LLM token cost calculator

Compare one prompt across current models. Your text stays in this browser.

1Choose a model
2Add text or a file
3Pick a response length

Calculate one request

Private in your browser · 2 MiB max

Your text

Paste text to count it locally.

Or drop a UTF-8 text file

Response length

Medium (750 tokens) is a practical starting point.

How to choose

Short suits a direct answer, Medium a few paragraphs, and Long a detailed draft. Actual usage varies by model.

Ready

Choose a model or add text.

Either can come first.

Choose any model below.

Current model prices

229 models · Bundled fallback · 2026-08-25

← Scroll prices →


Bytedance Seed 1.8bytedance/seed-1.8	256K	64K	$0.2625	$2.1	—	Add workload
Claude 3 Haikuanthropic/claude-3-haiku	200K	4K	$0.2625	$1.3125	—	Add workload
Claude Fable 5anthropic/claude-fable-5	1M	128K	$10.5	$52.5	—	Add workload
Claude Haiku 4.5anthropic/claude-haiku-4.5	200K	64K	$1.05	$5.25	—	Add workload
Claude Opus 4anthropic/claude-opus-4	200K	8K	$15.75	$78.75	—	Add workload
Claude Opus 4.5anthropic/claude-opus-4.5	200K	64K	$5.25	$26.25	—	Add workload
Claude Opus 4.6anthropic/claude-opus-4.6	1M	128K	$5.25	$26.25	—	Add workload
Claude Opus 4.7anthropic/claude-opus-4.7	1M	128K	$5.25	$26.25	—	Add workload
Claude Opus 4.8anthropic/claude-opus-4.8	1M	128K	$5.25	$26.25	—	Add workload
Claude Opus 4.8 (Fast)anthropic/claude-opus-4.8-fast	1M	128K	$10.5	$52.5	—	Add workload
Claude Opus 5anthropic/claude-opus-5	1M	128K	$5.25	$26.25	—	Add workload
Claude Opus 5 (Fast)anthropic/claude-opus-5-fast	1M	128K	$10.5	$52.5	—	Add workload
Claude Sonnet 4anthropic/claude-sonnet-4	1M	8K	$3.15	$15.75	—	Add workload
Claude Sonnet 4.5anthropic/claude-sonnet-4.5	1M	64K	$3.15	$15.75	—	Add workload
Claude Sonnet 4.6anthropic/claude-sonnet-4.6	1M	128K	$3.15	$15.75	—	Add workload
Claude Sonnet 5anthropic/claude-sonnet-5	1M	128K	$2.1	$10.5	—	Add workload
Command Acohere/command-a	256K	8K	$2.625	$10.5	—	Add workload
DeepSeek V3 0324deepseek/deepseek-v3	164K	164K	$0.2835	$1.176	—	Add workload
DeepSeek V3.1deepseek/deepseek-v3.1	164K	128K	$0.2625	$0.9975	—	Add workload
DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminus	131K	66K	$0.2835	$1.05	—	Add workload
DeepSeek V3.2deepseek/deepseek-v3.2	128K	8K	$0.294	$0.441	—	Add workload
DeepSeek V3.2 Thinkingdeepseek/deepseek-v3.2-thinking	128K	8K	$0.651	$1.9425	—	Add workload
DeepSeek V4 Flashdeepseek/deepseek-v4-flash	1M	384K	$0.1365	$0.273	—	Add workload
DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731	1M	384K	$0.0798	$0.16065	—	Add workload
DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp	1M	384K	$0.231	$0.693	—	Add workload
DeepSeek V4 Prodeepseek/deepseek-v4-pro	1M	1M	$1.827	$3.654	—	Add workload
