Qwen: Qwen3 Coder Next

Qwen

qwen/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Context

262K

Input /1M

$0.30

Output /1M

$1.50

Latency (TTFT)

670ms

Pricing

Per 1M tokens, in USD

Input$0.30

Output$1.50

Specs

text intext out

TokenizerQwen

Max output tokens235,929

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$0.30

Cheaper than 59% of routable models

Output$1.50

Cheaper than 64% of routable models

Benchmarks

Intelligence10.1

Coding36.2

Agentic3.6

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-coder-next",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Qwen: Qwen3 Coder Next

Qwen

qwen/qwen3-coder-next

Qwen3-Coder-Next is an open-weight causal language model optimized for coding agents and local development workflows. It uses a sparse MoE design with 80B total parameters and only 3B activated per...

Context

262K

Input /1M

$0.30

Output /1M

$1.50

Latency (TTFT)

670ms

Pricing

Per 1M tokens, in USD

Input$0.30

Output$1.50

Specs

text intext out

TokenizerQwen

Max output tokens235,929

Supported parameters

frequency_penaltylogit_biaslogprobsmax_tokenspresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$0.30

Cheaper than 59% of routable models

Output$1.50

Cheaper than 64% of routable models

Benchmarks

Intelligence10.1

Coding36.2

Agentic3.6

Composite scores (0–100) from Artificial Analysis, via OpenRouter's model catalog.

Call this model

Swap in your Mizan key — the request/response bodies are OpenAI chat-completion shaped.

cURL

curl https://api.app-mizan.com/v1/chat/completions \
  -H "Authorization: Bearer mizan_rt_..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "qwen/qwen3-coder-next",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'