Seed 2.0 Code
deepinfra/ByteDance/Seed-2.0-code · family seed · in: text, image → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image.
$1.13
Blended $/1M (3:1)
$0.5
Input $/1M
$3
Output $/1M
$3.50
1M in + 1M out
$0.1 −80%
Cache read $/1M
#4463 of 7,979
Cheapest rank
- Provider
- Deep Infra (
deepinfra) - Kind
- text (outputs text)
- Context
- 256,000 tokens
- Max output
- 131,072 tokens
- Capabilities
- tools reasoning text image
Same model, other providers
“Seed 2.0 Code” is offered by 8 providers — cheapest-effective first. EmpirioLabs AI is the cheapest at $0.90 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| EmpirioLabs AI | $0.4 | $2.4 | $0.90 | 256k |
| Merge Gateway | $0.4 | $2.4 | $0.90 | 256k |
| Volcengine Ark | $0.475 | $2.37 | $0.95 | 262k |
| Deep Infra (this) | $0.5 | $3 | $1.13 | 256k |
| Kilo Gateway | $0.5 | $3 | $1.13 | 262k |
| OpenRouter | $0.5 | $3 | $1.13 | 262k |
| Requesty | $0.5 | $3 | $1.13 | 256k |
| Ofox | $0.67 | $3.36 | $1.34 | 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-code","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):