DeepSeek V4 Pro 0813deepseek/deepseek-v4-pro-0813	1M	384K	$0.693	$2.079	—	Add workload
DeepSeek-R1deepseek/deepseek-r1	128K	8K	$1.4175	$5.67	—	Add workload
Devstral 2mistral/devstral-2	256K	256K	$0.42	$2.1	—	Add workload
Devstral Small 2mistral/devstral-small-2	256K	256K	$0.105	$0.315	—	Add workload
Fugu Ultrasakana/fugu-ultra	1M	1M	$5.25	$31.5	—	Add workload
Gemini 2.5 Flashgoogle/gemini-2.5-flash	1M	66K	$0.315	$2.625	—	Add workload
Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite	1M	66K	$0.105	$0.42	—	Add workload
Gemini 2.5 Progoogle/gemini-2.5-pro	1M	66K	$1.3125	$10.5	—	Add workload
Gemini 3 Flashgoogle/gemini-3-flash	1M	65K	$0.525	$3.15	—	Add workload
Gemini 3.1 Flash Image (Nano Banana 2)google/gemini-3.1-flash-image	131K	33K	$0.525	$3.15	—	Add workload
Gemini 3.1 Flash Image Preview (Nano Banana 2)google/gemini-3.1-flash-image-preview	131K	33K	$0.525	$3.15	—	Add workload
Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-lite	1M	65K	$0.2625	$1.575	—	Add workload
Gemini 3.1 Flash Lite Image (Nano Banana 2 Lite)google/gemini-3.1-flash-lite-image	66K	4K	$0.2625	$1.575	—	Add workload
Gemini 3.1 Pro Previewgoogle/gemini-3.1-pro-preview	1M	64K	$2.1	$12.6	—	Add workload
Gemini 3.5 Flashgoogle/gemini-3.5-flash	1M	64K	$1.575	$9.45	—	Add workload
Gemini 3.5 Flash Litegoogle/gemini-3.5-flash-lite	1M	65K	$0.315	$2.625	—	Add workload
Gemini 3.6 Flashgoogle/gemini-3.6-flash	1M	64K	$0.7875	$3.9375	—	Add workload
Gemini 3.7 Flashgoogle/gemini-3.7-flash	1M	66K	$0.7875	$3.9375	—	Add workload
Gemini Omni Flash Previewgoogle/gemini-omni-flash-preview	1M	58K	$1.575	$9.45	—	Add workload
Gemma 4 31B ITgoogle/gemma-4-31b-it	262K	131K	$0.147	$0.42	—	Add workload
GLM 4.5zai/glm-4.5	128K	96K	$0.63	$2.31	—	Add workload
GLM 4.5 Airzai/glm-4.5-air	128K	96K	$0.21	$1.155	—	Add workload
GLM 4.5Vzai/glm-4.5v	66K	16K	$0.63	$1.89	—	Add workload
GLM 4.6zai/glm-4.6	200K	96K	$0.63	$2.31	—	Add workload
GLM 4.7zai/glm-4.7	200K	120K	$0.63	$2.31	—	Add workload
GLM 4.7 Flashzai/glm-4.7-flash	200K	131K	$0.0735	$0.42	—	Add workload
GLM 4.7 FlashXzai/glm-4.7-flashx	200K	128K	$0.063	$0.42	—	Add workload
GLM 5zai/glm-5	203K	131K	$1.05	$3.36	—	Add workload
GLM 5 Turbozai/glm-5-turbo	203K	131K	$1.26	$4.2	—	Add workload
GLM 5.1zai/glm-5.1	203K	64K	$1.47	$4.62	—	Add workload
GLM 5.2zai/glm-5.2	1M	128K	$0.84	$2.6775	—	Add workload
GLM 5.2 Fastzai/glm-5.2-fast	1M	128K	$2.205	$6.93	—	Add workload
GLM 5.3zai/glm-5.3	1M	13K	$1.47	$4.62	—	Add workload
GLM 5V Turbozai/glm-5v-turbo	200K	128K	$1.26	$4.2	—	Add workload
Google Gemma 4 26B A4Bgoogle/gemma-4-26b-a4b-it	262K	131K	$0.1575	$0.63	—	Add workload
GPT 5.1 Codex Maxopenai/gpt-5.1-codex-max	400K	128K	$1.3125	$10.5	—	Add workload
GPT 5.1 Codex Miniopenai/gpt-5.1-codex-mini	400K	128K	$0.2625	$2.1	—	Add workload
