Inference.net
- Categories
- Inference hosts
- Owned by
- Inference R&D, Inc. (private)
- HQ
- US
- Website
- https://inference.net
- Pricing page
- https://inference.net/models
- Fee model
- per_token+subscription
- Fees
- Pay as you go $0 + usage; Growth $250/mo (50M gateway requests, 250 req/min, $50 one-time credit); Enterprise custom
- Free tier
- Pay-as-you-go plan: 1M gateway requests/mo, 1M tracing spans/mo, 14-day retention, 1 seat, 30 req/min
- OpenAI-compatible API
- yes
- Bring your own key
- no
- Notes
- Positions itself as a unified API that also resells closed models (Claude, GPT, Gemini, Grok) at list-equivalent prices — only open-weight models recorded here; also sells fine-tuning/evals/observability. Public /v1/models returns per-token pricing.
- Sources
- https://inference.net/pricing https://inference.net/models https://api.inference.net/v1/models collected 2026-09-18
LLM prices (22 models, USD per 1M tokens)
| Model | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| DeepSeek V3.2 deepseek-v3.2 |
$0.70 | $2 | $0.35 | 164k | ✓ src |
| DeepSeek V4 Flash 0423 deepseek-v4-flash |
$0.23 | $0.62 | $0.0028 | 1M | ✓ src |
| DeepSeek V4 Flash 0731 deepseek-v4-flash-0731 |
$0.53 | $1.58 | $0.017 | 1.05M | ✓ src |
| DeepSeek V4 Pro 0423 deepseek-v4-pro |
$2.10 | $4.20 | $0.00363 | 1.05M | ✓ src |
| DeepSeek V4 Pro 0813 deepseek-v4-pro-0813 |
$1.32 | $3.96 | $0.044 | 1.05M | ✓ src |
| DeepSeek V4.1 Flash deepseek-v4.1-flash |
$0.30 | $1 | $0.007 | 1.04M | ✓ src |
| Gemma 3 27B IT gemma-3-27b-it |
$0.09 | $0.25 | — | 131k | ✓ src |
| Gemma 3 4B gemma-3-4b-it |
$0.05 | $0.10 | — | 131k | ✓ src |
| GLM 5 glm-5 |
$0.95 | $2.55 | $0.20 | 205k | ✓ src |
| GLM-5.2 glm-5.2 |
$1.30 | $4.40 | $0.20 | 1M | ✓ src |
| GLM-5.3 glm-5.3 |
$0.90 | $3 | $0.15 | 1M | ✓ src |
| GLM-5.3 Flash glm-5.3-flash |
$0.09 | $0.28 | $0.02 | 1.05M | ✓ src |
| Kimi K2.5 kimi-k2.5 |
$0.80 | $3.95 | $0.13 | 262k | ✓ src |
| Kimi K2.6 kimi-k2.6 |
$1.25 | $5.30 | $0.21 | 262k | ✓ src |
| Kimi K3 moonshotai/kimi-k3 |
$2.10 | $10.95 | $0.23 | 1.05M | ✓ src |
| Llama 3.2 1B Instruct llama-3.2-1b-instruct |
$0.027 | $0.201 | — | 60k | ✓ src |
| Llama 3.2 3B Instruct llama-3.2-3b-instruct |
$0.05 | $0.33 | — | 131k | ✓ src |
| Llama 3.3 70B Instruct llama-3.3-70b-instruct |
$0.13 | $0.40 | — | 131k | ✓ src |
| Nemotron 3 Super 120B A12B nemotron-3-super |
$0.102 | $0.48 | — | 262k | ✓ src |
| Qwen3 14B qwen3-14b |
$0.228 | $0.91 | — | 131k | ✓ src |
| Qwen3 30B A3B qwen3-30b-a3b |
$0.12 | $0.50 | — | 41k | ✓ src |
| Qwen3 8B qwen3-8b |
$0.117 | $0.455 | — | 131k | ✓ src |