Overview
Live data · synced 85 min ago. Compare 490 models from 63 companies, see what runs on your own machine, and let the advisor cut your token bill.
Active models
490
44 deprecated
Companies
63
model creators
Run locally
144
151 open-weights
Cheapest / 1M
$0.024
gpt-oss-120b (3:1 in/out)
Largest context
1.05M
GPT Astra Latest
Best value by tier
All models →- DeepSeek V4 Pro 0813$1.24
- Nova Pro 1.0$1.40
- Hermes 4 405B$1.50
- Doubao Seed 2.1 Pro 260628$1.73
- Doubao Seed 2.1 Pro 260915$1.73
- Qwen3.5-122B-A10B$0.72
- Nemotron 3 Super$0.82
- Gemini Exp 1206$0.85
- Moondream 3 Preview$0.85
- R1 0528$0.91
- gpt-oss-120b$0.024
- Mistral Nemo$0.029
- Ling 3.0 Flash$0.032
- Llama 3 8B Lunaris$0.042
- Nex-N2.5-Mini$0.044
Cheapest by blended price per 1M tokens (3 input : 1 output).
Recent price changes
All updates →No price changes recorded yet.
Models
Prices are USD per 1M tokens from vendor price lists. Est. cost / token is blended at a 3:1 input:output mix.
| Compare | Model | Company | Parameters | Context | Input $/1M | Output $/1M | Est. cost / token | Features |
|---|---|---|---|---|---|---|---|---|
| Gemini Omni Flash Preview fast | Undisclosed | 131K | $1.50 | $9.00 | $3.38 /1M $0.000003375/token | VisionAudio inReasoningVideo in | ||
| Gemini Pro frontier | Undisclosed | 1.05M | $2.00 | $12.00 | $4.50 /1M $0.0000045/token | VisionAudio inBatchPDFCaching+5 | ||
| MythoMax 13B v2fastlocal | Gryphe | 13B | 4K | $0.080 | $0.11 | $0.087 /1M $0.000000087/token | JSON schema | |
| Granite 4.2 8B v4.2fastlocal | IBM | 8.8B | 131K | $0.060 | $0.25 | $0.11 /1M $0.000000108/token | CachingReasoningJSON schemaTools | |
| Mercury 3 v3fast | Inception Labs | Undisclosed | 1M | $0.10 | $0.35 | $0.16 /1M $0.000000163/token | CachingReasoningJSON schemaTools | |
| Mercury 2.5 v2.5fast | Inception Labs | Undisclosed | 260K | $0.20 | $0.75 | $0.34 /1M $0.000000337/token | CachingReasoningJSON schemaTools | |
| Mercury 2 v2fast | Inception Labs | Undisclosed | 128K | $0.25 | $0.75 | $0.38 /1M $0.000000375/token | CachingReasoningJSON schemaTools | |
| Ling 3.1 Flash v3.1fast | Inclusionai | Undisclosed | 1M | $0.075 | $0.23 | $0.11 /1M $0.000000112/token | CachingReasoningJSON schemaTools | |
| Ling 3.0 Flash VL v3fastlocal | Inclusionai | 124.8B | 131K | $0.060 | $0.18 | $0.090 /1M $0.00000009/token | VisionCachingReasoningJSON schemaTools | |
| Ling 3.0 Flash v3fastlocal | Inclusionai | 127.5B | 262K | $0.021 | $0.063 | $0.032 /1M $0.000000031/token | CachingReasoningJSON schemaTools | |
| Schematron V2 Turbo v2fast | Inference Net | Undisclosed | 128K | $0.030 | $0.15 | $0.060 /1M $0.00000006/token | CachingJSON schema | |
| Schematron V2 Small v2fastlocal | Inference Net | 3B | 128K | $0.050 | $0.23 | $0.095 /1M $0.000000095/token | CachingJSON schema | |
| LFM2.5-24B-A2B v2.5fastlocal | Liquid AI | 24B (2B active) | 128K | $0.050 | $0.70 | $0.21 /1M $0.000000213/token | CachingReasoningJSON schemaTools | |
| LFM2.5-2.6B v2.5fastlocal | Liquid AI | 2.7B | 128K | $0.35 | $0.50 | $0.39 /1M $0.000000387/token | CachingReasoningJSON schemaTools | |
| Weaver (alpha) fast | Mancer | Undisclosed | 8K | $0.40 | $0.75 | $0.49 /1M $0.000000487/token | JSON schema | |
| LongCat 2.0 v2fastlocal | Meituan | 1.78T | 1.05M | $0.30 | $1.20 | $0.52 /1M $0.000000525/token | CachingReasoningTools | |
