LLM Token Counter

Get real-time LLM pricing in Claude Code and Cursor. Try Price Per Token MCP Token Counter & LLM Pricing Calculator - GPT-5, Claude, Gemini & More (Free)Price Per Token Token Counter Count tokens for GPT-5, Claude, Gemini, Llama, and DeepSeek. Estimate API costs and compare pricing across 300+ LLM models in real-time. 8 Ways to Use Fewer TokensGet the free PDF guide — practical tips to cut your token usage and API costs. Subscribe to the Price Per Token newsletter and download instantly.Download Now Last updated: March 26, 2026 at 05:10 PMEstimate the cost of a promptEnter your prompt:Or enter amounts directlyInput TokensOutput TokensAPI CallsCalculate by Tokens Words Characters Columns Provider Model Input Output Est. Tokens Input Cost Output Cost Actions Deepcogitocogito-v1-preview-llama-70b-turbo $0.000 $0.000 --- Try Vote ZZ-aiglm-5-fp4 $0.000 $0.000 --- Try Vote Googlegemma-3-270m-it $0.000 $0.000 --- Try Vote Mistral AIdevstral-small-2505 $0.000 $0.000 --- Try Vote Fireworkssarvam-m $0.000 $0.000 --- Try Vote Fireworksapriel-1.5-15b-thinker $0.000 $0.000 --- Try Vote Fireworksapriel-1.6-15b-thinker $0.000 $0.000 --- Try Vote Fireworkscwm $0.000 $0.000 --- Try Vote Qwenqwen2-1.5b $0.000 $0.000 --- Try Vote Qwenqwen3-0.6b-base $0.000 $0.000 --- Try Vote Qwenqwen3-14b-base $0.000 $0.000 --- Try Vote Qwenqwen3-1.7b-base $0.000 $0.000 --- Try Vote Qwenqwen3-30b-a3b-base $0.000 $0.000 --- Try Vote Qwenqwen3-4b-base $0.000 $0.000 --- Try Vote Qwenqwen3-8b-base $0.000 $0.000 --- Try Vote Fireworksdeepcoder-14b-preview $0.000 $0.000 --- Try Vote Qwenqwen3.5-0.8b $0.010 $0.050 --- Try Vote Liquidlfm2-8b-a1b $0.010 $0.020 --- Try Vote Liquidlfm-2.2-6b $0.010 $0.020 --- Try Vote Deepseekdeepseek-chat $0.014 $0.028 --- Try Vote IBIbm-granitegranite-4.0-h-micro $0.017 $0.110 --- Try Vote Qwenqwen3.5-2b $0.020 $0.100 --- Try Vote Googlegemma-3n-e4b-it $0.020 $0.040 --- Try Vote Meta-llamallama-3.2-1b-instruct $0.020 $0.020 --- Try Vote Meta-llamallama-3.1-8b-instruct $0.020 $0.050 --- Try Vote Mistral AImistral-nemo $0.020 $0.040 --- Try Vote Qwenqwen2-1.5b-instruct $0.020 $0.020 --- Try Vote Qwenqwen3.5-4b $0.030 $0.150 --- Try Vote Mistral AImistral-small-3.1-24b-instruct $0.030 $0.110 --- Try Vote Liquidailfm2-24b-a2b $0.030 $0.120 --- Try Vote Liquidlfm-2-24b-a2b $0.030 $0.120 --- Try Vote OpenAIgpt-oss-20b $0.030 $0.100 --- Try Vote Qwenqwen2.5-coder-7b-instruct $0.030 $0.090 --- Try Vote Meta-llamallama-3.2-3b-instruct $0.030 $0.050 --- Try Vote Googlegemma-2-9b-it $0.030 $0.080 --- Try Vote Meta-llamallama-3-8b-instruct $0.030 $0.040 --- Try Vote Qwenqwen-turbo $0.033 $0.130 --- Try Vote Amazonnova-micro-v1 $0.035 $0.140 --- Try Vote Coherecommand-r7b-12-2024 $0.037 $0.150 --- Try Vote OpenAIgpt-oss-120b $0.039 $0.100 --- Try Vote Deepseekdeepseek-r1-distill-llama-8b $0.040 $0.040 --- Try Vote Nvidianemotron-nano-9b-v2 $0.040 $0.160 --- Try Vote Qwenqwen3.5-9b $0.040 $0.150 --- Try Vote Googlegemma-3-4b-it $0.040 $0.080 --- Try Vote Googlegemma-3-12b-it $0.040 $0.130 --- Try Vote Mistral AIministral-3b $0.040 $0.040 --- Try Vote Qwenqwen-2.5-7b-instruct $0.040 $0.100 --- Try Vote MSao10kl3-lunaris-8b $0.040 $0.050 --- Try Vote ARArcee AItrinity-mini $0.045 $0.150 --- Try Vote Meta-llamallama-3.2-11b-vision-instruct $0.049 $0.049 --- Try Vote Qwenqwen3-8b $0.050 $0.200 --- Try Vote Mistral AImistral-small-24b-instruct-2501 $0.050 $0.080 --- Try Vote AAllenaiolmo-2-0325-32b-instruct $0.050 $0.200 --- Try Vote Nvidianemotron-3-nano-30b-a3b $0.050 $0.200 --- Try Vote Meta-llamallama-3-8b $0.050 $0.080 --- Try Vote OpenAIgpt-5-nano $0.050 $0.400 --- Try Vote OpenAIgpt-4.1-nano $0.050 $0.200 --- Try Vote Mistral AImistral-7b-instruct $0.059 $0.059 --- Try Vote Amazonnova-lite-v1 $0.060 $0.240 --- Try Vote ZZ-aiglm-4.7-flash $0.060 $0.400 --- Try Vote Qwenqwen3-14b $0.060 $0.200 --- Try Vote Nousresearchopenchat-7b $0.060 $0.060 --- Try Vote GRGryphemythomax-l2-13b $0.060 $0.060 --- Try Vote Qwenqwen3.5-flash $0.065 $0.260 --- Try Vote Microsoftphi-4 $0.065 $0.140 --- Try Vote Baiduernie-4.5-21b-a3b-thinking $0.070 $0.280 --- Try Vote Baiduernie-4.5-21b-a3b $0.070 $0.280 --- Try Vote Qwenqwen3-coder-30b-a3b-instruct $0.070 $0.270 --- Try Vote Mistral AIdevstral-small $0.070 $0.280 --- Try Vote Googlegemma-7b-it $0.070 $0.070 --- Try Vote Qwenqwen3-235b-a22b-2507 $0.071 $0.100 --- Try Vote Bytedance-seedseed-1.6-flash $0.075 $0.300 --- Try Vote Mistral AImistral-small-3.2-24b-instruct $0.075 $0.200 --- Try Vote Googlegemini-2.0-flash-lite-001 $0.075 $0.300 --- Try Vote Qwenqwen3-30b-a3b-thinking-2507 $0.080 $0.300 --- Try Vote Qwenqwen3-30b-a3b $0.080 $0.280 --- Try Vote Qwenqwen3-32b $0.080 $0.240 --- Try Vote Meta-llamallama-4-scout $0.080 $0.300 --- Try Vote Googlegemma-3-27b-it $0.080 $0.160 --- Try Vote Qwenqwen3-vl-8b-instruct $0.080 $0.200 --- Try Vote XXiaomimimo-v2-flash $0.090 $0.290 --- Try Vote ALAlibabatongyi-deepresearch-30b-a3b $0.090 $0.400 --- Try Vote Qwenqwen3-next-80b-a3b-instruct $0.090 $0.780 --- Try Vote Qwenqwen3-30b-a3b-instruct-2507 $0.090 $0.300 --- Try Vote Qwenqwen3-next-80b-a3b-thinking $0.098 $0.300 --- Try Vote Nvidianemotron-3-super-120b-a12b $0.100 $0.500 --- Try Vote Nvidianvidia-nemotron-3-super-120b-a12b $0.100 $0.500 --- Try Vote Qwenqwen1.5.0.5b $0.100 $0.100 --- Try Vote Qwenqwen1.5.0.5b-chat $0.100 $0.100 --- Try Vote Googlecodegemma-2b $0.100 $0.100 --- Try Vote Bytedanceui-tars-1.5-7b $0.100 $0.200 --- Try Vote Googlegemini-2.5-flash-lite-preview-09-2025 $0.100 $0.400 --- Try Vote Deepcogitocogito-v1-preview-llama-3b $0.100 $0.100 --- Try Vote Qwenqwen2-vl-2b-instruct $0.100 $0.100 --- Try Vote SStepfun-aistep-3.5-flash $0.100 $0.300 --- Try Vote Qwenqwen2.5-coder-3b-instruct $0.100 $0.100 --- Try Vote Deepseekdeepseek-coder-1b-base $0.100 $0.100 --- Try Vote Mistral AIvoxtral-small-24b-2507 $0.100 $0.300 --- Try Vote Mistral AImistral-small-creative $0.100 $0.300 --- Try Vote Googlegemma-2b-it $0.100 $0.100 --- Try Vote Qwenqwen2.5-coder-3b $0.100 $0.100 --- Try Vote Qwenqwen2.5-vl-3b-instruct $0.100 $0.100 --- Try Vote Mistral AIministral-3b-2512 $0.100 $0.100 --- Try Vote Nvidiallama-3.3-nemotron-super-49b-v1.5 $0.100 $0.400 --- Try Vote Meta-llamallama-3.2-1b $0.100 $0.100 --- Try Vote Meta-llamallama-3.2-3b $0.100 $0.100 --- Try Vote ZZ-aiglm-4-32b $0.100 $0.100 --- Try Vote Googlegemini-2.5-flash-lite $0.100 $0.400 --- Try Vote Googlegemini-2.0-flash-001 $0.100 $0.400 --- Try Vote Meta-llamallama-3.3-70b-instruct $0.100 $0.320 --- Try Vote Bytedance-seedseed-2.0-mini $0.100 $0.400 --- Try Vote Mistral AIministral-8b $0.100 $0.100 --- Try Vote Googlegemma-2b $0.100 $0.100 --- Try Vote Mistral AIpixtral-12b $0.100 $0.100 --- Try Vote Googlegemma-3-1b-it $0.100 $0.100 --- Try Vote Mistral AImistral-small $0.100 $0.300 --- Try Vote Qwenqwen3-vl-32b-instruct $0.104 $0.416 --- Try Vote