Runyard / LLM API Index · GPU Index →
LLM API Pricing Index
Input and output price per million tokens for 440 models from 59 vendors, in one schema. 418 are paid, 22 have a free tier. Blended price assumes 3 input tokens per output token, the ratio most chat and agent work lands near.
Last collected 2026-09-12 · 7 snapshots
Models priced
44059 vendors
Median paid model
$0.850/1M blended
Frontier tier
$20.00/1M blended
Cheapest paid
$0.022Mistral Nemo
Flagships, blended $/1M tokens
3 input : 1 output · as listed on OpenRouter
The spread is the story: the frontier tier costs 13× the cheapest flagship-class model on this chart, for work that often does not need it.
Every model
| Context | Cache read | 7D | ||||
|---|---|---|---|---|---|---|
 Mistral NemoMistral · mistralai/mistral-nemo | 131K | $0.019 | $0.030 | $0.022 | — | — |
| iLing 3.0 FlashinclusionAI · inclusionai/ling-3.0-flash | 262K | $0.021 | $0.063 | $0.032 | $0.0042 | — |
| ~DeepSeek V4 Flash Latest~Deepseek · ~deepseek/deepseek-v4-flash-latest | 1.3M | $0.030 | $0.070 | $0.040 | $0.0030 | — |
| IGranite 4.0 MicroIbm Granite · ibm-granite/granite-4.0-h-micro | 131K | $0.017 | $0.112 | $0.041 | — | — |
| SLlama 3 8B LunarisSao10k · sao10k/l3-lunaris-8b | 8K | $0.040 | $0.050 | $0.043 | — | — |
| 1.3M | $0.040 | $0.080 | $0.050 | $0.0080 | — | |
 Qwen3.7 FlashAlibaba Qwen · qwen/qwen3.7-flash | 1M | $0.030 | $0.130 | $0.055 | $0.0060 | — |
 gpt-oss-20bOpenAI · openai/gpt-oss-20b | 131K | $0.030 | $0.130 | $0.055 | $0.030 | — |
| Mistral Small 3Mistral · mistralai/mistral-small-24b-instruct-2501 | 33K | $0.050 | $0.080 | $0.058 | — | — |
 Llama 3.1 8B InstructMeta · meta-llama/llama-3.1-8b-instruct | 131K | $0.050 | $0.080 | $0.058 | $0.025 | — |
| ISchematron V2 TurboInference Net · inference-net/schematron-v2-turbo | 128K | $0.030 | $0.150 | $0.060 | — | — |
| GMythoMax 13BGryphe · gryphe/mythomax-l2-13b | 8K | $0.060 | $0.060 | $0.060 | — | — |
 Nova Micro 1.0Amazon · amazon/nova-micro-v1 | 128K | $0.035 | $0.140 | $0.061 | — | — |
 Gemma 3 4BGoogle · google/gemma-3-4b-it | 131K | $0.050 | $0.100 | $0.063 | — | — |
 Command R7B (12-2024)Cohere · cohere/command-r7b-12-2024 | 128K | $0.037 | $0.150 | $0.066 | — | — |
| IMercury 2.5Inception · inception/mercury-2.5 | 260K | $0.040 | $0.150 | $0.068 | $0.0040 | — |
| GPT-5 Nano (batch)OpenAI · openai/gpt-5-nano:batch | 400K | $0.025 | $0.200 | $0.069 | $0.0025 | — |
| gpt-oss-120bOpenAI · openai/gpt-oss-120b | 131K | $0.037 | $0.170 | $0.070 | — | — |
| Llama 3.2 1B InstructMeta · meta-llama/llama-3.2-1b-instruct | 60K | $0.027 | $0.201 | $0.070 | — | — |
| PLaguna XS 2.1Poolside · poolside/laguna-xs-2.1 | 262K | $0.060 | $0.120 | $0.075 | $0.030 | — |
| Ministral 3 8B 2512 (batch)Mistral · mistralai/ministral-8b-2512:batch | 262K | $0.075 | $0.075 | $0.075 | $0.0075 | — |
