Skip to content
API Pricing

10,896 prices on 4,759 listings · last collected 16 min ago · 442 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on eight platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.

Showing 1–21 of 21

“Cheapest” is the lowest exact price in this unit for your search. Rows can differ in resolution, length or quality — read the label, or add it to the search (e.g. “1080”).

Per million input tokens10

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyMeta: Llama 3.1 8B Instructvia DeepInfra · fp8$0.02/M inCheapestprompt: 0.00000002 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyMeta: Llama 3.2 1B Instruct$0.027/M inprompt: 0.000000027 / token (endpoint cloudflare)
OpenRouterThird-partySao10K: Llama 3 8B Lunarisvia Parasail · bf16$0.04/M inprompt: 0.00000004 / token (endpoint parasail/bf16)
OpenRouterThird-partyMeta: Llama 3.2 3B Instructvia Parasail · bf16$0.05/M inprompt: 0.00000005 / token (endpoint parasail/bf16)
OpenRouterThird-partyMeta: Llama 3.3 70B InstructTurbovia DeepInfra$0.1/M inprompt: 0.0000001 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyMeta: Llama 4 Scoutvia DeepInfra · fp8$0.1/M inprompt: 0.0000001 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyMeta: Llama Guard 4 12Bvia DeepInfra · bf16$0.18/M inprompt: 0.00000018 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyMeta: Llama 4 Maverickvia Parasail · fp8$0.35/M inprompt: 0.00000035 / token (endpoint parasail/fp8)
OpenRouterThird-partyMeta: Llama 3.1 70B Instruct$0.72/M inprompt: 0.00000072 / token (endpoint amazon-bedrock)
OpenRouterThird-partySao10K: Llama 3.1 Euryale 70B v2.2$0.85/M inprompt: 0.00000085 / token (endpoint deepinfra/fp8)

Per million output tokens10

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyMeta: Llama 3.1 8B Instructvia DeepInfra · fp8$0.04/M outCheapestcompletion: 0.00000004 / token (endpoint deepinfra/fp8)
OpenRouterThird-partySao10K: Llama 3 8B Lunarisvia Parasail · bf16$0.05/M outcompletion: 0.00000005 / token (endpoint parasail/bf16)
OpenRouterThird-partyMeta: Llama Guard 4 12Bvia DeepInfra · bf16$0.18/M outcompletion: 0.00000018 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyMeta: Llama 3.2 1B Instruct$0.201/M outcompletion: 0.000000201 / token (endpoint cloudflare)
OpenRouterThird-partyMeta: Llama 4 Scoutvia DeepInfra · fp8$0.3/M outcompletion: 0.0000003 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyMeta: Llama 3.3 70B InstructTurbovia DeepInfra$0.32/M outcompletion: 0.00000032 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyMeta: Llama 3.2 3B Instructvia Parasail · bf16$0.33/M outcompletion: 0.00000033 / token (endpoint parasail/bf16)
OpenRouterThird-partyMeta: Llama 3.1 70B Instruct$0.72/M outcompletion: 0.00000072 / token (endpoint amazon-bedrock)
OpenRouterThird-partySao10K: Llama 3.1 Euryale 70B v2.2$0.85/M outcompletion: 0.00000085 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyMeta: Llama 4 Maverickvia Parasail · fp8$1/M outcompletion: 0.000001 / token (endpoint parasail/fp8)

Per million cached input tokens (read)1

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyMeta: Llama 4 Maverickvia Parasail · fp8$0.17/M cache readCheapestinput_cache_read: 0.00000017 / token (endpoint parasail/fp8)