DeepSeek R1
nano-gpt/deepseek-r1 · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.73
Blended $/1M (3:1)
$0.4
Input $/1M
$1.7
Output $/1M
$2.10
1M in + 1M out
$0.2 −50%
Cache read $/1M
#3535 of 7,708
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek R1” is offered by 6 providers — cheapest-effective first. This one (NanoGPT) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT (this) | $0.4 | $1.7 | $0.73 | 128k |
| D.Run (China) | $0.55 | $2.2 | $0.96 | 131k |
| Alibaba (China) | $0.574 | $2.29 | $1.00 | 131k |
| Merge Gateway | $1.35 | $5.4 | $2.36 | 164k |
| IO.NET | $2 | $8.75 | $3.69 | 128k |
| Abacus | $3 | $7 | $4.00 | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT 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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):