| Gemma 3 12BGoogle · google/gemma-3-12b-it | 131K | $0.050 | $0.150 | $0.075 | — | — |
 Hy-MT2-1.8BTencent · tencent/hy-mt2-1.8b | 8K | $0.044 | $0.177 | $0.077 | — | — |
| 1.0M | $0.066 | $0.131 | $0.082 | $0.013 | — | |
| Gemma 4 26B A4B Google · google/gemma-4-26b-a4b-it | 262K | $0.042 | $0.220 | $0.086 | — | — |
| 262K | $0.050 | $0.200 | $0.087 | $0.030 | — | |
| gpt-oss-20b (batch)OpenAI · openai/gpt-oss-20b:batch | 131K | $0.050 | $0.200 | $0.087 | — | — |
| Gemini 2.5 Flash Lite (batch)Google · google/gemini-2.5-flash-lite:batch | 1.0M | $0.050 | $0.200 | $0.087 | $0.010 | — |
| GPT-4.1 Nano (batch)OpenAI · openai/gpt-4.1-nano:batch | 1.0M | $0.050 | $0.200 | $0.087 | $0.013 | — |
| 16K | $0.070 | $0.140 | $0.087 | — | — | |
| iLing 3.0 Flash VLinclusionAI · inclusionai/ling-3.0-flash-vl | 131K | $0.060 | $0.180 | $0.090 | $0.012 | — |
| iLing 3.0 Flash FininclusionAI · inclusionai/ling-3.0-flash-fin | 262K | $0.060 | $0.180 | $0.090 | $0.012 | — |
| ISchematron V2 SmallInference Net · inference-net/schematron-v2-small | 128K | $0.050 | $0.230 | $0.095 | — | — |
| RReka EdgeRekaai · rekaai/reka-edge | 16K | $0.100 | $0.100 | $0.100 | — | — |
| Ministral 3 3B 2512Mistral · mistralai/ministral-3b-2512 | 131K | $0.100 | $0.100 | $0.100 | $0.010 | — |
| Nova Lite 1.0Amazon · amazon/nova-lite-v1 | 300K | $0.060 | $0.240 | $0.105 | — | — |
| Mistral Small 3.2 24BMistral · mistralai/mistral-small-3.2-24b-instruct | 256K | $0.075 | $0.200 | $0.106 | — | — |
| IGranite 4.2 8BIbm Granite · ibm-granite/granite-4.2-8b | 131K | $0.060 | $0.250 | $0.107 | $0.015 | — |
| 262K | $0.080 | $0.200 | $0.110 | $0.040 | — | |
| PLaguna S 2.1Poolside · poolside/laguna-s-2.1 | 1.0M | $0.090 | $0.180 | $0.113 | $0.0090 | — |
| Qwen3.5-9BAlibaba Qwen · qwen/qwen3.5-9b | 262K | $0.100 | $0.150 | $0.113 | — | — |
| Qwen3.5-FlashAlibaba Qwen · qwen/qwen3.5-flash-02-23 | 1M | $0.065 | $0.260 | $0.114 | — | — |
| ~GLM Flash Latest~Z Ai · ~z-ai/glm-flash-latest | 1.3M | $0.075 | $0.250 | $0.119 | $0.015 | — |
 GLM 5.3 Flash (batch)Z.ai (Zhipu) · z-ai/glm-5.3-flash:batch | 1.0M | $0.075 | $0.250 | $0.119 | $0.015 | — |
| Llama 3.2 3B InstructMeta · meta-llama/llama-3.2-3b-instruct | 131K | $0.050 | $0.330 | $0.120 | — | — |
| Qwen3 Coder 30B A3B InstructAlibaba Qwen · qwen/qwen3-coder-30b-a3b-instruct | 262K | $0.070 | $0.280 | $0.122 | — | — |
| MMuse Spark 1.3 ContributorMeta · meta/muse-spark-1.3-contributor | 1.0M | $0.100 | $0.200 | $0.125 | $0.0020 | — |
| MMuse Spark 1.2 ContributorMeta · meta/muse-spark-1.2-contributor | 1.0M | $0.100 | $0.200 | $0.125 | $0.0020 | — |
| BUI-TARS 7B Bytedance · bytedance/ui-tars-1.5-7b | 128K | $0.100 | $0.200 | $0.125 | $0.100 | — |
| RReka Flash 3Rekaai · rekaai/reka-flash-3 | 66K | $0.100 | $0.200 | $0.125 | — | — |
| Qwen2.5 7B InstructAlibaba Qwen · qwen/qwen-2.5-7b-instruct | 33K | $0.100 | $0.200 | $0.125 | — | — |
