Meta: Llama 3.3 70B Instruct · OpenRouter / deepinfra/turbo

meta-llama/llama-3.3-70b-instruct/deepinfra/turbo · Last successfully verified Oct 23, 2026, 12:19 AM

VerifiedRecently verified against the official source. Last successfully verified 2026-10-23 UTC.

Input$0.10per 1M tokens

Output$0.32per 1M tokens

Cached inputNot publishedper 1M tokens

OpenRouter route quote for API model meta-llama/llama-3.3-70b-instruct, fixed backend deepinfra/turbo (fp8). Not the upstream developer's direct API price or an OpenRouter-wide minimum. Text-token estimate only; pin this backend and disable fallbacks to match this quote. Taxes, credit-purchase fees and optional tools are excluded.

Calculator

Cost calculator

Estimate this model’s cost for uncached input, published cached input and output usage.

Uncached input tokensOutput tokens

Estimated cost$1.64for this workload

History

Pricing history

Verified changes to standard input and output rates.

No verified pricing changes recorded yet.

Changes will appear here after a verified update.

Model details

Specifications

Context window131,072

Maximum output16,384

ModalitiesText

ReasoningNot published

Tool callingNot published

Structured outputNot published

Alternatives

Compare with similar models

Open comparison

AMAmazon Nova Lite · Bedrock us-east-1Amazon Bedrock$0.06input / 1M OPOpenAI: gpt-oss-120b · OpenRouter / deepinfra/bf16OpenRouter$0.037input / 1M AMAmazon Nova Micro · Bedrock us-east-1Amazon Bedrock$0.035input / 1M

Alternatives above are nearest by combined input/output rate, not a claim of equivalent model quality or capabilities.

Explore pricing rankings

Calculate your own workload →

Provenance

Official source

Every price is tied to the official page and an immutable source snapshot. A successful HTTP check alone does not verify a price.

Official pricing URL: Open source
Last source check: Oct 23, 2026, 12:19 AM
Snapshot captured: Oct 23, 2026, 12:19 AM
Last price verification: Oct 23, 2026, 12:19 AM
Snapshot: 9fe607c32e2b