qwen2.5-7b-instruct in the catalog and in GET /v1/models, sent as model; its current version is qwen2.5-7b-instruct-a09a3545. Its page on the site, with its rate history: Qwen2.5 7B Instruct .
Fig. 1, sheet 06 Model and task guides Field Value Type and task language, task chatInputs text Outputs text License and usage conditions apache-2.0
Field Type and task
Value language, task chat
Field License and usage conditions
Value apache-2.0 Limit Value context_tokens32,768 max_output_tokens32,768
Limit context_tokens
Value 32,768
Limit max_output_tokens
Value 32,768 Pool Lanes Precision Certified pool Shared Q4_K_M (int4) Community pool Shared Q4_K_M (int4)
Pool Certified pool
Lanes Shared
Precision Q4_K_M (int4)
Pool Community pool
Lanes Shared
Precision Q4_K_M (int4) On demand, in US dollars per million tokens
Pool Input Cached input Output Certified pool $0.098 Billed as input $0.196 Community pool $0.098 Billed as input $0.196
Pool Certified pool
Input $0.098
Cached input Billed as input
Output $0.196
Pool Community pool
Input $0.098
Cached input Billed as input
Output $0.196
Sheet 06 of 20
Updated 2026-11-17