Inkling
abacus/thinkingmachines/Inkling · family ling · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$5.14
Blended $/1M (3:1)
$3.74
Input $/1M
$9.36
Output $/1M
$13.10
1M in + 1M out
$0.748 −80%
Cache read $/1M
#6583 of 7,708
Cheapest rank
- Provider
- Abacus (
abacus) - Kind
- text (outputs text)
- Context
- 262,144 tokens
- Max output
- 131,072 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 |
| NanoGPT | $1 | $4.05 | $1.76 | 1M |
| Baseten | $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 |
| Abacus (this) | $3.74 | $9.36 | $5.14 | 262k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Abacus 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):