| Hy-MT2-30B-A3BTencent · tencent/hy-mt2-30b-a3b | 8K | $0.074 | $0.295 | $0.129 | — | — |
| Hy-MT2-7BTencent · tencent/hy-mt2-7b | 8K | $0.074 | $0.295 | $0.129 | — | — |
| Qwen3 32BAlibaba Qwen · qwen/qwen3-32b | 131K | $0.080 | $0.280 | $0.130 | — | — |
| Mistral Small 4 (batch)Mistral · mistralai/mistral-small-2603:batch | 262K | $0.075 | $0.300 | $0.131 | $0.0075 | — |
| BSeed 1.6 FlashBytedance Seed · bytedance-seed/seed-1.6-flash | 262K | $0.075 | $0.300 | $0.131 | — | — |
| gpt-oss-safeguard-20bOpenAI · openai/gpt-oss-safeguard-20b | 131K | $0.075 | $0.300 | $0.131 | $0.037 | — |
| GPT-4o-mini (batch)OpenAI · openai/gpt-4o-mini:batch | 128K | $0.075 | $0.300 | $0.131 | $0.037 | — |
| GPT-5 NanoOpenAI · openai/gpt-5-nano | 400K | $0.050 | $0.400 | $0.138 | $0.0050 | — |
| Qwen3 30B A3B Instruct 2507Alibaba Qwen · qwen/qwen3-30b-a3b-instruct-2507 | 262K | $0.090 | $0.300 | $0.142 | — | — |
| Hy3Tencent · tencent/hy3 | 262K | $0.083 | $0.330 | $0.144 | $0.021 | — |
| GLM 4.7 FlashZ.ai (Zhipu) · z-ai/glm-4.7-flash | 200K | $0.060 | $0.400 | $0.145 | — | — |
| SStep 3.5 FlashStepfun · stepfun/step-3.5-flash | 262K | $0.100 | $0.300 | $0.150 | — | — |
| Ministral 3 8B 2512Mistral · mistralai/ministral-8b-2512 | 262K | $0.150 | $0.150 | $0.150 | $0.015 | — |
| Voxtral Small 24B 2507Mistral · mistralai/voxtral-small-24b-2507 | 33K | $0.100 | $0.300 | $0.150 | $0.010 | — |
| Llama 4 ScoutMeta · meta-llama/llama-4-scout | 1.3M | $0.100 | $0.300 | $0.150 | — | — |
| Gemma 4 31BGoogle · google/gemma-4-31b-it | 262K | $0.090 | $0.340 | $0.152 | $0.050 | — |
| Qwen3 235B A22B Instruct 2507Alibaba Qwen · qwen/qwen3-235b-a22b-2507 | 262K | $0.087 | $0.350 | $0.153 | $0.018 | — |
| Llama 3.3 70B InstructMeta · meta-llama/llama-3.3-70b-instruct | 131K | $0.100 | $0.320 | $0.155 | — | — |
| USolar Pro 4Upstage · upstage/solar-pro4 | 524K | $0.090 | $0.360 | $0.158 | $0.018 | — |
| 262K | $0.085 | $0.400 | $0.164 | — | — | |
| 1.0M | $0.110 | $0.330 | $0.165 | $0.0035 | — | |
| 1.0M | $0.110 | $0.330 | $0.165 | $0.0035 | — | |
| Gemma 3 27BGoogle · google/gemma-3-27b-it | 131K | $0.080 | $0.450 | $0.172 | $0.040 | — |
| XMiMo-V2.5Xiaomi · xiaomi/mimo-v2.5 | 1.1M | $0.140 | $0.280 | $0.175 | $0.0028 | — |
| BSeed-2.0-MiniBytedance Seed · bytedance-seed/seed-2.0-mini | 262K | $0.100 | $0.400 | $0.175 | — | — |
| Gemini 2.5 Flash LiteGoogle · google/gemini-2.5-flash-lite | 1.0M | $0.100 | $0.400 | $0.175 | $0.010 | — |
| GPT-4.1 NanoOpenAI · openai/gpt-4.1-nano | 1.0M | $0.100 | $0.400 | $0.175 | $0.025 | — |
| Llama Guard 4 12BMeta · meta-llama/llama-guard-4-12b | 164K | $0.180 | $0.180 | $0.180 | — | — |
| Qwen3 VL 32B InstructAlibaba Qwen · qwen/qwen3-vl-32b-instruct | 131K | $0.104 | $0.416 | $0.182 | — | — |
80 of 418 models (free tiers hidden). Blended = 3 input tokens per output token. Prices as listed on OpenRouter on the date above.
