Token Price Index
What LLM tokens cost, channel by channel.
List prices for model APIs from vendors, clouds and aggregators. Each number links to the page it came from, with the time it was observed and a hash of what we saw.
2026-11-15DeepSeek V4.1 Flash is 83% cheaper on OpenRouter0.30 → 0.0507
AuraMatrix token price indicestrialOfficial list prices by tier, 2026-11-03 = 100. How it is built · JSON
GPU-hour reference pricestrialMedian on-demand price for one GPU for one hour across providers. How it is built
Moved in the last 7 days
- GLM-5.3-FlashOpenRouter▼ 73%0.15 → 0.0399
- GLM-5.3OpenRouter▲ 20%0.0699 → 0.084
- DeepSeek V4 ProOpenRouter▲ 2.2%0.8804 → 0.90
- DeepSeek V4.1 FlashOpenRouter▼ 0.6%0.051 → 0.0507
Announced, not yet in force
- Gemini 4 ArgonGemini Developer API2026-12-012.00 → 4.00
- Gemini 4 ArgonGemini Developer API · Batch2026-12-011.00 → 2.00
- Gemini 3.8 FlashGemini Developer API2027-01-010.75 → 1.50
- Gemini 3.8 FlashGemini Developer API · Batch2027-01-010.375 → 0.75
New in the index
- Claude Fable 5.22026-11-09
- Claude Mythos 5.22026-11-09
123 / 123 prices matched their sources at the last daily check →
New to token prices? What do these numbers mean in practice? Real jobs, priced →
Use in your AIConnect
Use in your AI
Connect once, then just ask: "Where is Claude Opus 5.5 cheapest?", "What does an H100 cost per hour?", "Which models got cheaper this week?" Your assistant answers from this index, with the source for every number. Free, read-only, no account.
{
"mcpServers": {
"auramatrix": {
"url": "https://auramatrix.ai/mcp"
}
}
}24 of 24 models
| Model | Vendor | Inputofficial | Outputofficial | Lowest inputany channel | Channels | Official status |
|---|---|---|---|---|---|---|
| Alibaba (Qwen) | 2.00 | 6.00 | 1.65Model Studio, China (Beijing) · −18% | 4 | VERIFIED | |
| Alibaba (Qwen) | 0.15 | 0.47 | 0.113Model Studio, China (Beijing) · −25% | 4 | VERIFIED | |
| Anthropic | 10.00 | 50.00 | 10.00official is lowest | 2 | VERIFIED | |
| Anthropic | 8.00 | 40.00 | 8.00official is lowest | 1 | VERIFIED | |
| Anthropic | 8.00 | 40.00 | 8.00official is lowest | 1 | VERIFIED | |
| Anthropic | 4.00 | 20.00 | 4.00official is lowest | 2 | VERIFIED | |
| Anthropic | 2.00 | 10.00 | 2.00official is lowest | 2 | VERIFIED | |
| Anthropic | 0.10 | 0.50 | 0.10official is lowest | 2 | VERIFIED | |
| DeepSeek V4 Prodeepseek/deepseek-v4-pro | DeepSeek | 1.32 | 3.96 | 0.90OpenRouter · −32% | 3 | VERIFIED |
| DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flash | DeepSeek | 0.30 | 1.20 | 0.0507OpenRouter · −83% | 3 | VERIFIED |
| 2.00 | 10.00 | 2.00official is lowest | 4 | VERIFIED | ||
| 0.75 | 3.75 | 0.75official is lowest | 4 | VERIFIED | ||
| 0.30 | 2.50 | 0.30official is lowest | 4 | VERIFIED | ||
| Meta | — | — | 0.24Amazon Bedrock, US East (N. Virginia) | 2 | no official price | |
| MiniMax M3minimax/minimax-m3 | MiniMax | 0.30 | 1.20 | 0.30official is lowest | 3 | VERIFIED |
| MiniMax M3.1 Flashminimax/minimax-m3.1-flash | MiniMax | 0.15 | 0.60 | 0.075OpenRouter · −50% | 3 | VERIFIED |
| Kimi K3moonshot/kimi-k3 | Moonshot AI (Kimi) | 3.00 | 15.00 | 3.00official is lowest | 4 | VERIFIED |
| Kimi K3.1 Promoonshot/kimi-k3.1-pro | Moonshot AI (Kimi) | 2.00 | 10.00 | 2.00official is lowest | 3 | VERIFIED |
| OpenAI | 10.00 | 50.00 | 10.00official is lowest | 5 | VERIFIED | |
| OpenAI | 2.00 | 10.00 | 2.00official is lowest | 5 | VERIFIED | |
| OpenAI | 1.00 | 5.00 | 1.00official is lowest | 5 | VERIFIED | |
| OpenAI | 0.10 | 0.50 | 0.10official is lowest | 5 | VERIFIED | |
| GLM-5.3zhipu/glm-5.3 | Zhipu AI (Z.ai) | 1.40 | 4.40 | 0.084OpenRouter · −94% | 3 | VERIFIED |
| GLM-5.3-Flashzhipu/glm-5.3-flash | Zhipu AI (Z.ai) | 0.15 | 0.50 | 0.0399OpenRouter · −73% | 3 | VERIFIED |
Cheapest in class
How to read this
Tiers follow each vendor's own positioning of a model within its lineup (flagship, mid-range, small/fast). They are an editorial grouping for comparing like with like, not a capability ranking. Ranked by official input price per 1M tokens, with output price alongside. Rank changes will appear once we have history.
