DeepSeek V3.1
abacus/deepseek/deepseek-v3.1 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.83
Blended $/1M (3:1)
$0.55
Input $/1M
$1.66
Output $/1M
$2.21
1M in + 1M out
—
Cache read $/1M
#4030 of 8,511
Cheapest rank
- Provider
- Abacus (
abacus) - Kind
- text (outputs text)
- Context
- 128,000 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek V3.1” is offered by 12 providers — cheapest-effective first. NanoGPT is the cheapest at $0.33 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT | $0.2 | $0.7 | $0.33 | 128k |
| Meganova | $0.19 | $0.79 | $0.34 | 164k |
| submodel | $0.2 | $0.8 | $0.35 | 75k |
| Kilo Gateway | $0.25 | $0.95 | $0.42 | 164k |
| OpenRouter | $0.25 | $0.95 | $0.42 | 164k |
| Jiekou.AI | $0.27 | $1 | $0.45 | 164k |
| CoreWeave | $0.5 | $1.5 | $0.75 | 161k |
| Abacus (this) | $0.55 | $1.66 | $0.83 | 128k |
| Merge Gateway | $0.56 | $1.68 | $0.84 | 131k |
| Alibaba (China) | $0.574 | $1.72 | $0.86 | 131k |
| Vertex | $0.6 | $1.7 | $0.88 | 164k |
| Together AI | $0.6 | $1.7 | $0.88 | 131k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Abacus 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):