Mistral AImistral-7b-instruct-v0.1 $0.110 $0.190 --- Try Vote Qwenqwen3-vl-8b-thinking $0.117 $1.365 --- Try Vote Qwenqwen3-coder-next $0.120 $0.750 --- Try Vote Qwenqwen-2.5-72b-instruct $0.120 $0.390 --- Try Vote OpenAIgpt-5-mini $0.125 $1.000 --- Try Vote Googlegemini-1.0-pro $0.125 $0.375 --- Try Vote ZZ-aiglm-4.5-air $0.130 $0.850 --- Try Vote Nousresearchhermes-4-70b $0.130 $0.400 --- Try Vote Qwenqwen3-vl-30b-a3b-thinking $0.130 $0.600 --- Try Vote Qwenqwen3-vl-30b-a3b-instruct $0.130 $0.520 --- Try Vote Nex-AGIdeepseek-v3.1-nex-n1 $0.135 $0.500 --- Try Vote Qwenqwen-vl-plus $0.137 $0.409 --- Try Vote Tencenthunyuan-a13b-instruct $0.140 $0.570 --- Try Vote Baiduernie-4.5-vl-28b-a3b $0.140 $0.560 --- Try Vote Nousresearchhermes-2-pro-llama-3-8b $0.140 $0.140 --- Try Vote Mistral AImistral-7b-instruct-v0.3 $0.140 $0.200 --- Try Vote Mistral AImistral-tiny $0.140 $0.420 --- Try Vote Mistral AImistral-7b-instruct-v0.2 $0.140 $0.200 --- Try Vote Mistral AImixtral-8x7b-instruct $0.140 $0.420 --- Try Vote Qwenqwen3-235b-a22b-thinking-2507 $0.149 $0.900 --- Try Vote Mistral AImistral-small-2603 $0.150 $0.600 --- Try Vote AAllenaiolmo-3.1-32b-think $0.150 $0.500 --- Try Vote AAllenaiolmo-3-32b-think $0.150 $0.500 --- Try Vote EEssential AIrnj-1-instruct $0.150 $0.150 --- Try Vote Coherecommand-r-08-2024 $0.150 $0.600 --- Try Vote Mistral AIministral-8b-2512 $0.150 $0.150 --- Try Vote Deepseekdeepseek-chat-v3.1 $0.150 $0.750 --- Try Vote Meta-llamallama-4-maverick $0.150 $0.600 --- Try Vote Qwenqwq-32b $0.150 $0.580 --- Try Vote Coherecommand-r $0.150 $0.600 --- Try Vote Deepseekdeepseek-r1-distill-qwen-14b $0.150 $0.150 --- Try Vote OpenAIgpt-4o-mini $0.150 $0.600 --- Try Vote Qwenqwen3.5-35b-a3b $0.163 $1.000 --- Try Vote Nousresearchopenhermes-2.5-mistral-7b $0.170 $0.170 --- Try Vote Nousresearchnous-hermes-llama2-13b $0.170 $0.170 --- Try Vote TDThedrummerrocinante-12b $0.170 $0.430 --- Try Vote ARArcee AIspotlight $0.180 $0.180 --- Try Vote Deepseekdeepseek-r1-distill-qwen-1.5b $0.180 $0.180 --- Try Vote Qwenqwen3.5-27b $0.195 $1.560 --- Try Vote Qwenqwen3-coder-flash $0.195 $0.975 --- Try Vote OpenAIgpt-5.4-nano $0.200 $1.250 --- Try Vote AAllenaiolmo-3.1-32b-instruct $0.200 $0.600 --- Try Vote Qwenqwen2.5-coder-7b $0.200 $0.200 --- Try Vote Meta-llamacode-llama-7b-instruct $0.200 $0.200 --- Try Vote Mistral AIsnorkel-mistral-7b-pairrm-dpo $0.200 $0.200 --- Try Vote Qwenqwen2.5-coder-14b-instruct $0.200 $0.200 --- Try Vote Qwenqwen2.5-14b-instruct $0.200 $0.200 --- Try Vote Qwenqwen2.5-0.5b-instruct $0.200 $0.200 --- Try Vote OpenAItext-ada-001 $0.200 $0.200 --- Try Vote Googlecodegemma-7b $0.200 $0.200 --- Try Vote Nousresearchchronos-hermes-13b-v2 $0.200 $0.200 --- Try Vote MMeituanlongcat-flash-chat $0.200 $0.800 --- Try Vote Mistral AImistral-saba $0.200 $0.600 --- Try Vote Minimaxminimax-m2.5 $0.200 $0.950 --- Try Vote Qwenqwen2-vl-7b-instruct $0.200 $0.200 --- Try Vote AAllenaimolmo2-4b $0.200 $0.200 --- Try Vote Eleutheraipythia-12b $0.200 $0.200 --- Try Vote Meta-llamacode-llama-13b $0.200 $0.200 --- Try Vote Meta-llamacode-llama-13b-instruct $0.200 $0.200 --- Try Vote Meta-llamacode-llama-13b-python $0.200 $0.200 --- Try Vote Meta-llamacode-llama-7b $0.200 $0.200 --- Try Vote Mistral AIopenorca-7b $0.200 $0.200 --- Try Vote Qwenqwen2-7b-instruct $0.200 $0.200 --- Try Vote Qwenqwen3-4b $0.200 $0.200 --- Try Vote AAllenaimolmo-2-8b $0.200 $0.200 --- Try Vote Qwencode-qwen-1.5-7b $0.200 $0.200 --- Try Vote Qwenqwen2.5-14b $0.200 $0.200 --- Try Vote Qwenqwen2.5-1.5b-instruct $0.200 $0.200 --- Try Vote Qwenqwen2.5-7b $0.200 $0.200 --- Try Vote Qwenqwen2.5-coder-0.5b $0.200 $0.200 --- Try Vote Qwenqwen2.5-coder-0.5b-instruct $0.200 $0.200 --- Try Vote Qwenqwen2.5-coder-14b $0.200 $0.200 --- Try Vote Qwenqwen2.5-coder-1.5b $0.200 $0.200 --- Try Vote Qwenqwen3-0.6b $0.200 $0.200 --- Try Vote Qwenqwen3-4b-instruct-2507 $0.200 $0.200 --- Try Vote Deepcogitocogito-v1-preview-llama-8b $0.200 $0.200 --- Try Vote Deepcogitocogito-v1-preview-qwen-14b $0.200 $0.200 --- Try Vote Deepseekdeepseek-coder-7b-base $0.200 $0.200 --- Try Vote Nousresearchtoppy-m-7b $0.200 $0.200 --- Try Vote Nousresearchzephyr-7b-beta $0.200 $0.200 --- Try Vote PPrime-intellectintellect-3 $0.200 $1.100 --- Try Vote Mistral AIministral-14b-2512 $0.200 $0.200 --- Try Vote Deepseekdeepseek-r1-distill-qwen-7b $0.200 $0.200 --- Try Vote Deepseekdeepseek-coder-7b-base-v1.5 $0.200 $0.200 --- Try Vote Deepseekdeepseek-coder-7b-instruct-v1.5 $0.200 $0.200 --- Try Vote Googlegemma-7b $0.200 $0.200 --- Try Vote Meta-llamallama-2-13b $0.200 $0.200 --- Try Vote Meta-llamallama-2-13b-chat $0.200 $0.200 --- Try Vote Nousresearchhermes-2-pro-mistral-7b $0.200 $0.200 --- Try Vote Opengvlabinternvl3-8b $0.200 $0.200 --- Try Vote Qwenqwen2.5-coder-1.5b-instruct $0.200 $0.200 --- Try Vote Qwenqwen3-1.7b $0.200 $0.200 --- Try Vote Xaigrok-4.1-fast $0.200 $0.500 --- Try Vote Nvidianemotron-nano-12b-v2-vl $0.200 $0.200 --- Try Vote Nousresearchnous-capybara-7b-v1.9 $0.200 $0.200 --- Try Vote Xaigrok-4-fast $0.200 $0.500 --- Try Vote Xaigrok-code-fast-1 $0.200 $1.500 --- Try Vote Mistral AImistral-7b-v0.2 $0.200 $0.200 --- Try Vote Meta-llamallama-2-7b-chat $0.200 $0.200 --- Try Vote Mistral AImistral-7b $0.200 $0.200 --- Try Vote Nousresearchnous-hermes-llama2-7b $0.200 $0.200 --- Try Vote Nousresearchopenhermes-2-mistral-7b $0.200 $0.200 --- Try Vote Nvidianvidia-nemotron-nano-12b-v2 $0.200 $0.200 --- Try Vote Deepseekdeepseek-r1-0528-qwen3-8b $0.200 $0.200 --- Try Vote Meta-llamallama-2-7b $0.200 $0.200 --- Try Vote Meta-llamallama-3-8b-instruct-hf $0.200 $0.200 --- Try Vote Nousresearchopenchat-3.5-0106-7b $0.200 $0.200 --- Try Vote Qwenqwen2.5-vl-32b-instruct $0.200 $0.600 --- Try Vote Deepseekdeepseek-chat-v3-0324 $0.200 $0.770 --- Try Vote Minimaxminimax-01 $0.200 $1.100 --- Try Vote AAllenaiolmo-7b-instruct $0.200 $0.200 --- Try Vote Qwenqwen3-vl-235b-a22b-instruct $0.200 $0.880 --- Try Vote Qwenqwen-2.5-vl-7b-instruct $0.200 $0.200 --- Try Vote Open Orcamistral-7b-openorca $0.200 $0.200 --- Try Vote KKwaipilotkat-coder-pro $0.207 $0.828 --- Try Vote Deepseekdeepseek-v3.1-terminus $0.210 $0.790 --- Try Vote Qwenqwen3-coder $0.220 $0.900 --- Try Vote Mistral AImixtral-8x7b $0.240 $0.240 --- Try Vote Bytedance-seedseed-2.0-lite $0.250 $2.000 --- Try Vote Inceptionmercury $0.250 $0.750 --- Try Vote Inceptionmercury-coder $0.250 $0.750 --- Try Vote Bytedance-seedseed-1.6 $0.250 $2.000 --- Try Vote OpenAIgpt-5.1-codex-mini $0.250 $2.000 --- Try Vote Xaigrok-3-mini $0.250 $0.500 --- Try Vote Googlegemini-3.1-flash-lite-preview $0.250 $1.500 --- Try Vote Anthropicclaude-3-haiku $0.250 $1.250 --- Try Vote Inceptionmercury-2 $0.250 $0.750 --- Try Vote Minimaxminimax-m2 $0.255 $1.000 --- Try Vote Qwenqwen-plus-2025-07-28 $0.260 $0.780 --- Try Vote Qwenqwen3.5-plus $0.260 $1.560 --- Try Vote