Novita AI
Inference providerUS Westprices checked Oct 23, 06:00 UTC
Novita AI serves 87 models at a verified price. On the 77 it shares with other hosts, it is the cheapest on 16 and charges a median 30% above the cheapest.
Models served8772 with open weights · +1 without a price
Cheapest input, per M$0.02Llama 3.1 8B
Uptime, last 24 h93.0%average of its 2 OpenRouter endpoints
Sign-upNo card neededno free credits stated
| Model | Precision | Context | Tools | Input | Output | Cache |
|---|---|---|---|---|---|---|
| DeepSeek V4.1 Flash 1017 | fp8 | 1M | ✓ | $0.30 | $1.20 | $0.006 |
| Ling 3.1 Flash | not stated by the host | 256K | ✓ | $0.30 | $0.90 | $0.06 |
| MiMo-V2.6-Flash | not stated by the host | 1M | — | $0.14 | $0.28 | $0.0028 |
| MiMo-V2.6-Pro | not stated by the host | 1M | — | $0.43 | $0.87 | $0.0036 |
| Step 5 Previewcheapest | — | 1M | — | $1.00 | $2.70 | $0.10 |
| DeepSeek V4.1 Flash | fp8 | 1M | ✓ | $0.30 | $1.20 | $0.006 |
| Ling 3.0 Flash Sante (inclusionAI) | — | 256K | — | $0.075 | $0.22 | $0.015 |
| Ling 3.0 Flash VL (inclusionAI) | not stated by the host | under review | — | $0.075 | $0.22 | $0.015 |
| Ling 3.0 Flash Fin (inclusionAI) | not stated by the host | 256K | — | $0.075 | $0.22 | $0.015 |
| Hunyuan 4 Preview | fp8 | 1M | ✓ | $0.83 | $2.50 | $0.042 |
| Qwen3.8 27B | not stated by the host | under review | ✓ | $0.42 | $3.00 | $0.085 |
| GLM-5.3-Flash | fp8 | 1M | ✓ | $0.15 | $0.50 | $0.03 |
| Qwen3.8 Flashcheapest | — | 1M | — | $0.15 | $0.47 | $0.016 |
| Apodex 1.1 Minino verified price | — | 256K | — | — | — | — |
| DeepSeek V4 Flash Vision Exp | not stated by the host | 1M | — | $0.44 | $1.32 | $0.028 |
| GLM-5.3 | not stated by the host | 128K | — | $1.40 | $4.40 | — |
| DeepSeek V4 Pro 0813 | fp8 | 1M | ✓ | $1.32 | $3.96 | $0.044 |
| Qwen3.8 2.4T A95Bcheapest | not stated by the host | 1M | ✓ | $2.00 | $6.00 | $0.25 |
| Qwen3.8 Maxcheapest | — | 1M | — | $2.00 | $6.00 | $0.25 |
| DeepSeek V4 Flash 0731 | fp8 | 1M | ✓ | $0.44 | $1.32 | $0.028 |
| Ling 3.0 Flashcheapest | not stated by the host | 256K | ✓ | $0.06 | $0.18 | $0.012 |
| Kimi K3 | not stated by the host | 1M | — | $3.00 | $15.00 | $0.30 |
| Hunyuan 3 | not stated by the host | 256K | ✓ | $0.14 | $0.58 | $0.035 |
| GLM 5.2 | fp8 | 1M | ✓ | $1.40 | $4.40 | $0.26 |
| Kimi K2.7 Code | int4 | 256K | ✓ | $0.95 | $4.00 | $0.19 |
| MiniMax-M3 | fp8 | 1M | ✓ | $0.30 | $1.20 | $0.06 |
| Step 3.7 Flash | fp8 | 256K | ✓ | $0.20 | $1.15 | $0.04 |
| Qwen3.7 Maxcheapest | — | 1M | — | $1.25 | $3.75 | $0.25 |
| DeepSeek V4 Pro 0423 | fp8 | 1M | ✓ | $1.60 | $3.20 | $0.14 |
| MiMo-V2.5 | — | 1M | — | $0.17 | $0.34 | $0.0034 |
| MiMo-V2.5-Pro | — | 1M | — | $0.52 | $1.04 | $0.0043 |
| Qwen3.6 27B | not stated by the host | 256K | — | $0.60 | $3.60 | — |
| Kimi K2.6 | not stated by the host | 256K | ✓ | $0.80 | $3.40 | $0.16 |
| Qwen3.6 35B A3B | not stated by the host | 256K | — | $0.25 | $1.49 | — |
| GLM 5.1 | fp8 | 200K | ✓ | $1.38 | $4.40 | $0.26 |
| Gemma 4 26B A4B | bf16 | 256K | ✓ | $0.13 | $0.40 | — |
| Gemma 4 31B | bf16 | 256K | ✓ | $0.14 | $0.40 | — |
| GLM 5V Turbocheapest | not stated by the host | 198K | — | $1.20 | $4.00 | $0.24 |
| MiniMax M2.7 | fp8 | 200K | ✓ | $0.30 | $1.20 | $0.06 |
| Qwen3.5 122B A10B | bf16 | 256K | ✓ | $0.40 | $3.20 | — |
| Qwen3.5-27B | bf16 | 256K | ✓ | $0.30 | $2.40 | — |
| Qwen3.5-35B-A3B | not stated by the host | 256K | — | $0.25 | $2.00 | — |
| Qwen3.5 397B A17B | not stated by the host | 256K | ✓ | $0.60 | $3.60 | — |
| GLM 5 | fp8 | 203K | ✓ | $1.00 | $3.20 | $0.20 |
| MiniMax M2.5 | fp8 | 200K | ✓ | $0.30 | $1.20 | $0.03 |
| Qwen3 Coder Next | not stated by the host | 256K | — | $0.20 | $1.50 | — |
| Kimi K2.5 | not stated by the host | 256K | ✓ | $0.60 | $3.00 | $0.10 |
| GLM 4.7 Flash | bf16 | 200K | ✓ | $0.07 | $0.40 | $0.01 |
