Qwen: Qwen3.8 2.4T A95B

Qwen

qwen/qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Context

1.048576M

Input /1M

$2.00

Output /1M

$6.00

Latency (TTFT)

1,633ms

Pricing

Per 1M tokens, in USD

Input$2.00

Output$6.00

Cache read$0.25

Cache write (5m)$2.50

Specs

text intext out

TokenizerQwen

Max output tokens262,144

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$2.00

Cheaper than 17% of routable models

Output$6.00

Cheaper than 24% of routable models

Benchmarks

Intelligence40.0

Coding71.9

Agentic50.4

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/qwen3.8-2.4t-a95b",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

Qwen: Qwen3.8 2.4T A95B

Qwen

qwen/qwen3.8-2.4t-a95b

Qwen3.8 2.4T A95B is an open-weight sparse mixture-of-experts model from Qwen and the open-weight variant of [Qwen3.8 Max](/qwen/qwen3.8-max), with 95 billion active parameters out of 2.4 trillion total. It is...

Context

1.048576M

Input /1M

$2.00

Output /1M

$6.00

Latency (TTFT)

1,633ms

Pricing

Per 1M tokens, in USD

Input$2.00

Output$6.00

Cache read$0.25

Cache write (5m)$2.50

Specs

text intext out

TokenizerQwen

Max output tokens262,144

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$2.00

Cheaper than 17% of routable models

Output$6.00

Cheaper than 24% of routable models

Benchmarks

Intelligence40.0

Coding71.9

Agentic50.4

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/qwen3.8-2.4t-a95b",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'