Claude Fable 5.2
LiveAnthropic1M context · Text, Vision, Tools, ReasoningBenchmark price · $8 input / $40 output per 1M tokens
Best discount now27.0%offYou pay 73.0% of reference.
Median discount14.3%offAcross 9 live offers.
Realized · 7 days21.1%avgRequest-weighted average.
Requests · 24h649 offers from 7 sellers.
Current offers
9 of 12 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
OpenRouter
27%
$5.84 in
$29.20 out
-
-
-
-
Venice AI
27%
$5.84 in
$29.20 out
3.0s
100.0%
36.8%
-
Venice AI
27%
$5.84 in
$29.20 out
3.0s
100.0%
36.8%
-
Venice AI
27%
$5.84 in
$29.20 out
3.0s
100.0%
36.8%
-
Venice AI
14%
$6.86 in
$34.29 out
3.0s
100.0%
36.8%
-
Venice AI
14%
$6.86 in
$34.30 out
3.0s
100.0%
36.8%
-
Venice AI
10%
$7.13 in
$35.64 out
3.0s
100.0%
36.8%
-
Uncensored AI
10%
$7.20 in
$36.00 out
-
-
-
$7
OpenRouter
0%
$8.00 in
$40.00 out
-
-
-
-
Total
Cumulative offers
Sold
$7
Discount trend
Realized · 7 days41.3%
Best, twice dailyMedian 14.3%
Recent fills
01:13232,193 tokensUncensored AI10.0%
01:12229,452 tokensUncensored AI10.0%
01:12223,244 tokensVenice AI27.0%
01:11221,648 tokensVenice AI27.0%
01:0426 tokensVenice AI27.1%
01:0349 tokensVenice AI27.0%
00:5038 tokensVenice AI27.0%
00:436,345 tokensVenice AI27.0%
00:436,351 tokensVenice AI27.0%
00:4327,279 tokensVenice AI27.0%
00:4327,279 tokensVenice AI27.0%
00:4226 tokensVenice AI27.0%
00:4226 tokensVenice AI27.0%
00:4226 tokensVenice AI27.0%
00:4226 tokensVenice AI27.0%
00:4226 tokensVenice AI27.0%
00:4298,475 tokensVenice AI27.0%
00:4229 tokensVenice AI27.1%
00:42426 tokensVenice AI27.0%
00:42426 tokensVenice AI27.0%
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 | 4.11 s | - | 73 tok/s | 100.0% | 100% |
Venice AI direct100% of traffic
100.0% 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
- max_completion_tokensintegerSame as max_tokens
- stopstring | arrayStop sequences
- 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
- reasoning_effortstringHow hard to think, as a string such as "high"
- reasoningobjectReasoning options as an object, such as {"effort": "high"}
- include_reasoningbooleanStripped before the request reaches the provider
- verbosity
Context window 1M tokens · Max output 128K 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="claude-fable-5.2", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1