Inkling
baseten/thinkingmachines/inkling · family ling · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$1.76
Blended $/1M (3:1)
$1
Input $/1M
$4.05
Output $/1M
$5.05
1M in + 1M out
—
Cache read $/1M
#5002 of 7,708
Cheapest rank
- Provider
- Baseten (
baseten) - Kind
- text (outputs text)
- Context
- 1,048,576 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Inkling” is offered by 21 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 1M |
| Deep Infra | $0.95 | $4.05 | $1.72 | 524k |
| Kilo Gateway | $0.95 | $4.05 | $1.72 | 524k |
| DevPass (LLM Gateway) | $0.95 | $4.05 | $1.72 | 524k |
| Baseten (this) | $1 | $4.05 | $1.76 | 1M |
| NanoGPT | $1 | $4.05 | $1.76 | 1M |
| OpenRouter | $1 | $4.05 | $1.76 | 1M |
| Hugging Face | $1 | $4.05 | $1.76 | 1M |
| Vercel AI Gateway | $1 | $4.05 | $1.76 | 256k |
| Fireworks AI | $1 | $4.05 | $1.76 | 1M |
| Neon | $1 | $4.05 | $1.76 | 1M |
| Merge Gateway | $1 | $4.05 | $1.76 | 1M |
| Together AI | $1 | $4.05 | $1.76 | 524k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Baseten and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"thinkingmachines/inkling","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):