DeepSeek-R1
huggingface/deepseek-ai/DeepSeek-R1 · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$1.15
Blended $/1M (3:1)
$0.7
Input $/1M
$2.5
Output $/1M
$3.20
1M in + 1M out
—
Cache read $/1M
#4327 of 7,708
Cheapest rank
- Provider
- Hugging Face (
huggingface) - Kind
- text (outputs text)
- Context
- 64,000 tokens
- Max output
- 32,768 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek-R1” is offered by 12 providers — cheapest-effective first. iFlow is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| iFlow | free | free | $0.00 | 128k |
| Hugging Face (this) | $0.7 | $2.5 | $1.15 | 64k |
| Kilo Gateway | $0.7 | $2.5 | $1.15 | 64k |
| OpenRouter | $0.7 | $2.5 | $1.15 | 64k |
| Melious | $0.6955 | $2.78 | $1.22 | 164k |
| Azure | $1.35 | $5.4 | $2.36 | 164k |
| Azure Cognitive Services | $1.35 | $5.4 | $2.36 | 164k |
| Vercel AI Gateway | $1.35 | $5.4 | $2.36 | 128k |
| Amazon Bedrock | $1.35 | $5.4 | $2.36 | 128k |
| Together AI | $3 | $7 | $4.00 | 164k |
| Snowflake Cortex | — | — | — | 128k |
| Qiniu | — | — | — | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Hugging Face and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-ai/DeepSeek-R1","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):