Qwenqwen3.5-122b-a10b $0.260 $2.080 --- Try Vote Qwenqwen-plus $0.260 $0.780 --- Try Vote Deepseekdeepseek-v3.2 $0.260 $0.380 --- Try Vote Qwenqwen3-vl-235b-a22b-thinking $0.260 $0.900 --- Try Vote Minimaxminimax-m2.1 $0.270 $0.950 --- Try Vote Deepseekdeepseek-v3.2-exp $0.270 $0.410 --- Try Vote Baiduernie-4.5-300b-a47b $0.280 $0.900 --- Try Vote Deepseekdeepseek-r1-distill-qwen-32b $0.290 $0.290 --- Try Vote Minimaxminimax-m2.7 $0.300 $1.200 --- Try Vote Googlegemini-2.5-flash $0.300 $2.500 --- Try Vote Amazonnova-2-lite-v1 $0.300 $2.500 --- Try Vote Qwenqwen1.5-14b-chat $0.300 $0.300 --- Try Vote TNTngtechdeepseek-r1t2-chimera $0.300 $1.100 --- Try Vote Xaigrok-3-mini-beta $0.300 $0.500 --- Try Vote Minimaxminimax-m2-her $0.300 $1.200 --- Try Vote ZZ-aiglm-4.6v $0.300 $0.900 --- Try Vote Googlegemini-2.5-flash-image $0.300 $2.500 --- Try Vote TDThedrummercydonia-24b-v4.1 $0.300 $0.500 --- Try Vote Mistral AIcodestral-2508 $0.300 $0.900 --- Try Vote UUpstagesolar-10.7b-instruct-v1.0 $0.300 $0.300 --- Try Vote AAustismchronos-hermes-13b $0.300 $0.300 --- Try Vote LLmsysvicuna-13b-v1.5 $0.300 $0.300 --- Try Vote Nousresearchhermes-3-llama-3.1-70b $0.300 $0.300 --- Try Vote U9Undi95remm-slerp-l2-13b $0.300 $0.300 --- Try Vote Meta-llamallama-3.1-70b-instruct $0.340 $0.390 --- Try Vote Googlegemini-1.5-flash $0.350 $1.050 --- Try Vote ZZ-aiglm-4.7 $0.390 $1.750 --- Try Vote Qwenqwen3.5-397b-a17b $0.390 $0.900 --- Try Vote ZZ-aiglm-4.6 $0.390 $1.740 --- Try Vote XXiaomimimo-v2-omni $0.400 $2.000 --- Try Vote Mistral AIdevstral-2512 $0.400 $0.900 --- Try Vote Moonshotaikimi-k2-0905 $0.400 $2.000 --- Try Vote Mistral AImistral-medium-3.1 $0.400 $2.000 --- Try Vote Mistral AIdevstral-medium $0.400 $2.000 --- Try Vote Minimaxminimax-m1 $0.400 $1.760 --- Try Vote Mistral AImistral-medium-3 $0.400 $2.000 --- Try Vote Qwenqwen3-235b-a22b $0.400 $0.800 --- Try Vote OpenAIgpt-4.1-mini $0.400 $1.600 --- Try Vote Deepseekdeepseek-v3.2-speciale $0.400 $1.200 --- Try Vote TDThedrummerunslopnemo-12b $0.400 $0.400 --- Try Vote Baiduernie-4.5-vl-424b-a47b $0.420 $1.250 --- Try Vote Qwenqwen2-vl-72b-instruct $0.450 $0.450 --- Try Vote Moonshotaikimi-k2.5 $0.450 $2.200 --- Try Vote Deepseekdeepseek-r1-0528 $0.450 $2.150 --- Try Vote Moonshotaikimi-k2-thinking $0.470 $2.000 --- Try Vote Mistral AImixtral-8x7b-instruct-hf $0.500 $0.500 --- Try Vote ARArcee AIcoder-large $0.500 $0.800 --- Try Vote Googlegemini-3-flash-preview $0.500 $3.000 --- Try Vote Mistral AImistral-large-2512 $0.500 $1.500 --- Try Vote Ai21jamba-instruct $0.500 $0.700 --- Try Vote Nousresearchnous-hermes-2-mixtral-8x7b-dpo $0.500 $0.500 --- Try Vote CGCognitive Computationsdolphin-2.6-mixtral-8x7b $0.500 $0.500 --- Try Vote Mistral AImistral-large $0.500 $1.500 --- Try Vote OpenAIgpt-3.5-turbo $0.500 $1.000 --- Try Vote OpenAIbabbage $0.500 $0.500 --- Try Vote Meta-llamallama-3-70b-instruct $0.510 $0.740 --- Try Vote Qwenqwen-vl-max $0.520 $2.080 --- Try Vote OpenAIo1-mini $0.550 $2.200 --- Try Vote Moonshotaikimi-k2 $0.550 $2.200 --- Try Vote TDThedrummerskyfall-36b-v2 $0.550 $0.800 --- Try Vote OpenAIo3-mini $0.550 $2.200 --- Try Vote Deepseekdeepseek-r1 $0.550 $2.000 --- Try Vote WWriterpalmyra-x5 $0.600 $6.000 --- Try Vote ZZ-aiglm-4.5v $0.600 $1.800 --- Try Vote ZZ-aiglm-4.5 $0.600 $2.200 --- Try Vote Nvidiallama-3.1-nemotron-ultra-253b-v1 $0.600 $1.800 --- Try Vote Meta-llamallama-3.3-swallow-70b-instruct-v0.4 $0.600 $1.200 --- Try Vote Microsoftwizardlm-2-8x22b $0.620 $0.620 --- Try Vote OpenAIgpt-5.1 $0.625 $5.000 --- Try Vote OpenAIgpt-5.1-chat $0.625 $5.000 --- Try Vote MSao10kl3.3-euryale-70b $0.650 $0.750 --- Try Vote Qwenqwen3-coder-plus $0.650 $3.250 --- Try Vote Googlegemma-2-27b-it $0.650 $0.650 --- Try Vote Qwenqwen-2.5-coder-32b-instruct $0.660 $0.800 --- Try Vote Aion Labsaion-1.0-mini $0.700 $1.400 --- Try Vote Deepseekdeepseek-r1-distill-llama-70b $0.700 $0.800 --- Try Vote ZZ-aiglm-5 $0.720 $2.300 --- Try Vote Meta-llamallama-3.1-70b $0.720 $0.720 --- Try Vote OpenAIgpt-5.4-mini $0.750 $4.500 --- Try Vote ARArcee AIvirtuoso-large $0.750 $1.200 --- Try Vote OpenAIcodex-mini $0.750 $3.000 --- Try Vote MAMancerweaver $0.750 $1.000 --- Try Vote Meta-llamacode-llama-34b-instruct $0.776 $0.776 --- Try Vote Qwenqwen3-max-thinking $0.780 $3.900 --- Try Vote Qwenqwen3-max $0.780 $3.900 --- Try Vote SOSophosympatheiamidnight-rose-70b $0.800 $0.800 --- Try Vote Morphmorph-v3-fast $0.800 $1.200 --- Try Vote MAlfredproscodellama-7b-instruct-solidity $0.800 $1.200 --- Try Vote Aion Labsaion-rp-llama-3.1-8b $0.800 $1.600 --- Try Vote Anthropicclaude-3.5-haiku-20241022 $0.800 $4.000 --- Try Vote Deepseekdeepseek-coder-33b-instruct $0.800 $0.800 --- Try Vote Aion Labsaion-2.0 $0.800 $1.600 --- Try Vote Eleutheraillemma_7b $0.800 $1.200 --- Try Vote Qwenqwen2.5-vl-72b-instruct $0.800 $0.800 --- Try Vote ZZero One Aiyi-34b $0.800 $0.800 --- Try Vote Amazonnova-pro-v1 $0.800 $3.200 --- Try Vote Anthropicclaude-3.5-haiku $0.800 $4.000 --- Try Vote Nousresearchnous-hermes-2-yi-34b $0.800 $0.800 --- Try Vote RRelacerelace-apply-3 $0.850 $1.250 --- Try Vote Switchpointrouter $0.850 $3.400 --- Try Vote MSao10kl3.1-euryale-70b $0.850 $0.850 --- Try Vote OpenAIgpt-5.2-chat $0.875 $7.000 --- Try Vote OpenAIgpt-5.2 $0.875 $7.000 --- Try Vote Qwenqwen2.5-coder-32b-instruct-128k $0.900 $0.900 --- Try Vote Morphmorph-v3-large $0.900 $1.900 --- Try Vote ARArcee AImaestro-reasoning $0.900 $3.300 --- Try Vote Deepcogitocogito-v1-preview-llama-70b $0.900 $0.900 --- Try Vote Meta-llamacode-llama-34b $0.900 $0.900 --- Try Vote Meta-llamacode-llama-34b-python $0.900 $0.900 --- Try Vote Meta-llamacode-llama-70b $0.900 $0.900 --- Try Vote Meta-llamacode-llama-70b-instruct $0.900 $0.900 --- Try Vote Meta-llamacode-llama-70b-python $0.900 $0.900 --- Try Vote Meta-llamaphind-code-llama-34b-python-v1 $0.900 $0.900 --- Try Vote Meta-llamaphind-code-llama-34b-v1 $0.900 $0.900 --- Try Vote Meta-llamaphind-code-llama-34b-v2 $0.900 $0.900 --- Try Vote Qwenqwen2-72b-instruct $0.900 $0.900 --- Try Vote Qwenqwen3-coder-480b-instruct-bf16 $0.900 $0.900 --- Try Vote Qwenqwen2.5-72b $0.900 $0.900 --- Try Vote Qwenqwen3-omni-30b-a3b-instruct $0.900 $0.900 --- Try Vote Qwenqwen1.5-72b-chat $0.900 $0.900 --- Try Vote Qwenqwen2.5-32b $0.900 $0.900 --- Try Vote Qwenqwen2.5-32b-instruct $0.900 $0.900 --- Try Vote Qwenqwen2.5-coder-32b $0.900 $0.900 --- Try Vote Qwenqwen2.5-coder-32b-instruct-32k-rope $0.900 $0.900 --- Try Vote Qwenqwen2.5-coder-32b-instruct-64k $0.900 $0.900 --- Try Vote Qwenqwen2.5-math-72b-instruct $0.900 $0.900 --- Try Vote Qwenqwen-qwq-32b-preview $0.900 $0.900 --- Try Vote Bytedance-seedseed-oss-36b-instruct $0.900 $0.900 --- Try Vote Deepcogitocogito-v1-preview-qwen-32b $0.900 $0.900 --- Try Vote Fireworkskat-dev-72b-exp $0.900 $0.900 --- Try Vote CGCognitive Computationsdolphin-2-9-2-qwen2-72b $0.900 $0.900 --- Try Vote Fireworksfare-20b $0.900 $0.900 --- Try Vote Meta-llamallama-2-70b $0.900 $0.900 --- Try Vote Opengvlabinternvl3-38b $0.900 $0.900 --- Try Vote Meta-llamallama-3.1-405b-instruct-long $0.900 $0.900 --- Try Vote Googlemedgemma-27b $0.900 $0.900 --- Try Vote Meta-llamallama-3.1-70b-instruct-1b $0.900 $0.900 --- Try Vote Meta-llamallama-3-70b-instruct-hf $0.900 $0.900 --- Try Vote Opengvlabinternvl3-78b $0.900 $0.900 --- Try Vote Nousresearchnous-hermes-llama2-70b $0.900 $0.900 --- Try Vote Fireworkskat-dev-32b $0.900 $0.900 --- Try Vote Nvidiallama-3.1-nemotron-70b-instruct $0.900 $0.900 --- Try Vote Meta-llamallama-3.2-90b-vision-instruct $0.900 $0.900 --- Try Vote Meta-llamallama-3.1-405b-instruct $0.900 $0.900 --- Try Vote DDeepcogitocogito-v2.1-671b $0.900 $0.900 --- Try Vote XXiaomimimo-v2-pro $1.000 $3.000 --- Try Vote RRelacerelace-search $1.000 $3.000 --- Try Vote Anthropicclaude-haiku-4.5 $1.000 $5.000 --- Try Vote OpenAIcurie $1.000 $1.000 --- Try Vote Nousresearchhermes-4-405b $1.000 $3.000 --- Try Vote Googlegemini-2.5-pro $1.000 $10.000 --- Try Vote Perplexitysonar-reasoning $1.000 $5.000 --- Try Vote Perplexitysonar $1.000 $1.000 --- Try Vote Nousresearchhermes-3-llama-3.1-405b $1.000 $1.000 --- Try Vote Qwenqwen-max $1.040 $4.160 --- Try Vote OpenAIo4-mini-high $1.100 $4.400 --- Try Vote OpenAIo4-mini $1.100 $4.400 --- Try Vote OpenAIo3-mini-high $1.100 $4.400 --- Try Vote ZZ-aiglm-5-turbo $1.200 $4.000 --- Try Vote Mistral AImixtral-8x22b $1.200 $1.200 --- Try Vote Mistral AImixtral-8x22b-instruct $1.200 $1.200 --- Try Vote Googlegemini-2.5-pro-preview-05-06 $1.250 $10.000 --- Try Vote OpenAIgpt-5.1-codex-max $1.250 $10.000 --- Try Vote OpenAIgpt-5.1-codex $1.250 $10.000 --- Try Vote OpenAIgpt-5-codex $1.250 $10.000 --- Try Vote OpenAIgpt-5-chat $1.250 $10.000 --- Try Vote OpenAIgpt-5 $1.250 $10.000 --- Try Vote Googlegemini-2.5-pro-preview $1.250 $10.000 --- Try Vote MSao10kl3-euryale-70b $1.480 $1.480 --- Try Vote OpenAIgpt-3.5-turbo-instruct $1.500 $2.000 --- Try Vote OpenAIgpt-5.3-chat $1.750 $14.000 --- Try Vote OpenAIgpt-5.3-codex $1.750 $14.000 --- Try Vote OpenAIgpt-5.2-codex $1.750 $14.000 --- Try Vote Meta-llamallama-2-chat-70b $1.950 $2.560 --- Try Vote X Aigrok-4.20-beta $2.000 $6.000 --- Try Vote X Aigrok-4.20-multi-agent-beta $2.000 $6.000 --- Try Vote Mistral AImagistral-medium $2.000 $5.000 --- Try Vote Googlegemini-3.1-pro-preview-customtools $2.000 $12.000 --- Try Vote Googlegemini-3.1-pro-preview $2.000 $12.000 --- Try Vote Googlegemini-3-pro-image-preview $2.000 $12.000 --- Try Vote Googlegemini-3-pro-preview $2.000 $12.000 --- Try Vote OpenAIo4-mini-deep-research $2.000 $8.000 --- Try Vote Ai21jamba-large-1.7 $2.000 $8.000 --- Try Vote OpenAIgpt-4.1 $2.000 $8.000 --- Try Vote Perplexitysonar-reasoning-pro $2.000 $8.000 --- Try Vote Perplexitysonar-deep-research $2.000 $8.000 --- Try Vote OpenAIo3 $2.000 $8.000 --- Try Vote Mistral AImistral-large-2411 $2.000 $6.000 --- Try Vote Mistral AImistral-large-2407 $2.000 $6.000 --- Try Vote Mistral AIpixtral-large-2411 $2.000 $6.000 --- Try Vote OpenAIgpt-5.4 $2.500 $15.000 --- Try Vote Coherecommand-r-plus-08-2024 $2.500 $10.000 --- Try Vote Coherecommand-a $2.500 $10.000 --- Try Vote Coherecommand-r-plus $2.500 $10.000 --- Try Vote Inflectioninflection-3-pi $2.500 $10.000 --- Try Vote Inflectioninflection-3-productivity $2.500 $10.000 --- Try Vote Amazonnova-premier-v1 $2.500 $12.500 --- Try Vote OpenAIgpt-4o $2.500 $10.000 --- Try Vote Xaigrok-3-beta $3.000 $15.000 --- Try Vote Anthropicclaude-sonnet-4.6 $3.000 $15.000 --- Try Vote Perplexitysonar-pro-search $3.000 $15.000 --- Try Vote Anthropicclaude-sonnet-4.5 $3.000 $15.000 --- Try Vote Xaigrok-4 $3.000 $15.000 --- Try Vote Xaigrok-3 $3.000 $15.000 --- Try Vote Anthropicclaude-sonnet-4 $3.000 $15.000 --- Try Vote Perplexitysonar-pro $3.000 $15.000 --- Try Vote VVercelv0-1.0-md $3.000 $15.000 --- Try Vote VVercelv0-1-5-md $3.000 $15.000 --- Try Vote Anthropicclaude-3.7-sonnet $3.000 $15.000 --- Try Vote VVercelv0-1.5-md $3.000 $15.000 --- Try Vote MSao10kl3.1-70b-hanami-x1 $3.000 $3.000 --- Try Vote ANAnthracite-orgmagnum-v4-72b $3.000 $5.000 --- Try Vote Anthropicclaude-3.5-sonnet $3.000 $15.000 --- Try Vote OpenAIgpt-3.5-turbo-16k $3.000 $4.000 --- Try Vote ALAlpindalegoliath-120b $3.750 $7.500 --- Try Vote Aion Labsaion-1.0 $4.000 $8.000 --- Try Vote Meta-llamallama-3.1-405b $4.000 $4.000 --- Try Vote Anthropicclaude-opus-4.6 $5.000 $25.000 --- Try Vote Anthropicclaude-opus-4.5 $5.000 $25.000 --- Try Vote Xaigrok-3-fast $5.000 $25.000 --- Try Vote OpenAIchatgpt-4o-latest $5.000 $15.000 --- Try Vote Anthropicclaude-2 $8.000 $24.000 --- Try Vote OpenAIo3-deep-research $10.000 $40.000 --- Try Vote OpenAItext-davinci-002 $10.000 $10.000 --- Try Vote OpenAIgpt-4-turbo $10.000 $30.000 --- Try Vote OpenAIgpt-5.2-pro $10.500 $84.000 --- Try Vote OpenAIgpt-5-pro $15.000 $120.000 --- Try Vote Anthropicclaude-opus-4.1 $15.000 $75.000 --- Try Vote Anthropicclaude-opus-4 $15.000 $75.000 --- Try Vote OpenAIo1 $15.000 $60.000 --- Try Vote Anthropicclaude-3-opus $15.000 $75.000 --- Try Vote OpenAIo3-pro $20.000 $80.000 --- Try Vote OpenAItext-davinci-003 $20.000 $20.000 --- Try Vote OpenAIgpt-5.4-pro $30.000 $180.000 --- Try Vote OpenAIgpt-4 $30.000 $60.000 --- Try Vote OpenAIgpt-4.5-0227 $75.000 $150.000 --- Try Vote OpenAIo1-pro $150.000 $600.000 --- Try Vote * Some models use tiered pricing based on prompt length. Displayed prices are for prompts under 200k tokens. Showing lowest price across all providers. Benchmarks from Artificial Analysis and HuggingFace Open LLM Leaderboard. How to Use the Token Counter & Cost Estimator Step-by-Step Guide1Enter Your PromptType or paste your AI prompt into the text area. The token count will update automatically as you type.2Review Token Count & CostsSee the estimated token count and real-time cost calculations for your prompt across different AI models:Token Count: Estimated number of tokens your prompt will useInput Cost: Cost to send your prompt to each modelModel Comparison: Compare pricing across different providers and models3Optimize Your PromptUse the insights to optimize your AI usage:Cost Comparison: Find the most cost-effective model for your promptToken Optimization: Edit your prompt to reduce token count and costsBudget Planning: Estimate costs for your AI projects and workflows💡 Token Counter Example:Let's say you're planning to send 100 customer service prompts per day. Each prompt is about 50 tokens. You want to find the most cost-effective model.Prompt Length: ~50 tokens per promptDaily Volume: 100 prompts × 50 tokens = 5,000 tokens/dayMonthly Volume: 5,000 × 30 = 150,000 tokens/monthEnter your prompt in the tool above and instantly see which model offers the best value for your specific use case and volume.Understanding Token CountingWhat are