| Muse Spark Open balancedlocal | Meta | 822B (42B active) | 1.05M | $1.25 | $4.25 | $2.00 /1M $0.000002/token | VisionCachingReasoningJSON schemaTools | |
| Muse Wonder frontier | Meta | Undisclosed | 1.05M | $4.00 | $20.00 | $8.00 /1M $0.000008/token | VisionCachingReasoningJSON schemaTools | |
| Muse Spark 1.3 Contributor v1.3fast | Meta | Undisclosed | 1.05M | $0.10 | $0.20 | $0.13 /1M $0.000000125/token | VisionPDFCachingReasoningJSON schema+2 | |
| Muse Spark 1.3 v1.3balanced | Meta | Undisclosed | 1.05M | $1.25 | $4.25 | $2.00 /1M $0.000002/token | VisionPDFCachingReasoningJSON schema+2 | |
| Muse Spark 1.2 Contributor v1.2fast | Meta | Undisclosed | 1.05M | $0.10 | $0.20 | $0.13 /1M $0.000000125/token | VisionPDFCachingReasoningJSON schema+2 | |
| Muse Glimmer 30B fastlocal | Meta | 29.8B | 131K | $0.30 | $1.20 | $0.52 /1M $0.000000525/token | VisionCachingReasoningJSON schemaTools | |
| Muse Spark 1.2 v1.2balanced | Meta | Undisclosed | 1.05M | $1.25 | $4.25 | $2.00 /1M $0.000002/token | VisionPDFCachingReasoningJSON schema+2 | |
| Muse Spark 1.1 v1.1balanced | Meta | Undisclosed | 1.05M | $1.25 | $4.25 | $2.00 /1M $0.000002/token | VisionPDFCachingReasoningJSON schema+2 | |
| Llama Guard 4 12B v4fastlocal | Meta | 12B | 164K | $0.18 | $0.18 | $0.18 /1M $0.00000018/token | Vision |
Local LLMs
Open-weights models you can run on your own hardware: what to install, whether it fits your machine, whether it beats paying per token, and a live link to Ollama / LM Studio.
| Run it | ||||||
|---|---|---|---|---|---|---|
| Kimi K3.1 Pro Moonshot AI | 2.78T | 1797 GB | — | Hugging Face | $2.00 / $10.00 | 1.05M |
| Kimi K3 Moonshot AI | 2.78T | 1797 GB | — | Hugging Face | $3.00 / $15.00 | 1.05M |
| Qwen3.8 2.4T A95B Alibaba (Qwen) | 2.45T (95B active) | 1582 GB | — | Hugging Face | $2.00 / $6.00 | 1.05M |
| LongCat 2.0 Meituan | 1.78T | 1151 GB | — | Hugging Face | $0.30 / $1.20 | 1.05M |
| DeepSeek V4 Pro 0813 DeepSeek | 1.65T | 1070 GB | — | Hugging Face | $0.12 / $4.60 | 1.05M |
| DeepSeek V4 Pro 0423 DeepSeek | 1.6T | 1037 GB | — | Hugging Face | $1.32 / $3.96 | 1M |
| Kimi K2.6 Moonshot AI | 1.03T | 668 GB | — | Hugging Face | $0.95 / $4.00 | 262K |
| Kimi K2.7 Code Moonshot AI | 1.03T | 668 GB | — | Hugging Face | $0.95 / $4.00 | 262K |
| Kimi K2 0711 Moonshot AI | 1.03T | 668 GB | — | Hugging Face | $0.57 / $2.30 | 131K |
| Kimi K2 0905 Moonshot AI | 1.03T | 668 GB | — | Hugging Face | $0.60 / $2.50 | 262K |
Showing 1–10 of 144 local models
Memory is an estimate for Q4_K_M at 8K context. “Min. phone RAM” assumes a 4K context and that an app may use about half of the phone’s RAM; “Phone-ready” means it runs on a phone with 8 GB or less. “ollama run” tags come from a curated map (never guessed); verify with ollama show.
Advisor
Which model to use for what, and how to combine several to cut token cost. Task scores are heuristics: validate on your own data.
Which LLM should I use?
Describe your workload: tasks, volume, tokens per request, latency, privacy or hardware.
Data sync
The scheduler refreshes prices every 6 hours; every run is recorded.
Models
490 / 534
active / total
Newest data
85 min ago
Last run
success
85 min ago
| Started | Trigger | Status | New | Changed | Price changes | Alerts | Errors |
|---|---|---|---|---|---|---|---|
| 2026-11-05 03:20 | startup | success | 534 | 0 | 0 | 0 |