Fugu Ultra
aimlapi/sakana/fugu-ultra · family fugu · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$15.47
Blended $/1M (3:1)
$6.88
Input $/1M
$41.26
Output $/1M
$48.14
1M in + 1M out
$0.6877 −90%
Cache read $/1M
#7956 of 8,276
Cheapest rank
- Provider
- AI/ML API (
aimlapi) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Fugu Ultra” is offered by 11 providers — cheapest-effective first. NanoGPT is the cheapest at $11.25 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $5 | $30 | $11.25 | 1M |
| Kilo Gateway | $5 | $30 | $11.25 | 1M |
| OpenRouter | $5 | $30 | $11.25 | 1M |
| LLMTR | $5 | $30 | $11.25 | 1M |
| Vercel AI Gateway | $5 | $30 | $11.25 | 1M |
| Sakana AI | $5 | $30 | $11.25 | 1M |
| Merge Gateway | $5 | $30 | $11.25 | 1M |
| Pioneer | $5 | $30 | $11.25 | 1M |
| Requesty | $5 | $30 | $11.25 | 1M |
| DevPass (LLM Gateway) | $5 | $30 | $11.25 | 1M |
| AI/ML API (this) | $6.88 | $41.26 | $15.47 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at AI/ML API and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"sakana/fugu-ultra","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):