Seed 2.0 Mini
deepinfra/ByteDance/Seed-2.0-mini · family seed · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$0.18
Blended $/1M (3:1)
$0.1
Input $/1M
$0.4
Output $/1M
$0.50
1M in + 1M out
$0.02 −80%
Cache read $/1M
#1556 of 8,720
Cheapest rank
- Provider
- Deep Infra (
deepinfra) - Kind
- text (outputs text)
- Context
- 256,000 tokens
- Max output
- 32,000 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Seed 2.0 Mini” is offered by 9 providers — cheapest-effective first. Volcengine Ark is the cheapest at $0.10 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Volcengine Ark | $0.0297 | $0.2969 | $0.10 | 256k |
| Deep Infra (this) | $0.1 | $0.4 | $0.18 | 256k |
| Kilo Gateway | $0.1 | $0.4 | $0.18 | 262k |
| BytePlus ModelArk | $0.1 | $0.4 | $0.18 | 256k |
| Requesty | $0.1 | $0.4 | $0.18 | 256k |
| OpenRouter | $0.1 | $0.4 | $0.18 | 262k |
| Ofox | $0.06 | $0.56 | $0.18 | 256k |
| EmpirioLabs AI | $0.12 | $0.5 | $0.21 | 229k |
| Merge Gateway | $0.12 | $0.5 | $0.21 | 256k |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Deep Infra and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"ByteDance/Seed-2.0-mini","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):