| MiniMax M2.1cheapest | not stated by the host | 200K | — | $0.30 | $1.20 | $0.03 |
| GLM 4.7 | fp8 | 200K | ✓ | $0.60 | $2.20 | $0.11 |
| Nemotron 3 Nano 30B A3Bcheapest | fp4 | 256K | ✓ | $0.05 | $0.20 | — |
| GLM 4.6Vcheapest | bf16 | 128K | ✓ | $0.30 | $0.90 | $0.055 |
| Kimi K2 Thinkingcheapest | bf16 | 256K | ✓ | $0.60 | $2.50 | $0.15 |
| MiniMax M2 | not stated by the host | 200K | — | $0.30 | $1.20 | $0.03 |
| Qwen3 VL 30B A3B Instruct | bf16 | 128K | ✓ | $0.20 | $0.70 | — |
| GLM 4.6 | bf16 | 200K | ✓ | $0.55 | $2.20 | $0.11 |
| DeepSeek V3.2 | not stated by the host | 160K | — | $0.27 | $0.40 | $0.13 |
| DeepSeek V3.2 Exp | not stated by the host | 160K | — | $0.27 | $0.41 | — |
| Qwen3 Omni 30B A3B Instruct | — | 64K | — | $0.25 | $0.97 | — |
| Qwen3 Omni 30B A3B Thinking | — | 64K | — | $0.25 | $0.97 | — |
| Qwen3 Max | — | 256K | — | $2.11 | $8.45 | — |
| Qwen3 VL 235B A22B Instruct | not stated by the host | 128K | — | $0.30 | $1.50 | — |
| Qwen3 VL 235B A22B Thinking | not stated by the host | 128K | — | $0.98 | $3.95 | — |
| DeepSeek V3.1 Terminuscheapest | not stated by the host | 128K | — | $0.27 | $1.00 | $0.14 |
| DeepSeek V3.1 | not stated by the host | 128K | — | $0.27 | $1.00 | $0.14 |
| Baichuan M2 32B | — | 128K | — | $0.07 | $0.07 | — |
| GLM 4.5Vcheapest | fp8 | 64K | ✓ | $0.60 | $1.80 | $0.11 |
| gpt-oss-120b | fp4 | 128K | ✓ | $0.05 | $0.25 | — |
| gpt-oss-20b | not stated by the host | 125K | — | $0.04 | $0.15 | — |
| Qwen3 Coder 30B A3B Instructcheapest | not stated by the host | 160K | — | $0.07 | $0.27 | — |
| GLM 4.5 Aircheapest | bf16 | 128K | ✓ | $0.13 | $0.85 | $0.025 |
| Qwen3 235B A22B Thinking 2507 | not stated by the host | 128K | — | $0.30 | $3.00 | — |
| Qwen3 Coder | not stated by the host | 256K | — | $0.38 | $1.55 | — |
| Qwen3 235B A22B Instruct 2507 | not stated by the host | 128K | — | $0.09 | $0.58 | — |
| ERNIE 4.5 21B A3B | — | 120K | — | $0.07 | $0.28 | — |
| ERNIE 4.5 VL 424B A47B | — | 123K | — | $0.42 | $1.25 | — |
| MiniMax M1 | bf16 | 1M | ✓ | $0.55 | $2.20 | — |
| DeepSeek R1 | not stated by the host | 160K | — | $0.70 | $2.50 | $0.35 |
| Llama 4 Maverick | not stated by the host | 1M | — | $0.27 | $0.85 | — |
| Llama 4 Scout | not stated by the host | 128K | — | $0.18 | $0.59 | — |
| Gemma 3 12Bcheapest | not stated by the host | 128K | — | $0.05 | $0.10 | — |
| Gemma 3 27B | bf16 | 96K | — | $0.12 | $0.20 | — |
| Llama 3.3 70B | bf16 | 12K | ✓ | $0.14 | $0.40 | — |
| Qwen3 Next 80B A3B | not stated by the host | 128K | — | $0.15 | $1.50 | — |
| Qwen 2.5 72B | not stated by the host | 32K | — | $0.38 | $0.40 | — |
| Llama 3.1 8B | fp8 | 16K | — | $0.02 | $0.05 | — |
| Mistral Nemo | not stated by the host | 60K | — | $0.04 | $0.17 | — |
| GLM-4 32B | not stated by the host | 32K | — | $0.55 | $1.66 | — |
10 of 88 models · prices per million tokens · precision and context: read at Novita AI's own catalogue or docs where its terms allow, otherwise as declared to OpenRouter (hover a cell for its source) · tools as Novita AI declares them to OpenRouter
| Condition | What it says | Source |
|---|---|---|
| Sign-up | No credit card needed to start | docs.novita.ai |
| Free credits | None stated | — |
| Headquarters region | US West | — |
| Price list | Where its per-token prices are published | novita.ai |
| API documentation | Its own docs | docs.novita.ai |
| Status page | Outages and incidents, as Novita AI reports them | status.novita.ai |
| Terms of service | Its terms | novita.ai |
| Discount | 50% launch discount on input & output | novita.ai |
| Free model | Apodex 1.1 Mini, free at Novita | novita.ai |
Links checked Oct 8. The link to Novita AI is an affiliate link. It never changes an order or a price on this site. Affiliate disclosure.