OpenAI: gpt-oss-120b

Cerebras

cerebras/gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Context

131K

Input /1M

$0.35

Output /1M

$0.75

Latency (TTFT)

335ms

Pricing

Per 1M tokens, in USD

Input$0.35

Output$0.75

Cache read$0.35

Specs

text intext out

TokenizerGPT

Max output tokens117,964

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$0.35

Cheaper than 57% of routable models

Output$0.75

Cheaper than 81% of routable models

Benchmarks

Intelligence12.3

Coding30.4

Agentic6.2

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": "cerebras/gpt-oss-120b",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'

Models

OpenAI: gpt-oss-120b

Cerebras

cerebras/gpt-oss-120b

gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...

Context

131K

Input /1M

$0.35

Output /1M

$0.75

Latency (TTFT)

335ms

Pricing

Per 1M tokens, in USD

Input$0.35

Output$0.75

Cache read$0.35

Specs

text intext out

TokenizerGPT

Max output tokens117,964

Supported parameters

frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_atop_ktop_logprobstop_p

Where it ranks on price

Against 157 routable models

Input$0.35

Cheaper than 57% of routable models

Output$0.75

Cheaper than 81% of routable models

Benchmarks

Intelligence12.3

Coding30.4

Agentic6.2

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": "cerebras/gpt-oss-120b",
    "messages": [{ "role": "user", "content": "Say hi in five words." }]
  }'