jishie

DeepSeek R1

merge-gateway/deepseek/deepseek-r1 · family deepseek-thinking · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: reasoningtext.

$2.36Blended $/1M (3:1)
$1.35Input $/1M
$5.4Output $/1M
$6.751M in + 1M out
Cache read $/1M
#4178 of 5,000Cheapest rank
Provider
Merge Gateway (merge-gateway)
Context
163,840 tokens
Max output
40,960 tokens
Capabilities
reasoningtext

Same model, other providers

“DeepSeek R1” is offered by 6 providers — cheapest-effective first. NanoGPT is the cheapest at $0.73 blended.

ProviderInputOutputBlendedContext
NanoGPT$0.4$1.7$0.73128k
D.Run (China)$0.55$2.2$0.96131k
Alibaba (China)$0.574$2.294$1.00131k
Merge Gateway (this)$1.35$5.4$2.36164k
IO.NET$2$8.75$3.69128k
Abacus$3$7$4.00128k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at Merge Gateway 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-r1","messages":[{"role":"user","content":"hello"}]}'

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