DeepSeek: R1 Distill Llama 70B, DeepSeek — route, pricing & source
DeepSeek R1 Distill Llama 70B is a distilled large language model based on [Llama-3.3-70B-Instruct](/meta-llama/llama-3.3-70b-instruct), using outputs from [DeepSeek R1](/deepseek/deepseek-r1). The model combines advanced distillation techniques to achieve high performance across...
OpenRoutermediumLast checked: May 14, 2026
Input
$0.7000 / 1M
/ 1M tokens
Output
$0.8000 / 1M
/ 1M tokens
Cached input
Not available
Not available
Cache write
Not available
Not available
Context and limits
Context window
131.1K
Max output
16,384
Input modalities
text
Output modalities
text
Weight access
Closed
Availability
Unknown
Capability flags
JSONReasoningLong context
From source metadata + verification fields — confirm provider docs before production.
Benchmarks
No safely merged benchmark result for this model yet.
Access and license
Official API
No
Open weights
No
Self-hostable
No
License
Closed · API onlyNo public weights: use through a vendor’s cloud API or product. “Proprietary” means the creator does not distribute the trained model weights for self-hosting.
Example costs
Scenario: 1K input + 300 output tokens / request
10,000 requests
$9.40
100,000 requests
$94.00
1,000,000 requests
$940.00
Cheaper alternatives
Lower-cost models for the same scenario
