Nousresearch
Hermes 3 70B Instruct
Released 2024-08-18 · Knowledge up to 2023-12-31 · Retires 2026-11-02
Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the...
You send / 1M
$0.700
tokens in
It replies / 1M
$0.700
tokens out
Memory
131K
tokens it can read at once
Typical request
$0.0013
1,000 words in, 400 out
Data privacy
No training or retention: Yes. At least one provider serves it with zero data retention.
| Provider | You send / 1M | It replies / 1M | Uptime | Privacy policy |
|---|---|---|---|---|
| DeepInfra · fp8 | $0.700 | $0.700 | 100% | Read |
Based on OpenRouter and Vercel AI Gateway data. Confirm terms with the provider before sending sensitive data.
What it can do
- Reads: text
- Writes: text
- Reasoning: No
- Tool calling: No
- Longest reply: 16K tokens
- Intelligence score: 6 / 100 (Artificial Analysis)
Similar models
- Weaver (alpha)Mancer · $0.400 in / $0.750 out per 1M
- Gemma 2 27BGoogle · $0.650 in / $0.650 out per 1M
- ReMM SLERP 13BUndi95 · $0.350 in / $0.650 out per 1M
- Qwen-PlusQwen · $0.260 in / $0.780 out per 1M
- Qwen3 Coder NextQwen · $0.120 in / $0.800 out per 1M
- Skyfall 36B V2Thedrummer · $0.550 in / $0.800 out per 1M