10,634 prices on 4,757 listings · last collected 26 min ago · 399 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.
Version
All 49Llama 4 Maverick 5Llama 4 Scout 4Llama Guard 4 12B 4Llama 3.3 70B Instruct 2Llama 3.2 1B Instruct 2Llama 3.2 3B Instruct 2Llama 3.1 70B Instruct 2AionLabs Aion-RP 1.0 (8B) 2Llama 3.1 8B Instruct 2llama-3-70b 2llama-3-70b-instruct 2llama-3-8b 2llama-3-8b-instruct 2llama-2-13b 2llama-2-13b-chat 2llama-2-70b 2llama-2-70b-chat 2llama-2-7b 2llama-2-7b-chat 2No version named 4
Showing 1–49 of 49
“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 tokens24
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | Meta: Llama 3.1 8B Instructvia DeepInfra · fp8 | $0.02/M inCheapest | prompt: 0.00000002 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Meta: Llama 3.2 1B Instruct | $0.027/M in | prompt: 0.000000027 / token (endpoint cloudflare) | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.04/M in | prompt: 0.00000004 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Meta: Llama 3.2 3B Instructvia Parasail · bf16 | $0.05/M in | prompt: 0.00000005 / token (endpoint parasail/bf16) | |
| ReplicatePlatform-hosted | meta/llama-2-7b | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b-chat | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b | $0.05/M in | $0.05 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b-instruct | $0.05/M in | $0.05 per million input tokens | |
| OpenRouterThird-party | Meta: Llama 3.3 70B InstructTurbovia DeepInfra | $0.1/M in | prompt: 0.0000001 / token (endpoint deepinfra/turbo) | |
| OpenRouterThird-party | Meta: Llama 4 Scoutvia DeepInfra · fp8 | $0.1/M in | prompt: 0.0000001 / token (endpoint deepinfra/fp8) | |
| ReplicatePlatform-hosted | meta/llama-2-13b | $0.1/M in | $0.10 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-13b-chat | $0.1/M in | $0.10 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-4-scout-instruct | $0.17/M in | $0.17 per million input tokens | |
| OpenRouterThird-party | Meta: Llama Guard 4 12Bvia DeepInfra · bf16 | $0.18/M in | prompt: 0.00000018 / token (endpoint deepinfra/bf16) | |
| ReplicatePlatform-hosted | meta/llama-guard-4-12b | $0.2/M in | $0.20 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-4-maverick-instruct | $0.25/M in | $0.25 per million input tokens | |
| OpenRouterThird-party | Meta: Llama 4 Maverickvia Parasail · fp8 | $0.35/M in | prompt: 0.00000035 / token (endpoint parasail/fp8) | |
| ReplicatePlatform-hosted | meta/llama-2-70b | $0.65/M in | $0.65 per million input tokens | |
| ReplicatePlatform-hosted | meta/llama-2-70b-chat | $0.65/M in | $0.65 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b | $0.65/M in | $0.65 per million input tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b-instruct | $0.65/M in | $0.65 per million input tokens | |
| OpenRouterThird-party | Meta: Llama 3.1 70B Instruct | $0.72/M in | prompt: 0.00000072 / token (endpoint amazon-bedrock) | |
| OpenRouterOfficial | AionLabs: Aion-RP 1.0 (8B) | $0.8/M in | prompt: 0.0000008 / token (endpoint aion-labs) | |
| OpenRouterThird-party | Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85/M in | prompt: 0.00000085 / token (endpoint deepinfra/fp8) |
Per million output tokens24
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | Meta: Llama 3.1 8B Instructvia DeepInfra · fp8 | $0.04/M outCheapest | completion: 0.00000004 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Sao10K: Llama 3 8B Lunarisvia Parasail · bf16 | $0.05/M out | completion: 0.00000005 / token (endpoint parasail/bf16) | |
| OpenRouterThird-party | Meta: Llama Guard 4 12Bvia DeepInfra · bf16 | $0.18/M out | completion: 0.00000018 / token (endpoint deepinfra/bf16) | |
| ReplicatePlatform-hosted | meta/llama-guard-4-12b | $0.2/M out | $0.20 per million output tokens | |
| OpenRouterThird-party | Meta: Llama 3.2 1B Instruct | $0.201/M out | completion: 0.000000201 / token (endpoint cloudflare) | |
| ReplicatePlatform-hosted | meta/llama-2-7b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-2-7b-chat | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b | $0.25/M out | $0.25 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-8b-instruct | $0.25/M out | $0.25 per million output tokens | |
| OpenRouterThird-party | Meta: Llama 4 Scoutvia DeepInfra · fp8 | $0.3/M out | completion: 0.0000003 / token (endpoint deepinfra/fp8) | |
| OpenRouterThird-party | Meta: Llama 3.3 70B InstructTurbovia DeepInfra | $0.32/M out | completion: 0.00000032 / token (endpoint deepinfra/turbo) | |
| OpenRouterThird-party | Meta: Llama 3.2 3B Instructvia Parasail · bf16 | $0.33/M out | completion: 0.00000033 / token (endpoint parasail/bf16) | |
| ReplicatePlatform-hosted | meta/llama-2-13b | $0.5/M out | $0.50 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-2-13b-chat | $0.5/M out | $0.50 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-4-scout-instruct | $0.65/M out | $0.65 per million output tokens | |
| OpenRouterThird-party | Meta: Llama 3.1 70B Instruct | $0.72/M out | completion: 0.00000072 / token (endpoint amazon-bedrock) | |
| OpenRouterThird-party | Sao10K: Llama 3.1 Euryale 70B v2.2 | $0.85/M out | completion: 0.00000085 / token (endpoint deepinfra/fp8) | |
| ReplicatePlatform-hosted | meta/llama-4-maverick-instruct | $0.95/M out | $0.95 per million output tokens | |
| OpenRouterThird-party | Meta: Llama 4 Maverickvia Parasail · fp8 | $1/M out | completion: 0.000001 / token (endpoint parasail/fp8) | |
| OpenRouterOfficial | AionLabs: Aion-RP 1.0 (8B) | $1.6/M out | completion: 0.0000016 / token (endpoint aion-labs) | |
| ReplicatePlatform-hosted | meta/llama-2-70b | $2.75/M out | $2.75 per million output tokens | |
| ReplicatePlatform-hosted | meta/llama-2-70b-chat | $2.75/M out | $2.75 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b | $2.75/M out | $2.75 per million output tokens | |
| ReplicatePlatform-hosted | meta/meta-llama-3-70b-instruct | $2.75/M out | $2.75 per million output tokens |
Per million cached input tokens (read)1
| Platform | Model · what it covers | USD | Platform’s own wording | Since |
|---|---|---|---|---|
| OpenRouterThird-party | Meta: Llama 4 Maverickvia Parasail · fp8 | $0.17/M cache readCheapest | input_cache_read: 0.00000017 / token (endpoint parasail/fp8) |