Prime Inference
Inference hostPrime Inference runs open and licensed models on its own hardware and sells them by usage, often faster or cheaper than the maker.
Models122
- Cheapest for
- 0 models
- Serves
- 1 model types
Visits in September 2026172K−41.3%Unique visitors 70K
- Apr
- May
- Jun
- Jul
- Aug
- Sep
Models by type
Models on Prime Inference
| Model | Input | Output | vs official | Context |
|---|---|---|---|---|
 GLM-4.7Zhipu AI | $0.60/1M | $2.20/1M from $1.10 at AIHubMix | ±0% | — |
| GLM-4.5Zhipu AI | $0.60/1M | $2.20/1M from $1.16 at ZenMux | ±0% | — |
| GLM-4.6Zhipu AI | $0.60/1M | $2.20/1M from $1.10 at AIHubMix | ±0% | — |
 Qwen3-VL-8B-InstructAlibaba | $0.117/1M | $0.455/1M from $0.278 at SiliconFlow | +64% | — |
| Kimi K2.7 Code HighSpeedMoonshot AI | $1.90/1M | $8/1M from $2.76 at Kenari | +113% | — |
 MiMo-V2.5-ProXiaomi | $0.48/1M | $1.50/1M from $0.609 at OpenRouter | +146% | — |
 Nemotron 3.5 Lightning 30B A3BNVIDIA | $0.07/1M | $0.20/1M from $0.16 at Deep Infra | — | — |
 Llama-3.3-70B-InstructMeta | $1.04/1M | $2.25/1M from $0.32 at Deep Infra | +604% | — |
| Qwen3.6 27BAlibaba | $0.60/1M | $3.60/1M from $2 at OpenRouter | ±0% | — |
 Mistral NemoMistral | $0.165/1M | $0.17/1M from $0.03 at Deep Infra | +467% | — |
 DeepSeek V4 Flash 0731DeepSeek | $0.44/1M | $1.32/1M from $0.133 at OpenRouter | +890% | — |
| Qwen3.5 0.8BAlibabaOnly here | $0.04/1M | $0.08/1M | — | — |
 Laguna S 2.1Poolside | $0.09/1M | $0.18/1M | ±0% | — |
| Qwen3.5 397B-A17BAlibaba | $0.60/1M | $3.60/1M from $0.986 at AIHubMix | +249% | — |
| Qwen3.5 2BAlibaba | $0.06/1M | $0.18/1M from $0.10 at Requesty | +80% | — |
| Qwen3 Coder 480B A35B InstructAlibaba | $0.975/1M | $4.88/1M from $0.95 at Helicone | +413% | — |
| Qwen3.7 MaxAlibaba | $3.75/1M | $11.25/1M from $3.75 at DevPass (LLM Gateway) | +127% | — |
| Qwen3.5 35B-A3BAlibaba | $0.25/1M | $1.30/1M from $0.451 at AIHubMix | -35% | — |
 Gemma 3 27BGoogle | $0.119/1M | $0.30/1M from $0.16 at Deep Infra | +88% | — |
| GLM-4.5-AirZhipu AI | $0.20/1M | $1.10/1M from $0.291 at ZenMux | ±0% | — |
| Qwen3.7 PlusAlibaba | $0.60/1M | $2.40/1M from $0.30 at CrazyRouter | +118% | — |
| Mistral Small 4Mistral | $0.165/1M | $0.66/1M from $0.60 at EmpirioLabs AI | +10% | — |
| Nemotron 3 Nano 30B A3BNVIDIA | $0.06/1M | $0.24/1M from $0.20 at Novita AI | +20% | — |
| Claude Haiku 4.5 (latest)Anthropic | $1/1M | $5/1M from $4 at APIMart | ±0% | — |
| Claude Opus 4.1Anthropic | $15/1M | $75/1M | ±0% | — |
