Get Pass

Meta: Llama 3.1 70B Instruct

meta-llama/llama-3-1-70b-instruct
CompareAPITry this model

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.

Modalities
In / out per 1M$0.40 / $0.40
Context128K
ReleasedJul 23, 2024

Providers

2 providers serve this model upstream.

Providers serving this model
ProviderInput /MOutput /MCache read /MLatency P50Throughput P50Uptime
Amazon Bedrock$0.72$0.72Variable0.37s61 tps99.7%
DeepInfra (Turbo)us · fp8$0.40$0.40Variable1.43s27 tps99.12%

Market-wide measurements, refreshed every 15 minutes. They describe who serves Llama 3.1 70B Instruct in general, not how ProjectCOZY routes your requests.

Pricing

List rates per 1M tokens — what Llama 3.1 70B Instruct costs pay-as-you-go elsewhere, not what you pay here.

Input
$0.40
per 1M tokens
Output
$0.40
per 1M tokens
Cache read
—
not published
Included in every pass
Llama 3.1 70B Instruct is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.

Performance

Time to first token and output speed across every provider, over the last 3 days.

0.0s2.0s4.0s6.0s8.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
DeepInfra (Turbo) (us) Amazon Bedrock
0 tok/s50 tok/s100 tok/s150 tok/s200 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
DeepInfra (Turbo) (us) Amazon Bedrock

Uptime

100% of requests were served successfully over the last 3 days, across all providers.

Last 3 daysAvailability 99.99%
Oct 11, 2:00 PMNow
Availability over the last 24 hoursAvailability 99.96%
100% 98% 97% 95%
Oct 13, 2:50 PMNow

Apps

Tools that most often run Llama 3.1 70B Instruct, by tokens this week.

Verity Minecraft Mod68.7% of tokens526.1MKoalaBear15.5% of tokens118.3MSillyTavernRoleplay · 6.5% of tokens49.6MMedCOBE Simulation5.3% of tokens40.8MHermes AgentPersonal Agent · 4% of tokens30.6M

Activity

7.8B tokens processed market-wide in the last month.

0200.0M400.0M600.0M800.0M
Sep 14Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14
Tokens

FAQ

Which model id do I use for Llama 3.1 70B Instruct?
meta-llama/llama-3.1-70b-instruct. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Llama 3.1 70B Instruct hold?
131,072 tokens per request, of which up to 16,384 can be the response.
What can it accept and return?
Input: text. Output: text.
What does Llama 3.1 70B Instruct cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.40 per 1M input tokens and $0.40 per 1M output tokens.
How current is its knowledge?
Training data runs to Dec 2023. Anything later has to come from your prompt or a tool call.
Who built Llama 3.1 70B Instruct?
Meta, in the Llama family.

Explore

Other models your pass can call.

Aion 3.5aion-labs/aion-3.5256KAionAion 3.5 Miniaion-labs/aion-3.5-mini256KAionAion-2.0aion-labs/aion-2.0128KAionAion-3.0aion-labs/aion-3.0128KAionAion-3.0-Miniaion-labs/aion-3.0-mini128KAionAion-RP 1.0 (8B)aion-labs/aion-rp-llama-3.1-8b32KAion