GPT 5.1 Thinkingopenai/gpt-5.1-thinking	400K	128K	$1.3125	$10.5	—	Add workload
GPT 5.1 Thinking (Fast)openai/gpt-5.1-thinking-fast	400K	128K	$2.625	$21	—	Add workload
GPT 5.2openai/gpt-5.2	400K	128K	$1.8375	$14.7	—	Add workload
GPT 5.2openai/gpt-5.2-pro	400K	128K	$22.05	$176.4	—	Add workload
GPT 5.2 (Fast)openai/gpt-5.2-fast	400K	128K	$3.675	$29.4	—	Add workload
GPT 5.2 Codexopenai/gpt-5.2-codex	400K	128K	$1.8375	$14.7	—	Add workload
GPT 5.3 Codexopenai/gpt-5.3-codex	400K	128K	$1.8375	$14.7	—	Add workload
GPT 5.3 Codex (Fast)openai/gpt-5.3-codex-fast	400K	128K	$3.675	$29.4	—	Add workload
GPT 5.4openai/gpt-5.4	1.1M	128K	$2.625	$15.75	—	Add workload
GPT 5.4 (Fast)openai/gpt-5.4-fast	1.1M	128K	$5.25	$31.5	—	Add workload
GPT 5.4 Miniopenai/gpt-5.4-mini	400K	128K	$0.7875	$4.725	—	Add workload
GPT 5.4 Mini (Fast)openai/gpt-5.4-mini-fast	400K	128K	$1.575	$9.45	—	Add workload
GPT 5.4 Nanoopenai/gpt-5.4-nano	400K	128K	$0.21	$1.3125	—	Add workload
GPT 5.4 Proopenai/gpt-5.4-pro	1.1M	128K	$31.5	$189	—	Add workload
GPT 5.5openai/gpt-5.5	1M	128K	$5.25	$31.5	—	Add workload
GPT 5.5 (Fast)openai/gpt-5.5-fast	1M	128K	$13.125	$78.75	—	Add workload
GPT 5.5 Proopenai/gpt-5.5-pro	1M	128K	$31.5	$189	—	Add workload
GPT 5.6 Lunaopenai/gpt-5.6-luna	1.1M	128K	$0.21	$1.26	—	Add workload
GPT 5.6 Luna (Fast)openai/gpt-5.6-luna-fast	1.1M	128K	$0.42	$2.52	—	Add workload
GPT 5.6 Solopenai/gpt-5.6-sol	1.1M	128K	$2.1	$10.5	—	Add workload
GPT 5.6 Sol (Fast)openai/gpt-5.6-sol-fast	1.1M	128K	$4.2	$21	—	Add workload
GPT 5.6 Terraopenai/gpt-5.6-terra	1.1M	128K	$2.1	$12.6	—	Add workload
GPT 5.6 Terra (Fast)openai/gpt-5.6-terra-fast	1.1M	128K	$4.2	$25.2	—	Add workload
GPT OSS 120Bopenai/gpt-oss-120b	131K	131K	$0.105	$0.525	—	Add workload
GPT OSS 20Bopenai/gpt-oss-20b	131K	8K	$0.0525	$0.21	—	Add workload
GPT OSS Safeguard 120Bopenai/gpt-oss-safeguard-120b	128K	16K	$0.1575	$0.63	—	Add workload
GPT OSS Safeguard 20Bopenai/gpt-oss-safeguard-20b	128K	16K	$0.0735	$0.21	—	Add workload
GPT-3.5 Turboopenai/gpt-3.5-turbo	16K	4K	$0.525	$1.575	—	Add workload
GPT-4 Turboopenai/gpt-4-turbo	128K	4K	$10.5	$31.5	—	Add workload
GPT-4.1openai/gpt-4.1	1M	33K	$2.1	$8.4	—	Add workload
GPT-4.1 (Fast)openai/gpt-4.1-fast	1M	33K	$3.675	$14.7	—	Add workload
GPT-4.1 miniopenai/gpt-4.1-mini	1M	33K	$0.42	$1.68	—	Add workload
GPT-4.1 mini (Fast)openai/gpt-4.1-mini-fast	1M	33K	$0.735	$2.94	—	Add workload
GPT-4.1 nanoopenai/gpt-4.1-nano	1M	33K	$0.105	$0.42	—	Add workload
GPT-4.1 nano (Fast)openai/gpt-4.1-nano-fast	1M	33K	$0.21	$0.84	—	Add workload
GPT-4oopenai/gpt-4o	128K	16K	$2.625	$10.5	—	Add workload
GPT-4o (Fast)openai/gpt-4o-fast	128K	16K	$4.4625	$17.85	—	Add workload
GPT-4o miniopenai/gpt-4o-mini	128K	16K	$0.1575	$0.63	—	Add workload
