Models & Pricing | SingularityAPI

Model	Best for	Context window	Max output	Input $/1M	Output $/1M
`deepseek-v4-pro`	Hardest reasoning tasks	1,000,000	384,000	$0.392	$0.783
`deepseek-v4-flash`	Fast, cheap default workhorse	1,000,000	384,000	$0.081	$0.162
`deepseek-v3.2`	Solid general model	128,000	128,000	$0.186	$0.280
`kimi-k2.7-code`	Coding and agentic coding	262,144	262,144	$0.639	$3.150
`kimi-k2.6`	General and long-form	262,144	262,144	$0.581	$2.448
`gpt-5.6-sol`	Frontier flagship	272,000	128,000	$5.00	$30.00
`gpt-5.6-terra`	Frontier, balanced cost	272,000	128,000	$2.50	$15.00
`gpt-5.6-luna`	Frontier, budget	272,000	128,000	$1.00	$6.00

Prices are per million tokens, input and output priced separately.

gpt-5.6-sol, gpt-5.6-terra, and gpt-5.6-luna are the only models that serve /v1/responses, in addition to chat completions. The rest serve chat completions only.

Requests that omit the output-limit field get a per-model default: 4,096 tokens for deepseek-v3.2, 8,192 tokens for every other model listed above.

GET /v1/models is the authoritative live list, including current per-token pricing. Prices on this page are current as of 2026-08-03. See Models & Receipts for the endpoint reference.