jishie

Qwen3 VL 235B A22B Thinking

novita-ai/qwen/qwen3-vl-235b-a22b-thinking · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: reasoning text image video.

$1.72
Blended $/1M (3:1)
$0.98
Input $/1M
$3.95
Output $/1M
$4.93
1M in + 1M out
—
Cache read $/1M
#4979 of 7,708
Cheapest rank
Provider
NovitaAI (novita-ai)
Kind
text (outputs text)
Context
131,072 tokens
Max output
32,768 tokens
Capabilities
reasoning text image video

Same model, other providers

“Qwen3 VL 235B A22B Thinking” is offered by 9 providers — cheapest-effective first. Kilo Gateway is the cheapest at $1.30 blended.

ProviderInputOutputBlendedContext
Kilo Gateway$0.4$4$1.30131k
OpenRouter$0.4$4$1.30131k
OrcaRouter$0.4$4$1.30131k
Eden AI$0.4$4$1.30131k
NovitaAI (this)$0.98$3.95$1.72131k
Hugging Face$0.98$3.95$1.72131k
Jalapeno Cloud$0.98$3.95$1.72131k
DevPass (LLM Gateway)$0.98$3.95$1.72131k
NanoGPT$0.5$6$1.88131k

Call it

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

Most providers are OpenAI-compatible — point base_url at NovitaAI 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-vl-235b-a22b-thinking","messages":[{"role":"user","content":"hello"}]}'

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

← all NovitaAI models · model index · JSON