Llama-3.1-8B-Instruct
kitani/meta-llama/llama-3.1-8b-instruct · family llama · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.06
Blended $/1M (3:1)
$0.049
Input $/1M
$0.0765
Output $/1M
$0.13
1M in + 1M out
$0.0245 −50%
Cache read $/1M
#730 of 9,563
Cheapest rank
- Provider
- Kitani (
kitani) - Kind
- text (outputs text)
- Context
- 8,192 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools text
Same model, other providers
“Llama-3.1-8B-Instruct” is offered by 6 providers — cheapest-effective first. OpenRouter is the cheapest at $0.03 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| OpenRouter | $0.02 | $0.04 | $0.03 | 131k |
| Kilo Gateway | $0.02 | $0.04 | $0.03 | 131k |
| Novita AI | $0.02 | $0.05 | $0.03 | 16k |
| Kitani (this) | $0.049 | $0.0765 | $0.06 | 8k |
| Hugging Face | $0.06 | $0.06 | $0.06 | 131k |
| ZeroGPU | $0.15 | $0.28 | $0.18 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Kitani 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/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):