DeepSeek Reasoner
edenai/deepseek/deepseek-reasoner · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: reasoning text.
$0.32
Blended $/1M (3:1)
$0.28
Input $/1M
$0.42
Output $/1M
$0.70
1M in + 1M out
$0.028 −90%
Cache read $/1M
#1761 of 6,123
Cheapest rank
- Provider
- Eden AI (
edenai) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 384,000 tokens
- Capabilities
- reasoning text
Same model, other providers
“DeepSeek Reasoner” is offered by 6 providers — cheapest-effective first. DeepSeek is the cheapest at $0.18 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| DeepSeek | $0.14 | $0.28 | $0.18 | 1M |
| Eden AI (this) | $0.28 | $0.42 | $0.32 | 131k |
| OrcaRouter | $0.435 | $0.87 | $0.54 | 1M |
| NanoGPT | $0.4 | $1.7 | $0.73 | 64k |
| Helicone | $0.56 | $1.68 | $0.84 | 128k |
| AnyAPI | — | — | — | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Eden AI and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek/deepseek-reasoner","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):