GPT-4o mini (Fast)openai/gpt-4o-mini-fast	128K	16K	$0.2625	$1.05	—	Add workload
GPT-5openai/gpt-5	400K	128K	$1.3125	$10.5	—	Add workload
GPT-5 (Fast)openai/gpt-5-fast	400K	128K	$2.625	$21	—	Add workload
GPT-5 miniopenai/gpt-5-mini	400K	128K	$0.2625	$2.1	—	Add workload
GPT-5 mini (Fast)openai/gpt-5-mini-fast	400K	128K	$0.4725	$3.78	—	Add workload
GPT-5 nanoopenai/gpt-5-nano	400K	128K	$0.0525	$0.42	—	Add workload
GPT-5 proopenai/gpt-5-pro	400K	272K	$15.75	$126	—	Add workload
GPT-5-Codexopenai/gpt-5-codex	400K	128K	$1.3125	$10.5	—	Add workload
GPT-5.1-Codexopenai/gpt-5.1-codex	400K	128K	$1.3125	$10.5	—	Add workload
Grok 4.1 Fast Non-Reasoningspacexai/grok-4.1-fast-non-reasoning	1M	1M	$0.21	$0.525	—	Add workload
Grok 4.1 Fast Reasoningspacexai/grok-4.1-fast-reasoning	1M	1M	$0.21	$0.525	—	Add workload
Grok 4.20 Beta Non-Reasoningspacexai/grok-4.20-non-reasoning-beta	2M	2M	$1.3125	$2.625	—	Add workload
Grok 4.20 Beta Reasoningspacexai/grok-4.20-reasoning-beta	2M	2M	$1.3125	$2.625	—	Add workload
Grok 4.20 Multi Agent Betaspacexai/grok-4.20-multi-agent-beta	2M	2M	$1.3125	$2.625	—	Add workload
Grok 4.20 Multi-Agentspacexai/grok-4.20-multi-agent	2M	2M	$1.3125	$2.625	—	Add workload
Grok 4.20 Non-Reasoningspacexai/grok-4.20-non-reasoning	2M	2M	$1.3125	$2.625	—	Add workload
Grok 4.20 Reasoningspacexai/grok-4.20-reasoning	2M	2M	$1.3125	$2.625	—	Add workload
Grok 4.3spacexai/grok-4.3	1M	1M	$1.3125	$2.625	—	Add workload
Grok 4.5spacexai/grok-4.5	500K	500K	$2.1	$6.3	—	Add workload
Grok 4.6spacexai/grok-4.6	500K	500K	$2.1	$6.3	—	Add workload
Grok Build 0.1spacexai/grok-build-0.1	256K	256K	$1.05	$2.1	—	Add workload
Hy3tencent/hy3	256K	128K	$0.1386	$0.5544	—	Add workload
Inklingthinkingmachines/inkling	256K	256K	$1.05	$4.2525	—	Add workload
Inkling Smallthinkingmachines/inkling-small	1M	1M	$0.525	$1.26	—	Add workload
Interfaze Betainterfaze/interfaze-beta	1M	32K	$1.575	$3.675	—	Add workload
Kat Coder Air V2.5kwaipilot/kat-coder-air-v2.5	256K	80K	$0.1575	$0.63	—	Add workload
Kat Coder Pro V2kwaipilot/kat-coder-pro-v2	256K	256K	$0.315	$1.26	—	Add workload
Kat Coder Pro V2.5kwaipilot/kat-coder-pro-v2.5	256K	80K	$0.777	$3.108	—	Add workload
KAT-Coder-Pro V1kwaipilot/kat-coder-pro-v1	256K	32K	$0.315	$1.26	—	Add workload
Kimi K2 Instructmoonshotai/kimi-k2	131K	131K	$0.5985	$2.415	—	Add workload
Kimi K2 Thinkingmoonshotai/kimi-k2-thinking	216K	216K	$0.4935	$2.1	—	Add workload
Kimi K2.5moonshotai/kimi-k2.5	262K	262K	$0.63	$3.15	—	Add workload
Kimi K2.6moonshotai/kimi-k2.6	262K	262K	$0.9975	$4.2	—	Add workload
Kimi K2.7 Codemoonshotai/kimi-k2.7-code	256K	33K	$0.9975	$4.2	—	Add workload
Kimi K2.7 Code High Speedmoonshotai/kimi-k2.7-code-highspeed	262K	33K	$1.995	$8.4	—	Add workload
