Sakana: Sakana Namazu
LiveSakana262K context · Text, Vision, Tools, ReasoningBenchmark price · $0.95 input / $4 output per 1M tokens
Best discount now60.0%offYou pay 40.0% of reference.
Median discount60.0%offAcross 1 live offer.
Realized · 7 days61.4%avgRequest-weighted average.
Requests · 24h531 offer from 1 seller.
Current offers
1 of 2 offers
Availability
Providers
ProviderDiscountPriceLatencyUptimeCacheSold
OpenRouter
59%
$0.38 in
$1.60 out
1.2s
100.0%
24.8%
$0.003
Total
Cumulative offers
Sold
$0.003
Discount trend
Realized · 7 days65.1%
Best, twice dailyMedian 60.0%
Recent fills
10:38100 tokensOpenRouter60.8%
09:50507 tokensOpenRouter60.2%
09:33100 tokensOpenRouter60.8%
09:33100 tokensOpenRouter61.8%
09:25192 tokensOpenRouter59.8%
09:19101 tokensOpenRouter62.1%
08:58101 tokensOpenRouter62.7%
08:38101 tokensOpenRouter62.7%
08:28100 tokensOpenRouter62.4%
08:18101 tokensOpenRouter62.1%
07:58101 tokensOpenRouter60.0%
07:48192 tokensOpenRouter59.9%
07:48509 tokensOpenRouter60.3%
07:37101 tokensOpenRouter62.7%
07:23100 tokensOpenRouter60.8%
06:18100 tokensOpenRouter61.8%
05:13100 tokensOpenRouter60.8%
04:55508 tokensOpenRouter60.5%
04:08100 tokensOpenRouter60.8%
03:47192 tokensOpenRouter60.6%
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 |
|---|---|---|---|---|---|
| OpenRouter | 1.24 s | — | — | 100.0% | 100% |
OpenRouter100% 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
- toolsarrayFunctions the model may call, in the OpenAI format
- tool_choicestring | objectauto, required, none, or one named function
- 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
- web_search_options
Context window 262K tokens · Max output 66K 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="sakana-namazu", messages=[{"role": "user", "content": "Hello!"}] )
SURPLUS_BASE_URL
https://api.surplusintelligence.ai/v1