Llama 3.1 405B Instruct
Context
128K
Max output
128K
Serving providers
2
Cheapest input
$5.00 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial AnalysisSpeed & latency
Output speed
44 t/s
tokens / second
Time to first token
33.05s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |
|---|---|---|---|---|
| CritPt | 0% | default | — | |
| EvalComputeProxy | 768.5 | default | — | |
| GPQA Diamond | 52% | default | — | |
| Humanity's Last Exam | 4% | default | — | |
| IFBench | 39% | default | — | |
| LiveCodeBench | 30% | default | — | |
| Long-Context Reasoning | 24% | default | — | |
| MMLU-Pro | 73% | default | — | |
| Omniscience | -17.3 | default | — | |
| SciCode | 30% | default | — | |
| TerminalBench Hard | 7% | default | — | |
| τ²-bench | 19% | default | — |
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $5.00 to $10.68 per 1M tokens across 2 providers, so the dearest route costs 114% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DatabricksCheapest | $5.00 | $15.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
| OCI | $10.68 | $10.68 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Input down 84% since first tracked
Cost calculator
estimate your monthly spend on this model$2,200
estimated / month
Model IDs
copy the exact identifier for your platformdatabricks/databricks-meta-llama-3-1-405b-instructoci/meta.llama-3.1-405b-instruct
Frequently asked questions
Llama 3.1 405B Instruct pricing, context and availabilityHow much does Llama 3.1 405B Instruct cost?
Llama 3.1 405B Instruct costs $5.00 per 1M input tokens and $10.68 per 1M output tokens at its cheapest provider via Databricks. Across 2 serving providers, input prices range from $5.00 to $10.68 per 1M tokens.
What is the context window of Llama 3.1 405B Instruct?
Llama 3.1 405B Instruct accepts up to 128K tokens of context and can return up to 128K output tokens.
Which providers serve Llama 3.1 405B Instruct?
Llama 3.1 405B Instruct is available from 2 serving providers, each with its own pricing and model ID. Databricks is currently the cheapest.
What can Llama 3.1 405B Instruct do?
Llama 3.1 405B Instruct supports tool use.
Other Meta models
compare pricing across the Meta lineupLlama 3.3 70B Instruct$0.12/1M · 11 providersLlama 4 Scout 17B 16e Instruct$0.05/1M · 10 providersMeta Llama 3.1 8B Instruct$0.02/1M · 6 providersLlama 3.1 8B Instruct$0.02/1M · 6 providersLlama 4 Maverick 17B 128e Instruct FP8$0.05/1M · 6 providersLlama 3.2 3B Instruct$0.02/1M · 5 providersLlama 3.2 11B Vision Instruct$0.05/1M · 5 providersMeta Llama 3.1 70B Instruct$0.12/1M · 5 providers
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI