay 74.3% of reference.
Median discount0.0%offAcross 26 live offers.
Realized · 7 days35.0%avgRequest-weighted average.
Requests · 24h20726 offers from 20 sellers.
Current offers
26 of 63 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
Venice AI
25%
$0.74 in
$1.49 out
1.2s
98.8%
52.9%
$0.044
Venice AI
25%
$0.74 in
$1.49 out
1.2s
98.8%
52.9%
$0.003
Mordiem
24%
$0.75 in
$1.50 out
-
97.0%
60.7%
$0.028
Venice AI
21%
$0.79 in
$1.58 out
1.2s
98.8%
52.9%
-
Venice AI
19%
$0.80 in
$1.60 out
1.2s
98.8%
52.9%
-
Venice AI
19%
$0.80 in
$1.60 out
1.2s
98.8%
52.9%
-
Mordiem
15%
$0.85 in
$1.70 out
-
97.0%
60.7%
-
Mordiem
9%
$0.90 in
$1.80 out
-
97.0%
60.7%
-
Venice AI
9%
$0.90 in
$1.80 out
1.2s
98.8%
52.9%
-
Mordiem
9%
$0.90 in
$1.80 out
-
97.0%
60.7%
-
Total
Cumulative offers
Sold
$0.075
Discount trend
Realized · 7 days55.0%−5.4 pts vs last week
Best, twice dailyMedian 0.0%
Recent fills
17:2014 tokensVenice AI26.3%
17:0515 tokensVenice AI23.8%
17:00621 tokensVenice AI25.6%
16:5021 tokensVenice AI24.2%
16:42389 tokensVenice AI25.8%
16:421,366 tokensVenice AI25.7%
16:3515 tokensVenice AI23.8%
16:34328 tokensVenice AI25.6%
16:1914 tokensMordiem42.1%
16:06355 tokensMordiem40.2%
16:06301 tokensMordiem40.1%
16:0515 tokensMordiem42.9%
15:49307 tokensMordiem40.2%
15:42378 tokensMordiem40.3%
15:421,245 tokensMordiem40.0%
15:3514 tokensMordiem42.1%
15:29399 tokensMordiem40.3%
15:1915 tokensMordiem42.9%
15:0515 tokensMordiem42.9%
15:001,079 tokensMordiem40.0%
Times in UTCSettled on Base in USDC.
Performance by provider route · 24h
Measured on Surplus traffic| Route | p50 latency | p95 latency | Throughput | Success rate | ShareShare of traffic |
|---|---|---|---|---|---|
| Venice AI direct | 1.67 s | 10.11 s | 54 tok/s | 98.8% | 84% |
| Mordiem | 2.25 s | - | - | 97.0% | 16% |
Venice AI direct84% of traffic
98.8% success
Mordiem16% of traffic
97.0% success
Use this modelChange your base URL.
Change your base URL.
Keep your code.
Any OpenAI-compatible client works. Add /min30 to the path to only buy at 30% off or better.
Read the quickstart ↗Parameters this model acceptsPOST /v1/chat/completions
- modelstringThis model’s id
- messagesarrayThe conversation, as role and content pairs
- streambooleanSend the answer as server-sent events
- max_tokensintegerMost output tokens to generate
- temperaturenumberSampling temperature
- top_pnumberNucleus sampling
- stopstring | arrayStop sequences
- seedintegerDeterministic sampling
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
- response_formatobjectJSON mode or a JSON schema for structured output
- structured_outputsbooleanAccepts a JSON schema in response_format
- frequency_penaltynumberPenalises tokens by how often they appeared
- presence_penaltynumberPenalises tokens that appeared at all
Context window 256K tokens · Max output 33K tokensOthers are passed through; most providers ignore what they don’t support. Parameter compatibility ↗
from openai import OpenAI client = OpenAI( api_key="inf_your_key_here", base_url="$SURPLUS_BASE_URL" ) response = client.chat.completions.create( model="grok-build-0-1", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1