| Claude Opus 4.5 (latest)Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Opus 4.6Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Opus 4.7Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Opus 4.8Anthropic | $5/1M | $25/1M from $20 at APIMart | ±0% | — |
| Claude Sonnet 4.5 (latest)Anthropic | $3/1M | $15/1M from $12 at APIMart | ±0% | — |
| Deepseek 3.2DeepSeek | $0.37/1M | $1.11/1M from $0.308 at APIMart | +260% | — |
| DeepSeek V3.1 TerminusDeepSeek | $0.27/1M | $1/1M from $0.95 at Hugging Face | +5% | — |
| DeepSeek-V3.1DeepSeek | $0.60/1M | $1.70/1M from $0.798 at Poe | +113% | — |
| DeepSeek-V3.2-ExpDeepSeek | $0.27/1M | $0.41/1M from $0.308 at APIMart | +33% | — |
| Gemini 2.5 Flash-LiteGoogle | $0.10/1M | $0.40/1M from $0.32 at APIMart | ±0% | — |
| Gemini 3 Flash PreviewGoogle | $0.50/1M | $3/1M from $1.50 at Vertex | ±0% | — |
| Gemini 3.5 FlashGoogle | $1.50/1M | $9/1M from $2.70 at Kie.ai | +233% | — |
| Gemini 3.6 FlashGoogle | $1.50/1M | $7.50/1M from $3 at CometAPI | +100% | — |
| Gemini 3.7 FlashGoogle | $1.35/1M | $6.75/1M from $1.13 at Kie.ai | +500% | — |
| Gemini Pro LatestGoogle | $2/1M | $12/1M from $6.90 at Kenari | ±0% | — |
| GPT-4.1 miniOpenAI | $0.40/1M | $1.60/1M from $1.28 at APIMart | ±0% | — |
| GPT-4.1 nanoOpenAI | $0.10/1M | $0.40/1M from $0.32 at APIMart | ±0% | — |
| GPT-5.1OpenAI | $1.25/1M | $10/1M from $8 at APIMart | ±0% | — |
| GPT-5.6 TerraOpenAI | $2.50/1M | $15/1M from $9.60 at APIMart | +25% | — |
| GPT-6.1 Sol ProOpenAI | $2/1M | $10/1M | ±0% | — |
| Grok-4.20-Multi-AgentxAI | $2/1M | $6/1M from $2 at APIMart | +140% | — |
| Kimi K2 0905Moonshot AI | $0.60/1M | $2.50/1M from $2 at Helicone | +25% | — |
| Kimi K3.1 Pro HighspeedMoonshot AI | $2/1M | $10/1M from $6.13 at Kenari | +6% | — |
| Laguna XS 2.1Poolside | $0.06/1M | $0.12/1M | ±0% | — |
| Llama 3.2 1B InstructMeta | $0.027/1M | $0.201/1M from $0.10 at Amazon Bedrock | +101% | — |
Prime Inference at a glance
122 models in total: 122 text. The cheapest is Qwen3.5 0.8B at $0.08 /1M. GPT-6 Astra has the largest context window, 1.05M tokens. The most searched is Gemini 4 Argon, with about 2M Google searches a month. The newest is Kimi K3.1 Pro Highspeed, released Oct 23, 2026.
Cheapest
- Qwen3.5 0.8B$0.08/1M
- Laguna XS 2.1$0.12/1M
- Qwen3.7 Flash$0.13/1M
- Mistral Nemo$0.17/1M
- Laguna S 2.1$0.18/1M
Largest context
- GPT-6 Astra1.05M
- GPT-6.1 Sol1.05M
- GPT-6 Sol1.05M
- GPT-6 Luna1.05M
- GPT-5.6 Luna1.05M
Most searched
- Gemini 4 Argon2M
- Kimi K3658K
- GPT-6 Astra580K
- Claude Opus 5.5405K
- GPT-6.1 Sol384K
Newest
- Kimi K3.1 Pro HighspeedOct 23, 2026
- DeepSeek V4 Flash Vision ExpOct 17, 2026
- Muse Spark OpenOct 15, 2026
- Gemini 4 ArgonOct 13, 2026
- GPT-6.1 SolSep 29, 2026