jishie

Inkling

merge-gateway/thinkingmachines/inkling · family ling · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$1.76
Blended $/1M (3:1)
$1
Input $/1M
$4.05
Output $/1M
$5.05
1M in + 1M out
$0.17 −83%
Cache read $/1M
#5008 of 7,708
Cheapest rank
Provider
Merge Gateway (merge-gateway)
Kind
text (outputs text)
Context
1,048,000 tokens
Max output
32,000 tokens
Capabilities
tools reasoning text

Same model, other providers

“Inkling” is offered by 21 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Nvidiafreefree$0.001M
Deep Infra$0.95$4.05$1.72524k
Kilo Gateway$0.95$4.05$1.72524k
DevPass (LLM Gateway)$0.95$4.05$1.72524k
Merge Gateway (this)$1$4.05$1.761M
NanoGPT$1$4.05$1.761M
Baseten$1$4.05$1.761M
OpenRouter$1$4.05$1.761M
Hugging Face$1$4.05$1.761M
Vercel AI Gateway$1$4.05$1.76256k
Fireworks AI$1$4.05$1.761M
Neon$1$4.05$1.761M
Together AI$1$4.05$1.76524k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Merge Gateway 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):

← all Merge Gateway models · model index · JSON