jishie

Qwen3 32B

abacus/Qwen/Qwen3-32B · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$0.14
Blended $/1M (3:1)
$0.09
Input $/1M
$0.29
Output $/1M
$0.38
1M in + 1M out
—
Cache read $/1M
#1230 of 7,708
Cheapest rank
Provider
Abacus (abacus)
Kind
text (outputs text)
Context
131,072 tokens
Max output
8,192 tokens
Capabilities
tools reasoning text

Same model, other providers

“Qwen3 32B” is offered by 16 providers — cheapest-effective first. Deep Infra is the cheapest at $0.13 blended.

ProviderInputOutputBlendedContext
Deep Infra$0.08$0.28$0.1341k
Kilo Gateway$0.08$0.28$0.1341k
OpenRouter$0.08$0.28$0.13131k
Abacus (this)$0.09$0.29$0.14131k
NovitaAI$0.1$0.45$0.1941k
Jiekou.AI$0.1$0.45$0.1941k
Merge Gateway$0.15$0.6$0.26131k
Amazon Bedrock$0.15$0.6$0.2633k
Cortecs$0.179$0.697$0.3116k
DigitalOcean$0.25$0.55$0.3333k
Hugging Face$0.29$0.59$0.36131k
Helicone$0.29$0.59$0.36131k
DevPass (LLM Gateway)$0.36$0.87$0.4941k

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":"Qwen/Qwen3-32B","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Abacus models · model index · JSON