Kimi K3moonshotai/kimi-k3	1M	131K	$3.15	$15.75	—	Add workload
Kimi K3 Fastmoonshotai/kimi-k3-fast	1M	131K	$4.725	$23.625	—	Add workload
Laguna S 2.1poolside/laguna-s-2.1	1M	131K	$0.105	$0.21	—	Add workload
Laguna S 2.1 Freepoolside/laguna-s-2.1-free	256K	33K	Free	Free	—	Add workload
Ling 3.0 Flashinclusionai/ling-3.0-flash	256K	32K	$0.063	$0.189	—	Add workload
Llama 3.1 70B Instructmeta/llama-3.1-70b	128K	8K	$0.756	$0.756	—	Add workload
Llama 3.1 8B Instructmeta/llama-3.1-8b	128K	8K	$0.231	$0.231	—	Add workload
Llama 3.3 70B Instructmeta/llama-3.3-70b	128K	8K	$0.756	$0.756	—	Add workload
Llama 4 Maverick 17B Instructmeta/llama-4-maverick	128K	8K	$0.252	$1.0185	—	Add workload
Llama 4 Scout 17B Instructmeta/llama-4-scout	128K	8K	$0.1785	$0.693	—	Add workload
Mercury 2inception/mercury-2	128K	128K	$0.2625	$0.7875	—	Add workload
Mercury Coder Small Betainception/mercury-coder-small	32K	16K	$0.2625	$1.05	—	Add workload
MiMo M2.5xiaomi/mimo-v2.5	1.1M	131K	$0.147	$0.294	—	Add workload
MiMo V2.5 Proxiaomi/mimo-v2.5-pro	1.1M	131K	$0.45675	$0.9135	—	Add workload
MiniMax M2minimax/minimax-m2	205K	205K	$0.315	$1.26	—	Add workload
MiniMax M2.1minimax/minimax-m2.1	205K	131K	$0.315	$1.26	—	Add workload
MiniMax M2.1 Lightningminimax/minimax-m2.1-lightning	205K	131K	$0.315	$2.52	—	Add workload
MiniMax M2.5minimax/minimax-m2.5	205K	131K	$0.315	$1.26	—	Add workload
MiniMax M2.5 High Speedminimax/minimax-m2.5-highspeed	205K	131K	$0.63	$2.52	—	Add workload
Minimax M2.7minimax/minimax-m2.7	205K	131K	$0.315	$1.26	—	Add workload
MiniMax M2.7 High Speedminimax/minimax-m2.7-highspeed	205K	131K	$0.63	$2.52	—	Add workload
MiniMax M3minimax/minimax-m3	1M	1M	$0.315	$1.26	—	Add workload
Ministral 14Bmistral/ministral-14b	256K	256K	$0.21	$0.21	—	Add workload
Ministral 3Bmistral/ministral-3b	128K	4K	$0.105	$0.105	—	Add workload
Ministral 8Bmistral/ministral-8b	128K	4K	$0.1575	$0.1575	—	Add workload
Mistral Codestralmistral/codestral	128K	4K	$0.315	$0.945	—	Add workload
Mistral Large 3mistral/mistral-large-3	256K	256K	$0.525	$1.575	—	Add workload
Mistral Medium 3.1mistral/mistral-medium	128K	64K	$0.42	$2.1	—	Add workload
Mistral Medium Latestmistral/mistral-medium-3.5	256K	256K	$1.575	$7.875	—	Add workload
Mistral Nemo 12Bmistral/mistral-nemo	128K	128K	$0.1575	$0.1575	—	Add workload
Mistral Smallmistral/mistral-small	32K	4K	$0.105	$0.315	—	Add workload
Morph V3 Fastmorph/morph-v3-fast	82K	16K	$0.84	$1.26	—	Add workload
Morph V3 Largemorph/morph-v3-large	82K	16K	$0.945	$1.995	—	Add workload
Muse Glimmer 30Bmeta/muse-glimmer-30b	131K	131K	$0.3675	$1.575	—	Add workload
Muse Spark 1.1meta/muse-spark-1.1	1M	1M	$1.3125	$4.4625	—	Add workload
Muse Spark 1.2meta/muse-spark-1.2	1M	1M	$1.3125	$4.4625	—	Add workload
Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributor	1M	1M	$0.105	$0.21	—	Add workload
Nano Banana (Gemini 2.5 Flash Image)google/gemini-2.5-flash-image	33K	66K	$0.315	$2.625	—	Add workload
Nano Banana Pro (Gemini 3 Pro Image)google/gemini-3-pro-image	66K	33K	$2.1	$12.6	—	Add workload
Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3b	262K	262K	$0.0525	$0.252	—	Add workload
Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55b	1M	65K	$0.63	$2.52	—	Add workload
Nemotron 3.5 Lightning 30Bnvidia/nemotron-3.5-lightning	262K	131K	$0.0525	$0.21	—	Add workload
Nova 2 Liteamazon/nova-2-lite	1M	1M	$0.315	$2.625	—	Add workload
Nova Liteamazon/nova-lite	300K	8K	$0.063	$0.252	—	Add workload
Nova Microamazon/nova-micro	128K	8K	$0.03675	$0.147	—	Add workload
Nova Proamazon/nova-pro	300K	8K	$0.84	$3.36	—	Add workload
NVIDIA Nemotron 3 Super 120B A12Bnvidia/nemotron-3-super-120b-a12b	256K	32K	$0.1575	$0.6825	—	Add workload
Nvidia Nemotron Nano 12B V2 VLnvidia/nemotron-nano-12b-v2-vl	131K	131K	$0.21	$0.63	—	Add workload
Nvidia Nemotron Nano 9B V2nvidia/nemotron-nano-9b-v2	131K	131K	$0.063	$0.2415	—	Add workload
o1openai/o1	200K	100K	$15.75	$63	—	Add workload
o3openai/o3	200K	100K	$2.1	$8.4	—	Add workload
o3 (Fast)openai/o3-fast	200K	100K	$3.675	$14.7	—	Add workload
o3 Proopenai/o3-pro	200K	100K	$21	$84	—	Add workload
o3-miniopenai/o3-mini	200K	100K	$1.155	$4.62	—	Add workload
o4-miniopenai/o4-mini	200K	100K	$1.155	$4.62	—	Add workload
o4-mini (Fast)openai/o4-mini-fast	200K	100K	$2.1	$8.4	—	Add workload
Pixtral 12B 2409mistral/pixtral-12b	128K	4K	$0.1575	$0.1575	—	Add workload
Qwen 3 32Balibaba/qwen-3-32b	128K	8K	$0.168	$0.672	—	Add workload
Qwen 3 Coder 30B A3B Instructalibaba/qwen3-coder-30b-a3b	262K	8K	$0.1575	$0.63	—	Add workload
Qwen 3 Max Thinkingalibaba/qwen3-max-thinking	256K	66K	$1.26	$6.3	—	Add workload
Qwen 3.5 Flashalibaba/qwen3.5-flash	1M	64K	$0.105	$0.42	—	Add workload
Qwen 3.5 Plusalibaba/qwen3.5-plus	1M	64K	$0.42	$2.52	—	Add workload
Qwen 3.6 27Balibaba/qwen3.6-27b	256K	256K	$0.63	$3.78	—	Add workload
Qwen 3.6 Max Previewalibaba/qwen-3.6-max-preview	240K	64K	$1.365	$8.19	—	Add workload
Qwen 3.6 Plusalibaba/qwen3.6-plus	1M	64K	$0.525	$3.15	—	Add workload
Qwen 3.7 Flashalibaba/qwen3.7-flash	991K	64K	$0.0315	$0.1365	—	Add workload
Qwen 3.7 Maxalibaba/qwen3.7-max	991K	64K	$2.625	$7.875	—	Add workload
Qwen 3.7 Plusalibaba/qwen3.7-plus	1M	64K	$0.42	$1.68	—	Add workload
Qwen 3.8 Maxalibaba/qwen3.8-max	1M	128K	$2.1	$6.3	—	Add workload
Qwen3 235B A22Balibaba/qwen-3-235b	262K	16K	$0.231	$0.924	—	Add workload
Qwen3 Coder 480B A35B Instructalibaba/qwen3-coder	262K	66K	$1.575	$7.875	—	Add workload
Qwen3 Coder Nextalibaba/qwen3-coder-next	256K	256K	$0.525	$1.26	—	Add workload
Qwen3 Coder Plusalibaba/qwen3-coder-plus	1M	66K	$1.05	$5.25	—	Add workload
