DeepSeek V3
merge-gateway/deepseek/deepseek-v3 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.85
Blended $/1M (3:1)
$0.58
Input $/1M
$1.68
Output $/1M
$2.26
1M in + 1M out
—
Cache read $/1M
#3834 of 7,710
Cheapest rank
- Provider
- Merge Gateway (
merge-gateway) - Kind
- text (outputs text)
- Context
- 163,840 tokens
- Max output
- 81,920 tokens
- Capabilities
- tools text
Same model, other providers
“DeepSeek V3” is offered by 5 providers — cheapest-effective first. D.Run (China) is the cheapest at $0.49 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| D.Run (China) | $0.28 | $1.1 | $0.49 | 131k |
| Alibaba (China) | $0.287 | $1.15 | $0.50 | 66k |
| Helicone | $0.56 | $1.68 | $0.84 | 128k |
| Merge Gateway (this) | $0.58 | $1.68 | $0.85 | 164k |
| DigitalOcean | — | — | — | 164k |
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","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):