Models
Llama 3.1 70B Instruct
by Meta
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.
Our verdict
We have not reviewed Llama 3.1 70B Instruct yet
No one at Enterprise DNA has checked this listing against its sources. The description comes from public listings gathered automatically. Any fact below shows where it came from and when it was last checked.
From the listing
About Llama 3.1 70B Instruct
Meta's latest class of model (Llama 3.1) launched with a variety of sizes & flavors. This 70B instruct-tuned version is optimized for high quality dialogue usecases.
Notes
Llama 3.1 70B Instruct is listed in the EDNA Models directory from the OpenRouter catalogue.
Key facts
What we have checked
- Input price
- $0.720 per million tokens
- Output price
- $0.720 per million tokens
- Price on amazon-bedrock
- $0.720 per million input tokens
- Price on amazon-bedrock
- $0.720 per million output tokens
- Price on deepinfra
- $0.400 per million input tokens
- Price on deepinfra
- $0.400 per million output tokens
- Latest version
- meta-llama/llama-3.1-70b-instruct
- Time to first token (ms) on amazon-bedrock
- 350
- Time to first token (ms) on deepinfra
- 370
- Output speed (tokens a second) on amazon-bedrock
- 70
- Output speed (tokens a second) on deepinfra
- 33
- Tokens served on OpenRouter in a day
- 124.2M (for 10 Nov 2026)
Each value shows when we last confirmed it and where it came from. Values we have not confirmed are left out, never guessed.
API access
How to call it
Call via OpenRouter with model id `meta-llama/llama-3.1-70b-instruct`.
- openrouter ·
meta-llama/llama-3.1-70b-instruct· Docs
OpenRouter id: meta-llama/llama-3.1-70b-instruct
Price
What Llama 3.1 70B Instruct costs, over time
$0.400 to $0.720
$0.400 to $0.720
Prices by host
| Host | Price | Over time | Checked |
|---|---|---|---|
| amazon-bedrockInput | $0.720 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| amazon-bedrockOutput | $0.720 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraInput | $0.400 per million input tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
| deepinfraOutput | $0.400 per million output tokensSince 24 Oct 2026 | No change recorded | OpenRouter models API |
Usage
How much Llama 3.1 70B Instruct is used
180.3M to 124.2M
Scores
How Llama 3.1 70B Instruct scores
Each score comes from the named source and shows when we last confirmed it. A flag means the score needs care.
| Score | Value | Source | Checked |
|---|---|---|---|
| Artificial Analysis Intelligence Index | 6.6indexAs of 26 Oct 2026 | Artificial Analysis via OpenRouter | |
| LMArena text rating (Elo) | 1,261EloAs of 10 Nov 2026 | LMArena (CC-BY-4.0), published 2026-11-09 |
Sources
Where this comes from
- OpenRouter models APIRegistry
- OpenRouter models APIOfficial
- OpenRouter models APIThird party
A source shows what was published when we checked it. It does not certify security, performance or a working installation. Read our method.
Changelog
What changed
Price changed
output per mtok: 0.4 to 0.72
Price changed
input per mtok: 0.4 to 0.72
Deprecated
OpenRouter lists the route meta-llama/llama-3.1-70b-instruct to expire on 3 Nov 2026.
USAGE / OPENROUTER
How much Llama 3.1 70B Instruct is used
Tokens processed through OpenRouter each day. It shows what developers actually run, not every company's private traffic.
- Tokens, last 7 days
- 1.2B ▼20.4%
- Requests, last 7 days
- 1.1M
- Tool calls, last 7 days
- —
- People's vote
- 1261
- Price per million tokens
- $0.72 in · $0.72 out
MODEL FIELD GUIDE / SOURCE EVIDENCE
What you can do with Llama 3.1 70B Instruct.
Listed specifications; no EDNA task evaluation has been run. Sources checked 2026-11-10. Hosting routes and app features can differ.
meta-llama/llama-3.1-70b-instruct- Tool calling
- Not established
- Structured output
- Not established
- Reasoning controls
- Not established
- Availability
- available
- Price basis
- token
- Licence verification
- Llama 3.1 Community Licence, open weights (access request)
- Context length
- 131K tokens
- Knowledge cutoff
- 31 Dec 2023
- Developer release date
- Not established
- First seen in the catalogue
- 23 Jul 2024
- Listed retirement date
- Not established
Inspect the sources and their scope
meta-llama/llama-3.1-70b-instruct: listed route capabilities, availability and prices; provider endpoints can differ.
Checked 2026-11-10Source for first seen, context length, input, knowledge cutoff, output.
Checked 2026-11-10Licence declared in the meta-llama/Meta-Llama-3.1-70B-Instruct model repository on Hugging Face, which holds the weights files behind an access request. Read the licence terms before use.
Checked 2026-11-07FROM SPECIFICATIONS TO YOUR WORK
Is this the right model for your job?
Start with a realistic sample. These workflows match the model’s listed capabilities, not a verified result on your task.
What would it cost?
Pick a common job and how many times a month you run it. Token sizes are our assumption for a typical run, shown under the result.
Enter a whole number of runs from 1 to 100,000,000.
Working out the cost...
Token prices only. Per-request, image, tool, storage and subscription fees are not included. One token is about three quarters of an English word. Real counts vary by model and language. How tokens are counted ↗
Check the source
Price date: 10 Nov 2026, from OpenRouter models API. Prices are USD API token rates. Your app subscription, uploads, browsing and tools are separate.
Model source & availability ↗Understand the evidence
Listed capabilities and third-party benchmark scores do not establish Enterprise DNA task-test results. Validate accuracy and total cost on your own sample.
Intelligence Index: 6.6 (2026-10-26) ↗Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.