Vendors
| Vendor | Models | Cheapest paid, blended |
|---|---|---|
| OpenAI | 93 | $0.055 |
| Alibaba Qwen | 53 | $0.055 |
| Google | 43 | $0.063 |
 Anthropic | 27 | $0.500 |
| Mistral | 25 | $0.022 |
| 18 | $0.050 | |
| Z.ai (Zhipu) | 17 | $0.119 |
| 10 | $0.087 | |
| 9 | $0.425 | |
| 8 | $0.900 | |
| Meta | 8 | $0.058 |
| MMeta | 7 | $0.125 |
| Tencent | 7 | $0.077 |
 xAI | 7 | $1.25 |
| iinclusionAI | 6 | $0.032 |
| BBytedance Seed | 6 | $0.131 |
 Thinking Machines | 6 | $0.637 |
| ~~Openai | 5 | $0.450 |
| Cohere | 5 | $0.066 |
| Amazon | 5 | $0.061 |
 Perplexity | 5 | $1.00 |
 Sakana AI | 4 | $1.71 |
| PPoolside | 4 | $0.075 |
| AAion Labs | 4 | $0.875 |
| ~~Anthropic | 4 | $2.00 |
| TThedrummer | 3 | $0.350 |
 Nous Research | 3 | $0.700 |
| SSao10k | 3 | $0.043 |
| IInference Net | 2 | $0.060 |
| IInception | 2 | $0.068 |
| NNex Agi | 2 | — |
| IIbm Granite | 2 | $0.041 |
| ~~Z Ai | 2 | $0.119 |
| UUpstage | 2 | $0.158 |
| KKwaipilot | 2 | $0.525 |
| SStepfun | 2 | $0.150 |
| 2 | $1.50 | |
| XXiaomi | 2 | $0.175 |
| RRekaai | 2 | $0.100 |
| RRelace | 2 | $0.950 |
| MMorph | 2 | $0.900 |
| 2 | $0.087 | |
| DDots Studio | 1 | — |
 Liquid AI | 1 | — |
| ~~Deepseek | 1 | $0.040 |
| MMeituan | 1 | $0.525 |
| ~~X Ai | 1 | $3.00 |
| PPerceptron | 1 | $0.487 |
| ~~Moonshotai | 1 | $5.11 |
| AArcee Ai | 1 | $0.388 |
| OOpenrouter | 1 | — |
| WWriter | 1 | $1.95 |
| BBytedance | 1 | $0.125 |
| CCognitivecomputations | 1 | $0.375 |
| 1 | $0.627 | |
| AAnthracite Org | 1 | $3.13 |
| MMancer | 1 | $0.487 |
| UUndi95 | 1 | $0.425 |
| GGryphe | 1 | $0.060 |
How this is built
Prices are read from OpenRouter's public model list, which routes to each vendor and publishes the per-token price it charges — for nearly every model, the vendor's own list price passed through. It is the one place all vendors appear in one schema, which is why it is the source. Prices are shown as listed there; a vendor's direct price can differ, especially with volume discounts or provisioned throughput, and OpenRouter's own listing is the reference for what is shown.
Every collector run is stored as a snapshot and committed to the repository, so price changes are diffs anyone can inspect. Nothing is backfilled. The 7-day column compares a model against itself a week earlier and is blank until that run exists.
Blended weights input at 3 and output at 1. Change the ratio and the ranking changes — an output-heavy workload makes the frontier tier relatively more expensive, since output tokens cost five times input on most frontier models.
What the same tokens cost on hardware you rent or own.
Local cost per million tokens →