MODEL TOKEN COUNTER DIRECTORY

Token counters for every supported AI model.

Each model below has a dedicated token counter with current API pricing, the context window, and tokenizer accuracy notes. OpenAI models use exact browser-side tokenization; other providers are clearly labeled estimates. Pricing was last refreshed 2026-07-01.

OpenAI token counters

Google token counters

Extended catalog: 630 more models

Long-tail and hosted models with pricing from the community-maintained LiteLLM dataset (refreshed 2026-07-01). Counts on these pages are estimates unless the model uses a public OpenAI encoding; prices can lag provider changes.

OpenAI (69 models)
Anthropic (19 models)
Google (29 models)
Mistral (50 models)
DeepSeek (6 models)
xAI (37 models)
Alibaba (17 models)
Moonshot AI (22 models)
AI21 Labs (9 models)
Perplexity (20 models)
Groq (11 models)
Cerebras (5 models)
SambaNova (13 models)
Together AI (10 models)
Fireworks AI (228 models)
chronos-hermes-13b-v2code-llama-13bcode-llama-13b-instructcode-llama-13b-pythoncode-llama-34bcode-llama-34b-pythoncode-llama-70bcode-llama-70b-pythoncode-llama-7bcode-llama-7b-instructcode-llama-7b-pythoncode-qwen-1p5-7bcodegemma-2bcodegemma-7bcogito-671b-v2-p1cogito-v1-preview-llama-3bcogito-v1-preview-llama-70bcogito-v1-preview-llama-8bcogito-v1-preview-qwen-14bcogito-v1-preview-qwen-32bdbrx-instructdeepseek-coder-1b-basedeepseek-coder-33b-instructdeepseek-coder-7b-basedeepseek-coder-7b-base-v1p5deepseek-coder-7b-instruct-v1p5deepseek-coder-v2-instructdeepseek-coder-v2-lite-basedeepseek-coder-v2-lite-instructdeepseek-prover-v2deepseek-r1-0528deepseek-r1-0528-distill-qwen3-8bdeepseek-r1-basicdeepseek-r1-distill-llama-8bdeepseek-r1-distill-qwen-14bdeepseek-r1-distill-qwen-1p5bdeepseek-r1-distill-qwen-32bdeepseek-r1-distill-qwen-7bdeepseek-v2-lite-chatdeepseek-v2p5deepseek-v3p1deepseek-v3p1-terminusdeepseek-v3p2dobby-mini-unhinged-plus-llama-3-1-8bdobby-unhinged-llama-3-3-70b-newdolphin-2-9-2-qwen2-72bdolphin-2p6-mixtral-8x7bernie-4p5-21b-a3b-pternie-4p5-300b-a47b-ptfare-20bfirefunction-v1firefunction-v2firellava-13bfiresearch-ocr-v6flux-1-devflux-1-dev-controlnet-unionflux-1-schnellgemma-2b-itgemma-7bgemma2-9b-itglm-4p5glm-4p5-airglm-4p5vglm-4p6glm-4p7glm-5p1glm-5p1-fastglm-5p2gpt-oss-safeguard-120bhermes-2-pro-mistral-7binternvl3-38binternvl3-78binternvl3-8bkat-coderkat-dev-32bkat-dev-72b-expkimi-k2-instructkimi-k2p5kimi-k2p6kimi-k2p6-fastkimi-k2p7-codekimi-k2p7-code-fastllama-guard-2-8bllama-guard-3-1bllama-guard-3-8bllama-v2-13bllama-v2-13b-chatllama-v2-70bllama-v2-70b-chatllama-v2-7bllama-v2-7b-chatllama-v3-70b-instructllama-v3-70b-instruct-hfllama-v3-8bllama-v3-8b-instruct-hfllama-v3p1-405b-instructllama-