inference-providers

OLMo 3 32B Think

by allenai · family olmo

Facts

Release date2025-11-20
Retired date
Knowledge cutoff
Context (max)65,536
Max output
Modalitiestext → text
Aliasesolmo-3-32b-think
Open weightsyes (allenai/Olmo-3-32B-Think)
DescriptionFully open (Apache 2.0, all data + code + logs) 32B dense long-CoT reasoning model; 64K context.

Unknown values are shown as —.

Offerings

ProviderWire IDVariantEndpointProtocolStatusPrice (USD / Mtok)Reasoning
OpenCode Zenolmo-3-32b-thinkchat-completionsopenai-chatretiredalways_on · default on · mandatory · returns reasoning_content
OpenRouterallenai/olmo-3-32b-thinkchat-completionsopenai-chatretired0.15 / 0.50effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Reasoning controls

OpenCode Zen· olmo-3-32b-think· chat-completions always_on

always_on · default on · mandatory · returns reasoning_content

OpenRouter· allenai/olmo-3-32b-think· chat-completions effort

reasoning.effort lowmediumhigh●xhighmax

effort · default on · mandatory · returns reasoning_content · round-trips reasoning_content

Example requests

OpenCode Zen · openai-chat · olmo-3-32b-think

curl 'https://opencode.ai/zen/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "olmo-3-32b-think",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ]
}'
Python (requests)
import requests

resp = requests.post(
    "https://opencode.ai/zen/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "olmo-3-32b-think",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ]
    },
)
print(resp.json())
TypeScript (fetch)
const resp = await fetch("https://opencode.ai/zen/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "olmo-3-32b-think",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ]
  }),
})
console.log(await resp.json())

OpenRouter · openai-chat · allenai/olmo-3-32b-think

curl 'https://openrouter.ai/api/v1/chat/completions' \
  -H 'Authorization: Bearer <YOUR_API_KEY>' \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "allenai/olmo-3-32b-think",
  "messages": [
    {
      "role": "user",
      "content": "Tell me about the weather."
    }
  ],
  "reasoning": {
    "effort": "high"
  }
}'
Python (requests)
import requests

resp = requests.post(
    "https://openrouter.ai/api/v1/chat/completions",
    headers={
      "Authorization": "Bearer <YOUR_API_KEY>",
      "Content-Type": "application/json"
    },
    json={
      "model": "allenai/olmo-3-32b-think",
      "messages": [
        {
          "role": "user",
          "content": "Tell me about the weather."
        }
      ],
      "reasoning": {
        "effort": "high"
      }
    },
)
print(resp.json())
TypeScript (fetch)
const resp = await fetch("https://openrouter.ai/api/v1/chat/completions", {
  method: "POST",
  headers: {
    "Authorization": "Bearer <YOUR_API_KEY>",
    "Content-Type": "application/json"
  },
  body: JSON.stringify({
    "model": "allenai/olmo-3-32b-think",
    "messages": [
      {
        "role": "user",
        "content": "Tell me about the weather."
      }
    ],
    "reasoning": {
      "effort": "high"
    }
  }),
})
console.log(await resp.json())
  • ⚠ Responses include reasoning_content artifacts — pass them back unmodified on subsequent turns (dropping them triggers 400s or quality loss).