jishie

DeepSeek-R1

melious/deepseek-r1-0528 · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.

$1.22
Blended $/1M (3:1)
$0.6955
Input $/1M
$2.78
Output $/1M
$3.48
1M in + 1M out
$0.1855 −73%
Cache read $/1M
#4212 of 7,326
Cheapest rank
Provider
Melious (melious)
Kind
text (outputs text)
Context
164,000 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.

ProviderInputOutputBlendedContext
iFlowfreefree$0.00128k
Hugging Face$0.7$2.5$1.1564k
Kilo Gateway$0.7$2.5$1.1564k
OpenRouter$0.7$2.5$1.1564k
Melious (this)$0.6955$2.78$1.22164k
Azure Cognitive Services$1.35$5.4$2.36164k
Vercel AI Gateway$1.35$5.4$2.36128k
Azure$1.35$5.4$2.36164k
Amazon Bedrock$1.35$5.4$2.36128k
Together AI$3$7$4.00164k
Qiniu128k
Snowflake Cortex128k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Melious and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"deepseek-r1-0528","messages":[{"role":"user","content":"hello"}]}'

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

← all Melious models · model index · JSON