jishie

Qwen3 235B A22B Instruct 2507

modelscope/Qwen/Qwen3-235B-A22B-Instruct-2507 · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

free
Blended $/1M (3:1)
free
Input $/1M
free
Output $/1M
free
1M in + 1M out
—
Cache read $/1M
#483 of 7,710
Cheapest rank
Provider
ModelScope (modelscope)
Kind
text (outputs text)
Context
262,144 tokens
Max output
131,072 tokens
Capabilities
tools text

Same model, other providers

“Qwen3 235B A22B Instruct 2507” is offered by 11 providers — cheapest-effective first. This one (ModelScope) is the cheapest.

ProviderInputOutputBlendedContext
ModelScope (this)freefree$0.00262k
OpenRouter$0.0875$0.35$0.15262k
NovitaAI$0.09$0.58$0.21131k
Meganova$0.09$0.6$0.22262k
Merge Gateway$0.1$0.6$0.23131k
submodel$0.2$0.3$0.23262k
Nebius Token Factory$0.2$0.6$0.30262k
Jiekou.AI$0.15$0.8$0.31131k
Vercel AI Gateway$0.22$0.88$0.39262k
Scaleway$0.75$2.25$1.13260k
GreenPT$1.03$3.08$1.54262k

Call it

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

Most providers are OpenAI-compatible — point base_url at ModelScope and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"Qwen/Qwen3-235B-A22B-Instruct-2507","messages":[{"role":"user","content":"hello"}]}'

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

← all ModelScope models · model index · JSON