per 1M tokens
meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | — | — | $0.02/1M | $0.04/1M | 131K | — | Listed | deepinfra |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$0.06 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.02/1M | $0.04/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-10-08 | token | $0.02 | $0.04 | Not published— |
| 2026-10-09 | token | $0.02 | $0.04 | Not published— |
| 2026-10-10 | token | $0.02 | $0.04 | Not published— |
| 2026-10-11 | token | $0.02 | $0.04 | Not published— |
| 2026-10-12 | token | $0.02 | $0.04 | Not published— |
| 2026-10-13 | token | $0.02 | $0.04 | Not published— |
| 2026-10-14 | token | $0.02 | $0.04 | Not published— |
| 2026-10-15 | token | $0.02 | $0.04 | Not published— |
| 2026-10-16 | token | $0.02 | $0.04 | Not published— |
| 2026-10-17 | token | $0.02 | $0.04 | Not published— |
| 2026-10-18 | token | $0.02 | $0.04 | Not published— |
| 2026-10-19 | token | $0.02 | $0.04 | Not published— |
| 2026-10-20 | token | $0.02 | $0.04 | Not published— |
| 2026-10-21 | token | $0.02 | $0.04 | Not published— |
| 2026-10-22 | token | $0.02 | $0.04 | Not published— |
| 2026-10-23 | token | $0.02 | $0.04 | Not published— |
| 2026-10-24 | token | $0.02 | $0.04 | Not published— |
| 2026-10-25 | token | $0.02 | $0.04 | Not published— |
| 2026-10-26 | token | $0.02 | $0.04 | Not published— |
| 2026-10-27 | token | $0.02 | $0.04 | Not published— |
| 2026-10-28 | token | $0.02 | $0.04 | Not published— |
| 2026-10-29 | token | $0.02 | $0.04 | Not published— |
| 2026-10-30 | token | $0.02 | $0.04 | Not published— |
Alternatives
- @cf/baai/bge-small-en-v1.5$0.02/1M · Compare
- Amazon: Titan Text Embeddings V2$0.02/1M · Compare
- Decision Small$0.02/1M · Compare
- Inception: Mercury Decide$0.02/1M · Compare
- Krea: K3 Edit$0.02/image · Compare
- LiquidAI: d1$0.02/1M · Compare
Parameters (1)
chat
Call this model
OpenRouter id deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())