v3p1-405b-instruct-longllama-v3p1-70b-instructllama-v3p1-70b-instruct-1bllama-v3p1-8b-instructllama-v3p1-nemotron-70b-instructllama-v3p2-11b-vision-instructllama-v3p2-1bllama-v3p2-1b-instructllama-v3p2-3bllama-v3p2-3b-instructllama-v3p2-90b-vision-instructllama-v3p3-70b-instructllama4-maverick-instruct-basicllama4-scout-instruct-basicllamaguard-7bllava-yi-34bminimax-m1-80kminimax-m2minimax-m2p1minimax-m2p7minimax-m3ministral-3-14b-instruct-2512ministral-3-3b-instruct-2512ministral-3-8b-instruct-2512mistral-7bmistral-7b-instruct-4kmistral-7b-instruct-v0p2mistral-7b-instruct-v3mistral-7b-v0p2mistral-large-3-fp8mistral-nemo-base-2407mistral-nemo-instruct-2407mistral-small-24b-instruct-2501mixtral-8x22bmixtral-8x22b-instructmixtral-8x22b-instruct-hfmixtral-8x7bmixtral-8x7b-instruct-hfmythomax-l2-13bnemotron-nano-v2-12b-vlnous-capybara-7b-v1p9nous-hermes-2-mixtral-8x7b-dponous-hermes-2-yi-34bnous-hermes-llama2-13bnous-hermes-llama2-70bnous-hermes-llama2-7bnvidia-nemotron-nano-12b-v2nvidia-nemotron-nano-9b-v2openchat-3p5-0106-7bopenhermes-2-mistral-7bopenhermes-2p5-mistral-7bopenorca-7bphi-2-3bphi-3-mini-128k-instructphi-3-vision-128k-instructphind-code-llama-34b-python-v1phind-code-llama-34b-v1phind-code-llama-34b-v2pythia-12bqwen-qwq-32b-previewqwen-v2p5-14b-instructqwen-v2p5-7bqwen1p5-72b-chatqwen2-72b-instructqwen2-7b-instructqwen2-vl-2b-instructqwen2-vl-72b-instructqwen2-vl-7b-instructqwen2p5-0p5b-instructqwen2p5-14bqwen2p5-1p5b-instructqwen2p5-32bqwen2p5-32b-instructqwen2p5-72bqwen2p5-72b-instructqwen2p5-7b-instructqwen2p5-coder-0p5bqwen2p5-coder-0p5b-instructqwen2p5-coder-14bqwen2p5-coder-14b-instructqwen2p5-coder-1p5bqwen2p5-coder-1p5b-instructqwen2p5-coder-32bqwen2p5-coder-32b-instructqwen2p5-coder-32b-instruct-128kqwen2p5-coder-32b-instruct-32k-ropeqwen2p5-coder-32b-instruct-64kqwen2p5-coder-3bqwen2p5-coder-3b-instructqwen2p5-coder-7bqwen2p5-coder-7b-instructqwen2p5-math-72b-instructqwen2p5-vl-32b-instructqwen2p5-vl-3b-instructqwen2p5-vl-72b-instructqwen2p5-vl-7b-instructqwen3-0p6bqwen3-14bqwen3-1p7bqwen3-1p7b-fp8-draftqwen3-1p7b-fp8-draft-131072qwen3-1p7b-fp8-draft-40960qwen3-235b-a22bqwen3-235b-a22b-instruct-2507qwen3-30b-a3bqwen3-30b-a3b-instruct-2507qwen3-30b-a3b-thinking-2507qwen3-4bqwen3-4b-instruct-2507qwen3-8bqwen3-coder-30b-a3b-instructqwen3-coder-480b-a35b-instructqwen3-coder-480b-instruct-bf16qwen3-vl-30b-a3b-instructqwen3-vl-30b-a3b-thinkingqwen3-vl-8b-instructqwen3p7-plusrolm-ocrsnorkel-mistral-7b-pairrm-dpostablecode-3bstarcoder-16bstarcoder-7bstarcoder2-15bstarcoder2-3bstarcoder2-7btoppy-m-7byi-34byi-34b-200k-capybarayi-34b-chatyi-6byi-largezephyr-7b-beta
DeepInfra (34 models)
Novita (38 models)
Nebius (4 models)
Replicate (9 models)