Tokens?Tokens are the basic units that AI models use to process text. They can be words, parts of words, or punctuation marks. On average, 1 token ≈ 4 characters or ≈ 0.75 words in English.Token Examples • "Hello" = 1 token • "ChatGPT" = 2 tokens (Chat + GPT) • "Hello, world!" = 4 tokens (Hello, ,, world, !) Why Token Count MattersAI models charge based on token usage. Longer prompts use more tokens and cost more. Understanding token count helps you optimize prompts for both performance and cost.Token Optimization Tips✂️Concise PromptsRemove unnecessary words while keeping instructions clear and specific🎯Specific InstructionsClear, direct instructions often work better than lengthy explanations📊Test & CompareTry different prompt variations to find the optimal balance of length and effectiveness💰Budget AwarenessUse the cost calculator to stay within budget for high-volume applications💡Pro TipsToken counts are estimates - actual counts may vary slightly between modelsShorter prompts aren't always better - clarity and specificity matter moreUse this tool to estimate costs before deploying AI features in productionDifferent models may tokenize the same text differently, affecting costsProvider Token CountersCount tokens and estimate costs for all models from a specific AI provider68 providers Ai21All Ai21 models with token countingAion LabsAll Aion Labs models with token countingAlfredprosAll Alfredpros models with token countingAlibabaAll Alibaba models with token countingAllenaiAll Allenai models with token countingAlpindaleAll Alpindale models with token countingAmazonAll Amazon models with token countingAnthracite-orgAll Anthracite-org models with token countingAnthropicAll Anthropic models with token countingArcee AIAll Arcee AI models with token countingArliaiAll Arliai models with token countingAustismAll Austism models with token countingBaiduAll Baidu models with token countingBytedanceAll Bytedance models with token countingBytedance-seedAll Bytedance-seed models with token countingCognitive ComputationsAll Cognitive Computations models with token countingCohereAll Cohere models with token countingDeepcogitoAll Deepcogito models with token countingDeepseekAll Deepseek models with token countingEleutheraiAll Eleutherai models with token countingEssential AIAll Essential AI models with token countingFireworksAll Fireworks models with token countingGoogleAll Google models with token countingGrypheAll Gryphe models with token countingIbmAll Ibm models with token countingIbm-graniteAll Ibm-granite models with token countingInceptionAll Inception models with token countingInflectionAll Inflection models with token countingKwaipilotAll Kwaipilot models with token countingLiquidAll Liquid models with token countingLiquidaiAll Liquidai models with token countingLmsysAll Lmsys models with token countingMancerAll Mancer models with token countingMeituanAll Meituan models with token countingMeta-llamaAll Meta-llama models with token countingMicrosoftAll Microsoft models with token countingMinimaxAll Minimax models with token countingMistral AIAll Mistral AI models with token countingMoonshotaiAll Moonshotai models with token countingMorphAll Morph models with token countingNeversleepAll Neversleep models with token countingNex-AGIAll Nex-AGI models with token countingNousresearchAll Nousresearch models with token countingNvidiaAll Nvidia models with token countingOpen OrcaAll Open Orca models with token countingOpenAIAll OpenAI models with token countingOpengvlabAll Opengvlab models with token countingPerplexityAll Perplexity models with token countingPrime-intellectAll Prime-intellect models with token countingQwenAll Qwen models with token countingRaifleAll Raifle models with token countingRelaceAll Relace models with token countingSao10kAll Sao10k models with token countingSophosympatheiaAll Sophosympatheia models with token countingStepfun-aiAll Stepfun-ai models with token countingSwitchpointAll Switchpoint models with token countingTencentAll Tencent models with token countingThedrummerAll Thedrummer models with token countingTngtechAll Tngtech models with token countingUndi95All Undi95 models with token countingUpstageAll Upstage models with token countingVercelAll Vercel models with token countingWriterAll Writer models with token countingX AiAll X Ai models with token countingXaiAll Xai models with token countingXiaomiAll Xiaomi models with token countingZ-aiAll Z-ai models with token countingZero One AiAll Zero One Ai models with token countingModel-Specific Token CountersDetailed token counter for individual AI models0 models No models available Quick Access - Popular Models Loading model calculators... Built by @aellman ArchiveToolsPricing CalculatorToken CounterLLM PlaygroundAI Coding TrackerMCP ServerSubscription CalculatorDirectoriesAll DirectoriesAI Coding AssistantsAI Agent FrameworksLLM Observability ToolsLocal LLM RunnersOpenClaw DeploymentMCP ServersAI JobsModels & PricingLLM PricesEmbedding ModelsImage ModelsFine-Tuning PricingCheapest LLM APIGPU PricingPrice HistoryTrendsEndpointsTogether AIAWS BedrockGroqFireworks AICerebrasOpenRouterAzure OpenAIGoogle AI StudioNebius AICloudflare Workers AICompare ProvidersFree ModelsRankingsAll RankingsAll BenchmarksBest LLM for CodingBest LLM for MathBest LLM for WritingBest LLM for RAGBest Local LLMBest LLM for OpenClawBest LLM for CursorBest LLM for WindsurfBest LLM for ClineBest LLM for AiderBest LLM for GitHub CopilotBest LLM for BoltBest LLM for Continue.devMMLU-ProGPQALiveCodeBenchAiderAIMEMATH (Hard)Big-Bench HardNewsAll NewsModel ReleasesAI CodingOpen SourceBenchmarksHardwareChipsRegulationFundingImage GenerationVideo GenerationMCPFollow us: Advertise | Terms of Service | Privacy Policy 2026 68 Ventures, LLC. All rights reserved. Feedback 🤖✨ AI pricing changes weekly. Don't overpay. Every week we track price drops, new models, and benchmark changes across 30+ providers. Free newsletter, no spam. Subscribe Join 1,000+ developers tracking AI costs --- LLM Pricing MCP Server for Claude Code & Cursor | Price Per TokenLLM Pricing MCP Server for Claude Code and Cursor Access real-time LLM pricing, benchmark and speed data directly in Claude Code, Cursor, Windsurf, and other MCP-enabled AI assistants. How the MCP Server Works Our MCP server provides your coding assistant access to all of our data including pricing, benchmark, latency and endpoint availability. Make informed decisions without leaving your workflow. Available Tools Query pricing, compare models, and access benchmark data with these tools: ToolDescriptionget_all_modelsGet pricing for all models with filtering by author, context length, TTFT, speed, or capabilitiesget_modelGet detailed info for a specific model. Optionally specify a provider (e.g., "bedrock", "groq") to get that provider's pricing instead of the