Qwen: Qwen3 235B A22B

Qwen

qwen/qwen3-235b-a22b

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Context

131K

Input /1M

$0.455

Output /1M

$1.82

Latency (TTFT)

422ms

Pricing

Per 1M tokens, in USD

Input$0.455

Output$1.82

Specs

text intext out

TokenizerQwen3

Max output tokens8,192

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Where it ranks on price

Against 157 routable models

Input$0.455

Cheaper than 51% of routable models

Output$1.82

Cheaper than 60% of routable models

Benchmarks

No third-party benchmark data available for this model yet.

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/qwen3-235b-a22b",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Qwen: Qwen3 235B A22B

Qwen

qwen/qwen3-235b-a22b

Qwen3-235B-A22B is a 235B parameter mixture-of-experts (MoE) model developed by Qwen, activating 22B parameters per forward pass. It supports seamless switching between a "thinking" mode for complex reasoning, math, and...

Context

131K

Input /1M

$0.455

Output /1M

$1.82

Latency (TTFT)

422ms

Pricing

Per 1M tokens, in USD

Input$0.455

Output$1.82

Specs

text intext out

TokenizerQwen3

Max output tokens8,192

Supported parameters

frequency_penaltyinclude_reasoningmax_tokenspresence_penaltyreasoningresponse_formatseedstoptemperaturetool_choicetoolstop_ktop_p

Where it ranks on price

Against 157 routable models

Input$0.455

Cheaper than 51% of routable models

Output$1.82

Cheaper than 60% of routable models

Benchmarks

No third-party benchmark data available for this model yet.

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/qwen3-235b-a22b",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'