jishie

DeepSeek Reasoner

helicone/deepseek-reasoner · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: text.

$0.84
Blended $/1M (3:1)
$0.56
Input $/1M
$1.68
Output $/1M
$2.24
1M in + 1M out
$0.07 −88%
Cache read $/1M
#3734 of 7,708
Cheapest rank
Provider
Helicone (helicone)
Kind
text (outputs text)
Context
128,000 tokens
Max output
64,000 tokens
Capabilities
text

Same model, other providers

“DeepSeek Reasoner” is offered by 4 providers — cheapest-effective first. OrcaRouter is the cheapest at $0.18 blended.

ProviderInputOutputBlendedContext
OrcaRouter$0.147$0.295$0.181M
NanoGPT$0.4$1.7$0.7364k
Helicone (this)$0.56$1.68$0.84128k
AnyAPI———1M

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-reasoner","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Helicone models · model index · JSON