Qwen3 Maxalibaba/qwen3-max	262K	33K	$1.26	$6.3	—	Add workload
Qwen3 Max Previewalibaba/qwen3-max-preview	262K	33K	$1.26	$6.3	—	Add workload
Qwen3 Next 80B A3B Instructalibaba/qwen3-next-80b-a3b-instruct	131K	33K	$0.1575	$1.26	—	Add workload
Qwen3 Next 80B A3B Thinkingalibaba/qwen3-next-80b-a3b-thinking	131K	33K	$0.1575	$1.26	—	Add workload
Qwen3 VL 235B A22B Instructalibaba/qwen3-vl-235b-a22b-instruct	131K	129K	$0.42	$1.68	—	Add workload
Qwen3 VL 235B A22B Instructalibaba/qwen3-vl-instruct	131K	129K	$0.42	$1.68	—	Add workload
Qwen3 VL 235B A22B Thinkingalibaba/qwen3-235b-a22b-thinking	131K	33K	$0.42	$4.2	—	Add workload
Qwen3 VL 235B A22B Thinkingalibaba/qwen3-vl-thinking	131K	33K	$0.42	$4.2	—	Add workload
Qwen3-14Balibaba/qwen-3-14b	41K	16K	$0.126	$0.252	—	Add workload
Qwen3-30B-A3Balibaba/qwen-3-30b	41K	16K	$0.126	$0.525	—	Add workload
Qwen3.8 2.4T A95Balibaba/qwen3.8-2.4t-a95b	262K	131K	$2.1	$6.3	—	Add workload
Qwen3.8 27Balibaba/qwen3.8-27b	1M	131K	$0.5775	$3.465	—	Add workload
Sakana Namazusakana/namazu	256K	256K	$0.9975	$4.2	—	Add workload
Seed 1.6bytedance/seed-1.6	256K	32K	$0.2625	$2.1	—	Add workload
Step 3.7 Flashstepfun/step-3.7-flash	256K	256K	$0.21	$1.2075	—	Add workload
StepFun 3.5 Flashstepfun/step-3.5-flash	262K	262K	$0.0945	$0.315	—	Add workload
Tencent Hy-MT2-Litetencent/hy-mt2-lite	8K	4K	$0.0462	$0.18585	—	Add workload
Tencent Hy-MT2-Plustencent/hy-mt2-plus	8K	4K	$0.0777	$0.30975	—	Add workload
Tencent Hy-MT2-Protencent/hy-mt2-pro	8K	4K	$0.0777	$0.30975	—	Add workload
Trinity Large Thinkingarcee-ai/trinity-large-thinking	262K	80K	$0.2625	$0.945	—	Add workload

How estimates work

Formula, tokenizer limits and context fit.

How the calculation works

Input cost is the local token count multiplied by the model’s input rate. Output cost is your expected output tokens multiplied by its output rate. The total is for one request and uses decimal arithmetic rather than binary floating point.

Per-token and per-million rates

MiniRouter publishes decimal USD rates per token. The table expands those tiny values to the familiar price per one million tokens, while calculations continue to use the original per-token decimal.

Local count versus proxy estimate

The browser uses the o200k_base tokenizer. Compatible allowlisted models receive a local-count label. Other families receive a proxy-estimate label because their provider tokenizers can differ. No prompt or file is sent to a provider to count it.

What fitting means

A row fits when the local or proxy input count plus expected output stays within its reported context window, and expected output stays within its reported output limit when one exists. Proxy-family fit is always labelled as an estimate.