defaultcompare_modelsSide-by-side comparison of multiple models. Optionally specify a provider to compare pricing on a specific platformcompare_providersCompare pricing for the same model across all API providers to find the cheapest place to run itget_benchmarksGet models ranked by a specific benchmark (coding, math, intelligence, etc.)get_providersList all providers with model counts and price rangessearch_modelsSearch models by name, author, or descriptionget_provider_slugsLook up the provider-specific model ID for any API provider (OpenRouter, Bedrock, Groq, Fireworks, Cerebras, Together, DeepInfra, SambaNova, Gemini)Setup Choose your AI assistant below for setup instructions. No API key required. C Claude Code Run this command in your terminal:claude mcp add pricepertoken --transport http --url https://api.pricepertoken.com/mcp/mcpCu Cursor Add this to your ~/.cursor/mcp.json:{ "mcpServers": { "pricepertoken": { "url": "https://api.pricepertoken.com/mcp/mcp" } } }C Claude Desktop Add this to your claude_desktop_config.json:{ "mcpServers": { "pricepertoken": { "command": "npx", "args": [ "mcp-remote", "https://api.pricepertoken.com/mcp/mcp" ] } } }W Windsurf Add this to your ~/.codeium/windsurf/mcp_config.json:{ "mcpServers": { "pricepertoken": { "serverUrl": "https://api.pricepertoken.com/mcp/mcp" } } }Example Prompts Once connected, try asking your AI assistant: "What is the cheapest model with 100k+ context?""Compare GPT-4o and Claude 3.5 Sonnet pricing""Show me the top 10 models for coding benchmarks""Find the fastest models with TTFT under 2 seconds""What Anthropic models support vision?""What is the Bedrock slug for Claude Opus 4.6?""Compare Claude Sonnet 4.6 pricing across all providers""How much does GPT-4o cost on Groq vs direct from OpenAI?"Frequently Asked QuestionsDo I need an API key?No, the Price Per Token MCP is free to use and doesn't require authentication.How often is pricing data updated?Our pricing database is updated regularly as providers announce changes. You always get the latest data.What models are included?We track pricing for 100+ models from OpenAI, Anthropic, Google, Meta, Mistral, and many more providers. View all on our LLM pricing page.Can I compare model benchmarks?Yes, use the get_benchmarks tool to rank models by coding, math, or intelligence scores. See our LLM rankings for more.Is there a rate limit?There's no strict rate limit, but please use responsibly. If you need high-volume access, contact us.Ready to get started?Set up the MCP in under a minute and start making data-driven model decisions. Browse All Models Learn About MCP Coming SoonAPI Finder The first API directory for AI agents. Join the waitlist Built by @aellman ArchiveToolsPricing CalculatorToken CounterLLM PlaygroundAI Coding TrackerMCP ServerSubscription CalculatorDirectoriesAll DirectoriesAI Coding AssistantsAI Agent FrameworksLLM Observability ToolsLocal LLM RunnersOpenClaw DeploymentMCP ServersAI JobsModels & PricingLLM PricesEmbedding ModelsImage ModelsFine-Tuning PricingCheapest LLM APIGPU PricingPrice HistoryTrendsEndpointsTogether AIAWS BedrockGroqFireworks AICerebrasOpenRouterAzure OpenAIGoogle AI StudioNebius AICloudflare Workers AICompare ProvidersFree ModelsRankingsAll RankingsAll BenchmarksBest LLM for CodingBest LLM for MathBest LLM for WritingBest LLM for RAGBest Local LLMBest LLM for OpenClawBest LLM for CursorBest LLM for WindsurfBest LLM for ClineBest LLM for AiderBest LLM for GitHub CopilotBest LLM for BoltBest LLM for Continue.devMMLU-ProGPQALiveCodeBenchAiderAIMEMATH (Hard)Big-Bench HardNewsAll NewsModel ReleasesAI CodingOpen SourceBenchmarksHardwareChipsRegulationFundingImage GenerationVideo GenerationMCPFollow us: Advertise | Terms of Service | Privacy Policy 2026 68 Ventures, LLC. All rights reserved. Feedback --- LLM Benchmarks 2026 — Compare AI Model Scores & Rankings | Price Per TokenLLM BenchmarksDiscover and compare AI model performance across 39 benchmarks. Data from Artificial Analysis and LayerLens All Reasoning and Logic (15) Multi-turn (6) Mathematical Problem Solving (5) Computer Science and Programming (4) General Knowledge (4) Instruction Following (2) Financial Reasoning (2) Multilingual (2) Multimodal (1) Categories39 benchmarks GPQAReasoning and LogicGraduate-level multiple-choice questions written by domain experts in biology, physics, and chemistry. Questions are Google-proof and extremely difficult.1GPT-5.492.02GPT-5.3 Codex91.53Gemini 3 Pro Preview90.84GPT-5.2 Pro90.3Humanity's Last ExamReasoning and LogicHumanity's Last Exam — extremely challenging questions designed to test the upper limits of AI capability across diverse domains.1GPT-5.441.62GPT-5.3 Codex39.93Gemini 3 Pro Preview37.24Claude Opus 4.636.7SciCodeComputer Science and ProgrammingScience coding benchmark measuring AI ability to solve scientific computing tasks.1GPT-5.456.62Gemini 3 Pro Preview56.13GPT-5.2-Codex54.64GPT-5.3 Codex53.2IFBenchInstruction FollowingInstruction Following Benchmark measuring LLM ability to adhere to nuanced writing constraints and formatting requirements.1AQwen3.5 397B A17B78.82Gemini 3 Flash Preview78.03GPT-5.2-Codex77.64AQwen3.5-122B-A10B75.7LCRReasoning and LogicLong Context Retrieval benchmark testing ability to find and use information in very long documents.1GPT-5.2-Codex75.72GPT-575.63GPT-5.175.04KKAT-Coder-Pro V174.0Tau2Multi-turnTau2 benchmark testing multi-turn agent capabilities in airline and retail domains.1ZGLM-4.7-Flash98.82ZGLM-5 Turbo98.53ZGLM 598.24ZGLM 597.4TerminalBenchMulti-turnTerminal-based benchmark testing AI ability to interact with command-line interfaces and solve system tasks.1GPT-5.457.62Claude Sonnet 4.653.03GPT-5.3 Codex53.04Claude Opus 4.648.5LiveCodeBenchComputer Science and ProgrammingReal-world coding benchmark with problems from competitive programming contests, testing code generation and problem-solving abilities.1Gemini 3 Pro Preview91.72Gemini 3 Flash Preview90.83DeepSeek V3.2 Speciale89.64ZGLM 4.789.4MMLU-ProGeneral KnowledgeMassive Multitask Language Understanding benchmark testing knowledge across 57 diverse subjects including STEM, humanities, social sciences, and professional domains.1Gemini 3 Pro Preview89.82Claude Opus 4.589.53Gemini 3 Flash Preview89.04Claude Opus 4.588.9AIME 2025Mathematical Problem SolvingAmerican Invitational Mathematics Examination 2025 problems testing olympiad-level mathematical reasoning.1GPT-5.2 Pro99.02GPT-5 Codex98.73Gemini 3 Flash Preview97.04DeepSeek V3.2 Speciale96.7MATH-500Mathematical Problem SolvingCompetition mathematics problems requiring multi-step reasoning, covering algebra, geometry, number theory, and calculus.1GPT-599.42o399.23Grok 3 Mini99.24Claude Sonnet 499.1AGIEval EnglishReasoning and LogicAGIEval English — human-level reasoning tasks from standardized exams like SAT, LSAT, and civil service exams.1Gemini 3.1 Pro