Llama 3.1 8B Instruct
abacus/meta-llama/Meta-Llama-3.1-8B-Instruct · family llama · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.03
Blended $/1M (3:1)
$0.02
Input $/1M
$0.05
Output $/1M
$0.07
1M in + 1M out
—
Cache read $/1M
#642 of 7,708
Cheapest rank
- Provider
- Abacus (
abacus) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools text
Same model, other providers
“Llama 3.1 8B Instruct” is offered by 9 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 16k |
| Inference | $0.025 | $0.025 | $0.03 | 16k |
| Abacus (this) | $0.02 | $0.05 | $0.03 | 128k |
| NovitaAI | $0.02 | $0.05 | $0.03 | 16k |
| NanoGPT | $0.0544 | $0.085 | $0.06 | 131k |
| Pioneer | $0.2 | $0.2 | $0.20 | 128k |
| Vercel AI Gateway | $0.22 | $0.22 | $0.22 | 128k |
| Amazon Bedrock | $0.22 | $0.22 | $0.22 | 128k |
| Neon | $0.15 | $0.45 | $0.22 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Abacus and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"meta-llama/Meta-Llama-3.1-8B-Instruct","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):