DeepSeek-V3.1
tokengo/deepseek/deepseek-v3.1 · family deepseek · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text.
$0.32
Blended $/1M (3:1)
$0.19
Input $/1M
$0.71
Output $/1M
$0.90
1M in + 1M out
$0.06 −68%
Cache read $/1M
#2019 of 6,956
Cheapest rank
- Provider
- TokenGo (
tokengo) - Kind
- text (outputs text)
- Context
- 131,072 tokens
- Max output
- 8,192 tokens
- Capabilities
- tools reasoning text
Same model, other providers
“DeepSeek-V3.1” is offered by 7 providers — cheapest-effective first. This one (TokenGo) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| TokenGo (this) | $0.19 | $0.71 | $0.32 | 131k |
| Deep Infra | $0.25 | $0.95 | $0.42 | 164k |
| Vercel AI Gateway | $0.25 | $0.95 | $0.42 | 164k |
| Hugging Face | $0.27 | $1 | $0.45 | 131k |
| Pioneer | $0.56 | $1.68 | $0.84 | 164k |
| Amazon Bedrock | $0.58 | $1.68 | $0.85 | 164k |
| Qiniu | — | — | — | 128k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at TokenGo 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):