Preview94.02Gemini 3 Pro Preview93.23AQwen3.5 397B A17B91.44AQwen3.5 397B A17B91.4AIME 2024Mathematical Problem SolvingAmerican Invitational Mathematics Examination 2024 problems testing olympiad-level mathematical reasoning.1GPT-595.72Grok 494.33o4 Mini94.04AQwen3 235B A22B Thinking 250794.0BBHReasoning and LogicBig-Bench Hard — challenging subset of BIG-Bench focusing on tasks where language models previously underperformed.1Claude Sonnet 4.594.42Claude Sonnet 4.594.33ZGLM 594.34ZGLM 594.3HumanEvalComputer Science and ProgrammingOpenAI HumanEval benchmark measuring Python code generation from function docstrings.1Claude Sonnet 4.597.62R197.43Grok 497.04Claude Sonnet 4.597.0Accounting AuditFinancial ReasoningAccounting and audit benchmark testing financial reasoning capabilities.1Claude 3.7 Sonnet86.72Gemini 2.5 Pro Preview 05-0686.73Claude 3.7 Sonnet83.34AQwQ 32B83.3MBPP PlusComputer Science and ProgrammingMostly Basic Python Problems Plus — tests Python code generation with enhanced test cases.1AQwen3 235B A22B66.22AQwen3 235B A22B66.23R164.74o4 Mini High64.3MMMUMultimodalMultimodal Understanding benchmark testing vision-language models on expert-level tasks.1o4 Mini High79.22GPT-579.13GPT-579.14GPT-579.1SWE-bench LiteMulti-turnSoftware Engineering benchmark testing ability to resolve real GitHub issues.1Claude Opus 4.662.72Claude Opus 4.662.73MiniMax M2.556.34GPT-554.3GSM8KMathematical Problem SolvingGrade School Math 8K — 8,500 high quality grade school math word problems.1Claude Opus 496.22Claude Opus 496.23R196.24o4 Mini High96.0SimpleQAReasoning and LogicSimple question answering benchmark testing factual accuracy and knowledge retrieval.1Gemini 2.5 Pro53.02AQwen3 235B A22B Instruct 250750.63AQwen3 VL 235B A22B Instruct46.74GPT-4.140.4ARC ChallengeReasoning and LogicAI2 Reasoning Challenge (Challenge set) — grade-school science questions requiring complex reasoning.1GPT-596.32GPT-596.33GPT-596.34GPT-596.3BBEHReasoning and LogicBig Bench Extra Hard — even more challenging reasoning tasks pushing the limits of language model capabilities.1GPT-564.12GPT-564.13GPT-564.14GPT-564.1ARC EasyReasoning and LogicAI2 Reasoning Challenge (Easy set) — grade-school science questions.1Claude Opus 499.72Claude Opus 499.73AQwen3 32B99.14AQwen3 32B99.1MathematicsMathematical Problem SolvingMathematics benchmark covering algebra, geometry, number theory, and calculus problems.1Claude Opus 4.695.62Claude Opus 4.695.63o4 Mini High94.64ZGLM 594.0MedQAReasoning and LogicMedical question answering benchmark from USMLE-style questions.1o4 Mini High95.22Gemini 2.5 Pro94.63Claude 3.7 Sonnet92.34R192.1MMLUGeneral KnowledgeMassive Multitask Language Understanding — tests knowledge across 57 subjects.1ZGLM 591.72ZGLM 591.73R1 052890.54Grok 3 Mini Beta89.2AGIEval ChineseReasoning and LogicAGIEval Chinese — reasoning tasks from Chinese standardized exams (Gaokao, civil service).1DeepSeek V3.2 Exp90.12AQwen3 235B A22B89.43AQwen3 235B A22B89.44ERNIE 4.5 300B A47B89.0Stock BCSFinancial ReasoningStock market benchmark testing financial analysis capabilities.1AQwen2.5 72B Instruct100.02R191.73GPT-4.191.74o3 Mini83.3BIRD-CRITICMulti-turnBIRD-CRITIC — multi-turn benchmark testing SQL generation and database interaction.1Claude Opus 4.634.02Claude Opus 4.634.03ZGLM 4.733.04ZGLM 4.733.0Knights and KnavesReasoning and LogicLogic puzzle benchmark based on knights (truth-tellers) and knaves (liars) puzzles.1o3 Mini99.72o4 Mini High99.73R1 052897.94R197.3IFEvalInstruction FollowingInstruction Following Evaluation benchmark testing how well LLMs follow detailed formatting and content constraints.1KKimi K2.592.62KKimi K2.592.63Gemini 2.5 Pro90.84ZGLM 4.790.8BFCL v3Multi-turnBerkeley Function Calling Leaderboard v3 — testing function/tool calling accuracy.1ZGLM 4.576.72AQwen3 32B75.73AQwen3 32B75.74AQwen3 Max74.9Formal Logic ExtendedReasoning and LogicExtended formal logic benchmark testing deductive and propositional reasoning.1o3 Mini99.82R1 052899.23R198.44Claude 3.7 Sonnet95.6WMDPReasoning and LogicWeapons of Mass Destruction Proxy — benchmark testing knowledge safety boundaries.1Gemini 3 Flash Preview86.82Gemini 3 Flash Preview86.83o3 Mini80.54Claude 3.7 Sonnet78.2DarkBenchReasoning and LogicDarkBench — benchmark testing model safety and resistance to adversarial attacks.1Grok 451.12Phi 449.53AQwen3 32B49.24AQwen3 32B49.2WMT 2014MultilingualWorkshop on Machine Translation 2014 — multilingual translation quality benchmark.1Gemini 2.0 Flash38.92Llama 3.1 405B Instruct38.03Llama 4 Maverick38.04GPT-4.137.6GAIAMulti-turnGAIA — General AI Assistants benchmark testing multi-step real-world tasks.1GPT-5 Mini44.82Claude 3.7 Sonnet43.93Claude 3.7 Sonnet43.94Gemini 2.5 Pro33.3MultiChallengeGeneral KnowledgeMultiChallenge — general knowledge benchmark with diverse challenge types.1Mistral Medium 3.137.42Nova Pro 1.019.0122 out of our 514 tracked models have had a price change in March. Get our weekly newsletter on pricing changes, new releases, and tools. Subscribe Deploy OpenClaw in Under 1 Minute— We handle hosting, scaling, and maintenance 8 Ways to Use Fewer TokensDownload Now Built by @aellman ToolsPricing CalculatorToken CounterLLM PlaygroundAI Coding TrackerMCP ServerSubscription CalculatorDirectoriesAll DirectoriesAI Coding AssistantsAI Agent FrameworksLLM Observability ToolsLocal LLM RunnersOpenClaw DeploymentMCP ServersAI JobsModels & PricingLLM PricesEmbedding ModelsImage ModelsFine-Tuning PricingCheapest LLM APIGPU PricingPrice HistoryTrendsEndpointsTogether AIAWS BedrockGroqFireworks AICerebrasOpenRouterAzure OpenAIGoogle AI StudioNebius AICloudflare Workers AICompare ProvidersFree ModelsRankingsAll RankingsAll BenchmarksBest LLM for CodingBest LLM for MathBest LLM for WritingBest LLM for RAGBest Local LLMBest LLM for OpenClawBest LLM for CursorBest LLM for WindsurfBest LLM for ClineBest LLM for AiderBest LLM for GitHub CopilotBest LLM for BoltBest LLM for Continue.devMMLU-ProGPQALiveCodeBenchAiderAIMEMATH (Hard)Big-Bench HardNewsAll NewsModel ReleasesAI CodingOpen SourceBenchmarksHardwareChipsRegulationFundingImage GenerationVideo GenerationMCPFollow us: Advertise | Terms of Service | Privacy Policy 2026 68 Ventures, LLC. All rights reserved. Feedback --- Get real-time LLM pricing in Claude Code and Cursor. Try Price Per Token MCP Free Deepcogito Token Counter & Pricing CalculatorDDeepcogito Token Counter & Cost Estimator Count tokens and estimate costs for Deepcogito's newest models including Cogito v1 Preview Llama 3B, Cogito v1 Preview Llama 70B, Cogito v1 Preview Llama 70B Turbo, Cogito v1 Preview Llama 8B, Cogito v1 Preview Qwen 14B and more. Enter your prompt to get token counts and cost estimates using our interactive tokenizer.8 Ways to Use Fewer TokensGet the free PDF guide — practical tips to cut your token usage and API costs. Subscribe to the Price Per Token