jishie

DeepSeek V3.1

merge-gateway/deepseek/deepseek-v3.1 · family deepseek · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

$0.75Blended $/1M (3:1)
$0.5Input $/1M
$1.5Output $/1M
$2.001M in + 1M out
Cache read $/1M
#2813 of 5,000Cheapest rank
Provider
Merge Gateway (merge-gateway)
Context
164,000 tokens
Max output
41,000 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“DeepSeek V3.1” is offered by 9 providers — cheapest-effective first. NanoGPT is the cheapest at $0.33 blended.

ProviderInputOutputBlendedContext
NanoGPT$0.2$0.7$0.33128k
submodel$0.2$0.8$0.3575k
OpenRouter$0.25$0.95$0.42164k
NovitaAI$0.27$1$0.45131k
Jiekou.AI$0.27$1$0.45164k
Meganova$0.27$1$0.45164k
Merge Gateway (this)$0.5$1.5$0.75164k
Baseten$0.5$1.5$0.75164k
Weights & Biases$0.55$1.65$0.82161k

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-v3.1","messages":[{"role":"user","content":"hello"}]}'

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