DeepSeek TNG R1T2 Chimera
helicone/deepseek-tng-r1t2-chimera · family deepseek-thinking · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.
$0.52
Blended $/1M (3:1)
$0.3
Input $/1M
$1.2
Output $/1M
$1.50
1M in + 1M out
—
Cache read $/1M
#2860 of 7,712
Cheapest rank
- Provider
- Helicone (
helicone) - Kind
- text (outputs text)
- Context
- 130,000 tokens
- Max output
- 163,840 tokens
- Capabilities
- tools text
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at Helicone and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"deepseek-tng-r1t2-chimera","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):