DeepSeek R1 Distill Llama 70B
helicone/deepseek-r1-distill-llama-70b · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.06
Blended $/1M (3:1)
$0.03
Input $/1M
$0.13
Output $/1M
$0.16
1M in + 1M out
—
Cache read $/1M
#706 of 7,713
Cheapest rank
- Provider
- Helicone (
helicone) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 4,096 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek R1 Distill Llama 70B” is offered by 5 providers — cheapest-effective first. This one (Helicone) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Helicone (this) | $0.03 | $0.13 | $0.06 | 128k |
| FastRouter | $0.03 | $0.14 | $0.06 | 131k |
| Alibaba (China) | $0.287 | $0.861 | $0.43 | 33k |
| NovitaAI | $0.8 | $0.8 | $0.80 | 8k |
| DigitalOcean | $0.99 | $0.99 | $0.99 | 33k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Helicone and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-r1-distill-llama-70b","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):