Flagship
Each vendor's top model.
- 1MiniMax M30.30 / 1.20
- 2DeepSeek V4 Pro1.32 / 3.96
- 3GLM-5.31.40 / 4.40
- 4
Qwen3.8 Max2.00 / 6.00
- 5
Gemini 4 Argon2.00 / 10.00
- 6Kimi K3.1 Pro2.00 / 10.00
- 7Kimi K33.00 / 15.00
- 8
Claude Opus 5.54.00 / 20.00
- 9
Claude Fable 5.28.00 / 40.00
- 10
Claude Mythos 5.28.00 / 40.00
- 11
Claude Fable 5.110.00 / 50.00
- 12
GPT-6 Astra10.00 / 50.00
Mid-range
The balanced model in the lineup.
- 1
Gemini 3.8 Flash0.75 / 3.75
- 2
GPT-6.1 Terra1.00 / 5.00
- 3
Claude Sonnet 5.52.00 / 10.00
- 4
GPT-6.1 Sol2.00 / 10.00
- –
Llama 4 Maverick0.24 on AWS
Small and fast
The cheapest model each vendor pitches for high volume.
- 1
Claude Haiku 5.50.10 / 0.50
- 2
GPT-6 Luna0.10 / 0.50
- 3
Qwen3.8 Flash0.15 / 0.47
- 4GLM-5.3-Flash0.15 / 0.50
- 5MiniMax M3.1 Flash0.15 / 0.60
- 6DeepSeek V4.1 Flash0.30 / 1.20
- 7
Gemini 3.5 Flash-Lite0.30 / 2.50
Price ladder
How to read this
Official list price per 1M tokens, log scale. Input is the solid bar, output is the lighter one. Models without an official price are not shown.
Claude Fable 5.1
GPT-6 Astra
Claude Fable 5.2
Claude Mythos 5.2
Claude Opus 5.5
- Kimi K3
Qwen3.8 Max
Claude Sonnet 5.5
Gemini 4 Argon
- Kimi K3.1 Pro
GPT-6.1 Sol
- GLM-5.3
- DeepSeek V4 Pro
GPT-6.1 Terra
Gemini 3.8 Flash
- DeepSeek V4.1 Flash
Gemini 3.5 Flash-Lite
- MiniMax M3
Qwen3.8 Flash
- MiniMax M3.1 Flash
- GLM-5.3-Flash
Claude Haiku 5.5
GPT-6 Luna
Same model, different region
How to read this
Where an operator publishes different prices by region or deployment. Input price per 1M tokens; the cheapest region is the baseline.
Qwen3.8 MaxAlibaba Cloud
CNChinaChina (Beijing)1.65base
SGSingaporeInternational (Singapore)2.00+21%
Qwen3.8 FlashAlibaba Cloud
CNChinaChina (Beijing)0.113base
SGSingaporeInternational (Singapore)0.15+33%
Gemini 4 ArgonGoogle Cloud
- globalGlobal endpointglobal endpoint4.00base
- regionalRegional endpointsregional endpoint (any pinned region)4.40+10%
Gemini 3.8 FlashGoogle Cloud
- globalGlobal endpointglobal endpoint1.50base
- regionalRegional endpointsregional endpoint (any pinned region)1.65+10%
Gemini 3.5 Flash-LiteGoogle Cloud
- globalGlobal endpointglobal endpoint0.30base
- regionalRegional endpointsregional endpoint (any pinned region)0.33+10%
Kimi K3AWS
- globalGlobal endpointglobal cross-region3.00base
USUnited StatesUS East (N. Virginia)3.30+10%
GPT-6 AstraMicrosoft Azure
- globalGlobal endpointGlobal deployment10.00base
USUnited StatesData Zone (US)11.00+10%
EUEuropean UnionData Zone (EU)12.00+20%
GPT-6.1 SolMicrosoft Azure
- globalGlobal endpointGlobal deployment2.00base
USUnited StatesData Zone (US)2.20+10%
EUEuropean UnionData Zone (EU)2.40+20%
GPT-6.1 TerraMicrosoft Azure
- globalGlobal endpointGlobal deployment1.00base
USUnited StatesData Zone (US)1.10+10%
EUEuropean UnionData Zone (EU)1.20+20%
GPT-6 LunaMicrosoft Azure
- globalGlobal endpointGlobal deployment0.10base
USUnited StatesData Zone (US)0.11+10%
EUEuropean UnionData Zone (EU)0.12+20%
One job, every model
How to read this
Cost of sending 1,000,000 input tokens and receiving 100,000 output tokens at each model's official list price. Cached, batch and tier rates are not applied. Each vendor counts tokens with its own tokenizer, so the same text is not the same number of tokens everywhere; this compares prices per token, not the cost of a given document.
