Cogito v2.1 671B
Open weightsCogito v2.1 671B is a language model from Deepcogito with a 160K-token context window. Provider list price is $1.25 per million input tokens and $1.25 per million output; on Allocate you pay $1.34 and $1.34 with the 7% transaction fee. The weights are open, so you can fine-tune it and own the result.
Pricing
Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.
Price against its peers
Provider list prices per M tokens, Cogito v2.1 671B against its nearest language peers by price.
What a real workload costs
Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $1.25 + 350 × $1.25 = $1,938 a month. Billed on Allocate it is $2,073 with the 7% transaction fee.
Cogito v2.1 671B is an open-weights model; the catalog does not list its license, so check the lab’s model card before commercial fine-tuning.
Example usage
Point a route at deepcogito/cogito-v2-1-671b and the endpoint never changes; swap the model behind it whenever you want.
curl https://api.allocate.network/v1/chat/completions \ -H "Authorization: Bearer $ALLOCATE_KEY" \ -d '{ "model": "deepcogito/cogito-v2-1-671b", "messages": [{"role": "user", "content": "Summarise the attached contract."}] }'
Common questions
How much does Cogito v2.1 671B cost per million tokens?
Provider list price is $1.25 per million input tokens and $1.25 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $1.34 in and $1.34 out.
What context window does Cogito v2.1 671B have?
163,840 tokens (160K). At roughly 0.75 words per token, that is about 123k words of English text per request.
Can I fine-tune Cogito v2.1 671B?
Yes. Cogito v2.1 671B is an open-weights model; check the lab’s model card for the exact license terms. Read the license terms before fine-tuning for commercial use. On Allocate the trained weights stay inside your boundary and belong to you.
How do I call Cogito v2.1 671B on Allocate?
Send deepcogito/cogito-v2-1-671b in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.