Live index · synced 31 min ago
Every LLM, priced per token.
Find the model that fits your workload and your budget: live prices, context and capabilities, and a routing plan from the advisor.
491 active models · 63 companies · 148 run locally
Market pulse
median blended $ / 1MFrontier81
Cheapest: DeepSeek V4 Pro 0813 $1.15
$8.00
Balanced136
Cheapest: Qwen3.5-122B-A10B $0.72
$2.00
Fast / cheap271
Cheapest: gpt-oss-120b $0.019
$0.35
Top models
Latest flagships and the best value per tier.
Each major lab's newest frontier model in the live catalogue, newest first. This is a release list, not a benchmark ranking: quality scores are not published here.
Latest flagships
All frontier models| Model | Blended / 1M |
|---|---|
1GPT-6.1 Terra ProOpenAI | $2.00 |
2Muse WonderMeta | $8.00 |
3GLM 5.3 PrimeZ.ai (Zhipu) · balanced tier | $4.30 |
4Qwen3.8 Max PrimeAlibaba (Qwen) | $6.00 |
5Claude Opus 5.5Anthropic | $8.00 |
6Grok 4.7xAI · balanced tier | $3.00 |
7Seed-2.0-CodeByteDance · balanced tier | $1.13 |
8DeepSeek V4 Pro 0813DeepSeek | $1.15 |
9Gemini 2.5 ProGoogle | $3.44 |
10Mistral Large 2407Mistral AI | $3.00 |
Best value by tier
All models- 1DeepSeek V4 Pro 0813$1.15
- 2Nova Pro 1.0$1.40
- 3Hermes 4 405B$1.50
- 4Doubao Seed 2.1 Pro 260915$1.73
- 5Doubao Seed 2.1 Pro 260628$1.73
- 1Qwen3.5-122B-A10B$0.72
- 2Nemotron 3 Super$0.82
- 3Moondream 3 Preview$0.85
- 4Gemini Exp 1206$0.85
- 5R1 0528$0.91
- 1gpt-oss-120b$0.019
- 2Ling 3.0 Tiny$0.022
- 3Mistral Nemo$0.029
- 4Ling 3.0 Flash$0.032
- 5Llama 3 8B Lunaris$0.042
Cheapest by blended price per 1M tokens (3 input : 1 output).
Recent price moves
All updates- DeepSeek V4.1 Flash 1017DeepSeek · 31 min agoin $0.15 → $0.30100%out $0.60 → $1.20100%
- Kimi Latest~moonshotai · 31 min agoin $0.15 → $0.1819%out $10.56 → $9.3412%
- gpt-oss-120bOpenAI · 31 min agoin $0.013 → $0.01115%out $0.048 → $0.04212%
- Kimi Latest~moonshotai · 2 h agoin $0.16 → $0.156%
- gpt-oss-120bOpenAI · 2 h agoin $0.014 → $0.0137%out $0.052 → $0.0488%
Market
Where the market sits right now.
Hover any mark for details. Prices are blended USD per 1M tokens at 3 input : 1 output.
Price against context window
491 active modelsPrice range by company
10 largest cataloguesLaunch price by release quarter
- Frontier
- Balanced
- Fast / cheap
Median of today's blended price for models released each quarter (quarters with fewer than 2 releases are skipped). Log scale.
Capabilities
share of 491 active models- Tools84%
- JSON schema84%
- Reasoning69%
- Caching67%
- Vision63%
- Web search25%
- PDF18%
- Batch16%
- Computer use8%
- Audio in7%
Tools
All models
Every model, priced per token.
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 |
|---|---|---|---|---|---|---|---|---|
| Qwen-Plus fast | Alibaba (Qwen) | Undisclosed | 129K | $0.40 | $1.20 | $0.60 /1M $0.0000006/token | CachingReasoningJSON schemaTools | |
| Qwen2.5 Coder 32B Instruct v2.5fastlocal | Alibaba (Qwen) | 32.8B | 33K | $0.66 | $1.00 | $0.74 /1M $0.000000745/token | JSON schema | |
| Qwen2.5 7B Instruct v2.5fastlocal | Alibaba (Qwen) | 7.6B | 33K | $0.10 | $0.20 | $0.13 /1M $0.000000125/token | JSON schemaTools | |
| Qwen2.5 72B Instruct v2.5fastlocal | Alibaba (Qwen) | 72.7B | 33K | $0.36 | $0.40 | $0.37 /1M $0.00000037/token | JSON schemaTools | |
| DeepSeek V4 Flash v4fast | Alibaba (Qwen) | Undisclosed | 1M | $0.20 | $0.40 | $0.25 /1M $0.00000025/token | CachingReasoningJSON schemaTools | |
| DeepSeek V4 Flash 0731 v4fast | Alibaba (Qwen) | Undisclosed | 1M | $0.20 | $0.40 | $0.25 /1M $0.00000025/token | CachingReasoningJSON schemaTools | |
| DeepSeek V4 Pro v4frontier | Alibaba (Qwen) | Undisclosed | 1M | $2.40 | $4.80 | $3.00 /1M $0.000003/token | CachingReasoningJSON schemaTools | |
| GLM 5.1 v5.1balanced | Alibaba (Qwen) | Undisclosed | 203K | $1.40 | $4.40 | $2.15 /1M $0.00000215/token | CachingReasoningJSON schemaTools | |
| GLM 5.2 v5.2balanced | Alibaba (Qwen) | Undisclosed | 1.05M | $1.40 | $4.40 | $2.15 /1M $0.00000215/token | CachingReasoningJSON schemaTools | |
| Kimi K2 7 Code v2.7balanced | Alibaba (Qwen) | Undisclosed | 229K | $0.95 | $4.00 | $1.71 /1M $0.000001712/token | VisionCachingReasoningJSON schemaTools |
Local LLMs
Run it on your own hardware.
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 | $0.11 / $4.28 | 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 148 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, for which job?
Which model to use for what, and how to combine several to cut token cost. Task scores are heuristics: validate on your own data.
Advisor
Which LLM should I use?
Describe your workload: tasks, volume, tokens per request, latency, privacy or hardware.
Data
Where the numbers come from.
The scheduler refreshes prices every 6 hours; every run is recorded.
Models
491 / 535
active / total
Newest data
31 min ago
Last run
success
31 min ago
| Started | Trigger | Status | New | Changed | Price changes | Alerts | Errors |
|---|---|---|---|---|---|---|---|
| 2026-11-05 07:48 | startup | success | 1 | 3 | 3 | 4 | |
| 2026-11-05 06:00 | cron | success | 0 | 10 | 5 | 15 | |
| 2026-11-05 03:20 | startup | success | 534 | 0 | 0 | 0 |