Claude Haiku 5.5$0.15
GPT-6 Luna$0.15
Qwen3.8 Flash$0.20
- GLM-5.3-Flash$0.20
- MiniMax M3.1 Flash$0.21
- DeepSeek V4.1 Flash$0.42
- MiniMax M3$0.42
Gemini 3.5 Flash-Lite$0.55
Gemini 3.8 Flash$1.13
GPT-6.1 Terra$1.50
- DeepSeek V4 Pro$1.72
- GLM-5.3$1.84
Qwen3.8 Max$2.60
Claude Sonnet 5.5$3.00
Gemini 4 Argon$3.00
- Kimi K3.1 Pro$3.00
GPT-6.1 Sol$3.00
- Kimi K3$4.50
Claude Opus 5.5$6.00
Claude Fable 5.2$12
Claude Mythos 5.2$12
Claude Fable 5.1$15
GPT-6 Astra$15
Who moves the most tokens on OpenRouter
Share of all tokens routed through OpenRouter on 2026-11-03 (165.3T tokens that day), as published on its rankings page. This is one marketplace's traffic, weighted toward open-weight and low-price models; traffic that goes straight to vendor APIs is not visible to anyone.
- DeepSeek V4.1 FlashDeepSeek42.6%70.4T
- GLM-5.3-FlashZhipu AI9.9%16.4T
- hy4-previewtencent5.7%9.5T
GPT-6 LunaOpenAI5.6%9.3T
- step-5-previewstepfun4.0%6.7T
Claude Opus 5.5Anthropic4.0%6.7T
- MiniMax M3.1 FlashMiniMax3.9%6.5T
gpt-5.6-lunaOpenAI3.2%5.3T
GPT-6.1 SolOpenAI2.5%4.0T
- deepseek-v4-flashDeepSeek2.3%3.8T
- GLM-5.3Zhipu AI2.2%3.7T
- jev-1.13typesafe1.9%3.2T
Source: OpenRouter rankings page (embedded daily model stats), fetched 2026-11-04 05:46 UTC, snapshot SHA-256 ce75bb289e41396a…. Models without a link are not in the price index yet.
What changed
Price changes seen between successive records from the same source, and changes vendors have announced with a date. Recording began 2026-11-03; every record stays, so this list only grows. JSON feed.
- 2027-01-01ANNOUNCED
Gemini 3.8 FlashGemini Developer APIin 0.75 → 1.50 · out 3.75 → 7.50 from 2027-01-01; current price valid until 2026-12-31
- 2027-01-01ANNOUNCED
Gemini 3.8 FlashGemini Developer API · Batchin 0.375 → 0.75 · out 1.875 → 3.75 from 2027-01-01; current price valid until 2026-12-31
- 2026-12-01ANNOUNCED
Gemini 4 ArgonGemini Developer APIin 2.00 → 4.00 · out 10.00 → 20.00 from 2026-12-01; current price valid until 2026-11-30
- 2026-12-01ANNOUNCED
Gemini 4 ArgonGemini Developer API · Batchin 1.00 → 2.00 · out 5.00 → 10.00 from 2026-12-01; current price valid until 2026-11-30
- 2026-11-15OBSERVEDDeepSeek V4.1 FlashOpenRouterin 0.30 → 0.0507 · out 1.20 → 0.2028 observed 2026-11-15 22:15 UTC
- 2026-11-13OBSERVEDDeepSeek V4 ProOpenRouterin 0.889 → 0.90 · out 1.7779 → 1.50 observed 2026-11-13 22:15 UTC
- 2026-11-13OBSERVEDKimi K3.1 ProOpenRouterin 0.2375 → 2.00 · out 8.4114 → 10.00 observed 2026-11-13 22:15 UTC
- 2026-11-13OBSERVEDGLM-5.3OpenRouterin 0.0699 → 0.084 · out 1.40 → 3.60 observed 2026-11-13 22:15 UTC
- 2026-11-12OBSERVEDDeepSeek V4 ProOpenRouterin 0.8754 → 0.889 · out 1.7508 → 1.7779 observed 2026-11-12 22:15 UTC
- 2026-11-12OBSERVEDDeepSeek V4.1 FlashOpenRouterin 0.051 → 0.30 · out 0.567 → 1.20 observed 2026-11-12 22:15 UTC
- 2026-11-12OBSERVEDKimi K3.1 ProOpenRouterin 2.00 → 0.2375 · out 10.00 → 8.4114 observed 2026-11-12 22:15 UTC
- 2026-11-11OBSERVEDDeepSeek V4 ProOpenRouterin 0.889 → 0.8754 · out 1.7779 → 1.7508 observed 2026-11-11 22:15 UTC
19 more in the feed.