Llama 3.3 70B Instruct

Offerings

HostVariantRegionStatusInput $/MtokOutput $/MtokCache readCache writeConfidence?Source
akashmlfp8–active$0.20$0.52$0.10–apiopenrouter
aws-bedrock––active$0.72$0.72––aggregatorlitellm, modelsdev, backfill-litellm
aws-bedrock–usactive$0.72$0.72––aggregatorlitellm
azure––active$0.71$0.71––aggregatorlitellm, modelsdev, backfill-litellm
cloudflarefp8–active$0.29$2.25––apiopenrouter
coreweave––active$0.71$0.71$0.71–apiopenrouter
deepinfra––active$0.23$0.40––aggregatorlitellm, modelsdev, backfill-litellm
deepinfrafp8+turbo–active$0.10$0.32––apiopenrouter
google-vertex––active$0.72$0.72––apiopenrouter, litellm, modelsdev, backfill-litellm
google-vertex–us-central1active$0.72$0.72––apiopenrouter
groq––active$0.59$0.79$0.30–apiopenrouter, modelsdev
hyperbolic––active$0.12$0.30––aggregatorlitellm, backfill-litellm
meta––activefreefree––aggregatorlitellm, modelsdev, backfill-litellm
nebius––active$0.13$0.40––aggregatorlitellm, backfill-litellm
novita––active$0.14$0.40––apiopenrouter, litellm, modelsdev, backfill-litellm
nvidia––unlistedfreefree––aggregatormodelsdev
openrouter––active$0.71$0.71$0.71–apiopenrouter
parasailfp8–active$0.22$0.50$0.11–apiopenrouter
primeintellect––unlisted$1.04$2.25––apiopenrouter
sambanova––active$0.60$1.20––apiopenrouter, litellm, backfill-litellm
together––active$1.04$1.04––apiopenrouter, litellm, modelsdev, backfill-litellm

Confidence: official = vendor pricing page · api = OpenRouter per-host · aggregator = community list, may lag · unreviewed = automatic extraction awaiting review. When sources disagree the most authoritative wins. Details: /methodology#confidence

Sources for this model

Cite this page

Llama 3.3 70B Instruct: $0.10/$0.32 per 1M tokens on deepinfra as of 2026-11-19. Token Barometer by Dejan Strbad, https://tokenbarometer.com, data CC BY 4.0. https://tokenbarometer.com/model/meta/llama-3.3-70b-instruct

Badge

Embed a pricing badge for this model:

[![Llama 3.3 70B Instruct price](https://tokenbarometer.com/badge/meta/llama-3.3-70b-instruct.svg)](https://tokenbarometer.com/model/meta/llama-3.3-70b-instruct)

Price history

Change log

DateHostKindChange
2026-11-14openrouterMetadata changedmax output tokens 128000 → 115200
2026-11-13akashmlMetadata changedmax output tokens 115200 → 128000
2026-11-11openrouterMetadata changedmax output tokens 128000 → 115200
2026-11-10akashmlMetadata changedmax output tokens 32768 → 128000
2026-11-10novitaRemoved from sourceRemoved from source
2026-11-07openrouterMetadata changedmax output tokens 128000 → 32768
2026-11-05akashmlMetadata changedmax output tokens 16384 → 128000
2026-11-05togetherRemoved from sourceRemoved from source
2026-11-04openrouterMetadata changedmax output tokens 128000 → 16384
2026-11-03akashmlMetadata changedmax output tokens 16384 → 128000
2026-10-25metaRemoved from sourceRemoved from source
2026-10-25openrouterMetadata changedmax output tokens 128000 → 16384
2026-10-24nvidiaRemoved from sourceRemoved from source
2026-10-24akashmlMetadata changedmax output tokens 16384 → 128000
2026-10-18openrouterMetadata changedmax output tokens 128000 → 16384
2026-10-17akashmlMetadata changedmax output tokens 32768 → 128000
2026-10-15openrouterMetadata changedmax output tokens 128000 → 32768
2026-10-13akashmlMetadata changedmax output tokens 16384 → 128000
2026-10-12metaMetadata changeddeprecation date 2026-10-21 → 2027-03-30
2026-10-10openrouterMetadata changedmax output tokens 128000 → 16384
2026-10-08akashmlMetadata changedmax output tokens 16384 → 128000
2026-10-07openrouterMetadata changedmax output tokens 128000 → 16384
2026-10-06primeintellectRemoved from sourceRemoved from source
2026-10-06akashmlMetadata changedmax output tokens set to 128000
2026-09-24google-vertexNew offeringNew offering
2026-08-27deepinfraPrice cut0.13 → 0.10 (-23.1%), 0.39 → 0.32 (-17.9%)
2026-08-25togetherPrice increase0.88 → 1.04 (+18.2%), 0.88 → 1.04 (+18.2%)
2026-01-13novitaPrice cut1080.00 → 0.14 (-100.0%), 3200.00 → 0.40 (-100.0%)
2026-01-09novitaNew offeringNew offering
2025-10-04deepinfraPrice increase0.0380 → 0.13 (+242.1%), 0.12 → 0.39 (+225.0%)
2025-08-22deepinfraNew offeringNew offering
2025-07-21hyperbolicNew offeringNew offering
2025-06-06nebiusNew offeringNew offering
2025-05-19sambanovaNew offeringNew offering
2025-01-20togetherNew offeringNew offering
2024-12-21aws-bedrockNew offeringNew offering
2024-12-18azureNew offeringNew offering

Compare