jishie

Qwen3 Coder Next

merge-gateway/qwen/qwen3-coder-next · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.

$0.31
Blended $/1M (3:1)
$0.15
Input $/1M
$0.8
Output $/1M
$0.95
1M in + 1M out
$0.075 −50%
Cache read $/1M
#2276 of 7,712
Cheapest rank
Provider
Merge Gateway (merge-gateway)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
text

Same model, other providers

“Qwen3 Coder Next” is offered by 14 providers — cheapest-effective first. Alibaba Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Coding Planfreefree$0.00262k
Alibaba Coding Plan (China)freefree$0.00262k
DevPass (LLM Gateway)$0.108$0.675$0.25262k
OpenRouter$0.12$0.8$0.29262k
Merge Gateway (this)$0.15$0.8$0.31262k
Cortecs$0.167$0.891$0.35256k
NanoGPT$0.2$1.5$0.53262k
NovitaAI$0.2$1.5$0.53262k
Ofox$0.2$1.5$0.53262k
Kilo Gateway$0.3$1.5$0.60262k
Eden AI$0.3$1.5$0.60262k
Vercel AI Gateway$0.5$1.2$0.68256k
Amazon Bedrock$0.5$1.2$0.68262k

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":"qwen/qwen3-coder-next","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