newsletter and download instantly.Download Now Last updated: March 26, 2026 at 05:10 PMEstimate the cost of a promptEnter your prompt:Input TokensOutput TokensAPI CallsCalculate by Tokens Words Characters Current Pricing (per 1M tokens)10 models Columns Provider Model Input $/M Output $/M Est. Input Est. Output Total Actions Deepcogitocogito-v1-preview-llama-70b-turbo $0.000 $0.000<$0.001<$0.001<$0.001 Try Vote Deepcogitocogito-v1-preview-llama-3b $0.100 $0.100<$0.001<$0.001<$0.001 Try Vote Deepcogitocogito-v2-preview-llama-109b-moe $0.180 $0.590<$0.001<$0.001<$0.001 Try Vote Deepcogitocogito-v1-preview-llama-8b $0.200 $0.200<$0.001<$0.001<$0.001 Try Vote Deepcogitocogito-v1-preview-qwen-14b $0.200 $0.200<$0.001<$0.001<$0.001 Try Vote Deepcogitocogito-v2-preview-llama-70b $0.880 $0.880<$0.001<$0.001$0.001 Try Vote Deepcogitocogito-v1-preview-llama-70b $0.900 $0.900<$0.001<$0.001$0.001 Try Vote Deepcogitocogito-v1-preview-qwen-32b $0.900 $0.900<$0.001<$0.001$0.001 Try Vote DDeepcogitocogito-v2.1-671b $0.900 $0.900<$0.001<$0.001$0.001 Try Vote Deepcogitocogito-v2-preview-llama-405b $3.500 $3.500$0.004$0.002$0.005 Try Vote * Some models use tiered pricing based on prompt length. Displayed prices are for prompts ≤ 200k tokens. Chart Metric:Input Cost (per 1M tokens)Output Cost (per 1M tokens)Models:10 models selected How to Use the Token Counter & Cost Estimator Step-by-Step Guide1Enter Your PromptType or paste your AI prompt into the text area. The token count will update automatically as you type.2Review Token Count & CostsSee the estimated token count and real-time cost calculations for your prompt across different AI models:Token Count: Estimated number of tokens your prompt will useInput Cost: Cost to send your prompt to each modelModel Comparison: Compare pricing across different providers and models3Optimize Your PromptUse the insights to optimize your AI usage:Cost Comparison: Find the most cost-effective model for your promptToken Optimization: Edit your prompt to reduce token count and costsBudget Planning: Estimate costs for your AI projects and workflows💡 Token Counter Example:Let's say you're planning to send 100 customer service prompts per day. Each prompt is about 50 tokens. You want to find the most cost-effective model.Prompt Length: ~50 tokens per promptDaily Volume: 100 prompts × 50 tokens = 5,000 tokens/dayMonthly Volume: 5,000 × 30 = 150,000 tokens/monthEnter your prompt in the tool above and instantly see which model offers the best value for your specific use case and volume.Understanding Token CountingWhat are Tokens?Tokens are the basic units that AI models use to process text. They can be words, parts of words, or punctuation marks. On average, 1 token ≈ 4 characters or ≈ 0.75 words in English.Token Examples • "Hello" = 1 token • "ChatGPT" = 2 tokens (Chat + GPT) • "Hello, world!" = 4 tokens (Hello, ,, world, !) Why Token Count MattersAI models charge based on token usage. Longer prompts use more tokens and cost more. Understanding token count helps you optimize prompts for both performance and cost.Token Optimization Tips✂️Concise PromptsRemove unnecessary words while keeping instructions clear and specific🎯Specific InstructionsClear, direct instructions often work better than lengthy explanations📊Test & CompareTry different prompt variations to find the optimal balance of length and effectiveness💰Budget AwarenessUse the cost calculator to stay within budget for high-volume applications💡Pro TipsToken counts are estimates - actual counts may vary slightly between modelsShorter prompts aren't always better - clarity and specificity matter moreUse this tool to estimate costs before deploying AI features in productionDifferent models may tokenize the same text differently, affecting costsFrequently Asked QuestionsEverything you need to know about AI pricing and tokensWhat is a token?A token is the basic unit that AI models use to process text. Think of tokens as "chunks" of text that the AI reads and writes. 1,000 tokens equals approximately 750 words of English text. One token equals roughly 4 characters on average. Tokens can be whole words, parts of words, or punctuation. Different languages may use different numbers of tokens. For example, "Hello world" equals 2 tokens. "AI" equals 1 token. "ChatGPT" equals 2 tokens (Chat + GPT). A typical email contains 200-400 tokens. A blog post contains 1,000-3,000 tokens. What is an execution (API call)?An execution or API call is each time you send a request to an AI model and get a response back. Each call is charged separately. The text you send is counted as input tokens and the text you get back is counted as output tokensWhat is a prompt?A prompt is the input text you send to an AI model - essentially your question, instruction, or request. You can tailor your prompt to get a certain style of response. For examole you could say "You are a friendly customer service agent, respond to the user's request" followed by the question from the user.How should I pick a model?Choosing the right AI model depends on your specific needs, budget, and quality requirements. For simple tasks like summaries or basic questions, use cheaper models like GPT-4o-mini or Claude Haiku. For complex reasoning, use premium models like GPT-4o or Claude Sonnet. For specialized tasks, look for models trained for your specific use case. Test with a few models on your actual use case. Premium models often need fewer retries. Sometimes a cheaper model with a better prompt works just as well. Budget models like GPT-4o-mini and Claude Haiku cost $0.15-0.30 per 1M tokens. Balanced models like GPT-4o and Claude Sonnet cost $3-15 per 1M tokens. Premium models like GPT-4 Turbo and Claude Opus cost $15-75 per 1M tokens. Built by @aellman ArchiveToolsPricing CalculatorToken CounterLLM PlaygroundAI Coding TrackerMCP ServerSubscription CalculatorDirectoriesAll DirectoriesAI Coding AssistantsAI Agent FrameworksLLM Observability ToolsLocal LLM RunnersOpenClaw DeploymentMCP ServersAI JobsModels & PricingLLM PricesEmbedding ModelsImage ModelsFine-Tuning PricingCheapest LLM APIGPU PricingPrice HistoryTrendsEndpointsTogether AIAWS BedrockGroqFireworks AICerebrasOpenRouterAzure OpenAIGoogle AI StudioNebius AICloudflare Workers AICompare ProvidersFree ModelsRankingsAll RankingsAll BenchmarksBest LLM for CodingBest LLM for MathBest LLM for WritingBest LLM for RAGBest Local LLMBest LLM for OpenClawBest LLM for CursorBest LLM for WindsurfBest LLM for ClineBest LLM for AiderBest LLM for GitHub CopilotBest LLM for BoltBest LLM for Continue.devMMLU-ProGPQALiveCodeBenchAiderAIMEMATH (Hard)Big-Bench HardNewsAll NewsModel ReleasesAI CodingOpen SourceBenchmarksHardwareChipsRegulationFundingImage GenerationVideo GenerationMCPFollow us: Advertise | Terms of Service | Privacy Policy 2026 68 Ventures, LLC. All rights reserved. Feedback