# TokenPulse > Live AI API Pricing, Token Cost Calculator & Cloud GPU Break-Even Engine Updated: 2026-11-21 22:27 UTC Full machine-readable JSON pricing index: https://tokenpulse.pages.dev/api/models.json ## Featured Live Models - Thinking Machines: Inkling 2 Mini (`thinkingmachines/inkling-2-mini`): Input $0.075/1M, Output $0.300/1M, Context 1.0M — https://tokenpulse.pages.dev/models/thinkingmachines-inkling-2-mini/ - RadixArk: DaisyRose 27B (`radixark/daisyrose-27b`): Input $0.150/1M, Output $1.88/1M, Context 262K — https://tokenpulse.pages.dev/models/radixark-daisyrose-27b/ - Mistral: Pixtral Large 2502 (`mistralai/pixtral-large-2502`): Input $2.00/1M, Output $6.00/1M, Context 128K — https://tokenpulse.pages.dev/models/mistralai-pixtral-large-2502/ - Google: Gemini 4 Neon (batch) (`google/gemini-4-neon:batch`): Input $1.50/1M, Output $7.50/1M, Context 1.0M — https://tokenpulse.pages.dev/models/google-gemini-4-neon-batch/ - Google: Gemini 4 Neon (`google/gemini-4-neon`): Input $3.00/1M, Output $15.00/1M, Context 1.0M — https://tokenpulse.pages.dev/models/google-gemini-4-neon/ - OpenAI: GPT-6.2 Astra Pro (batch) (`openai/gpt-6.2-astra-pro:batch`): Input $4.00/1M, Output $20.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-astra-pro-batch/ - OpenAI: GPT-6.2 Astra Pro (`openai/gpt-6.2-astra-pro`): Input $8.00/1M, Output $40.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-astra-pro/ - OpenAI: GPT-6.2 Astra (batch) (`openai/gpt-6.2-astra:batch`): Input $4.00/1M, Output $20.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-astra-batch/ - OpenAI: GPT-6.2 Astra (`openai/gpt-6.2-astra`): Input $8.00/1M, Output $40.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-astra/ - OpenAI: GPT-6.2 Sol Pro (batch) (`openai/gpt-6.2-sol-pro:batch`): Input $1.00/1M, Output $5.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-sol-pro-batch/ - OpenAI: GPT-6.2 Sol Pro (`openai/gpt-6.2-sol-pro`): Input $2.00/1M, Output $10.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-sol-pro/ - OpenAI: GPT-6.2 Sol (batch) (`openai/gpt-6.2-sol:batch`): Input $1.00/1M, Output $5.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-sol-batch/ - OpenAI: GPT-6.2 Sol (`openai/gpt-6.2-sol`): Input $2.00/1M, Output $10.00/1M, Context 1.1M — https://tokenpulse.pages.dev/models/openai-gpt-6-2-sol/ - Tencent: Hy4 flash (`tencent/hy4-flash`): Input $0.035/1M, Output $0.141/1M, Context 1.0M — https://tokenpulse.pages.dev/models/tencent-hy4-flash/ - Qwen: Qwen4 Max (`qwen/qwen4-max`): Input $1.43/1M, Output $4.28/1M, Context 1M — https://tokenpulse.pages.dev/models/qwen-qwen4-max/ - inclusionAI: Ling 3.2 Flash (free) (`inclusionai/ling-3.2-flash:free`): Input $0.00/1M, Output $0.00/1M, Context 1.0M — https://tokenpulse.pages.dev/models/inclusionai-ling-3-2-flash-free/ - Google: Gemini 4 Hydrogen (batch) (`google/gemini-4-hydrogen:batch`): Input $0.750/1M, Output $3.75/1M, Context 1.0M — https://tokenpulse.pages.dev/models/google-gemini-4-hydrogen-batch/ - Google: Gemini 4 Hydrogen (`google/gemini-4-hydrogen`): Input $1.50/1M, Output $7.50/1M, Context 1.0M — https://tokenpulse.pages.dev/models/google-gemini-4-hydrogen/ - Baidu: ERNIE-5.5-Flash-Preview (free) (`baidu/ernie-5.5-flash-preview:free`): Input $0.00/1M, Output $0.00/1M, Context 1.0M — https://tokenpulse.pages.dev/models/baidu-ernie-5-5-flash-preview-free/ - Baidu: ERNIE-Light-DT-1.0 (`baidu/ernie-light-dt-1.0-intl`): Input $1.13/1M, Output $3.94/1M, Context 1.0M — https://tokenpulse.pages.dev/models/baidu-ernie-light-dt-1-0-intl/ - Google: Gemini 4 Carbon (batch) (`google/gemini-4-carbon:batch`): Input $1.00/1M, Output $5.00/1M, Context 1.0M — https://tokenpulse.pages.dev/models/google-gemini-4-carbon-batch/ - Google: Gemini 4 Carbon (`google/gemini-4-carbon`): Input $2.00/1M, Output $10.00/1M, Context 1.0M — https://tokenpulse.pages.dev/models/google-gemini-4-carbon/ - Nex AGI: Nex-N2.6 (`nex-agi/nex-n2.6`): Input $0.120/1M, Output $0.400/1M, Context 262K — https://tokenpulse.pages.dev/models/nex-agi-nex-n2-6/ - Thinking Machines: Inkling 2 Small (`thinkingmachines/inkling-2-small`): Input $0.300/1M, Output $1.00/1M, Context 1.0M — https://tokenpulse.pages.dev/models/thinkingmachines-inkling-2-small/ - Anthropic: Claude Fable 5.2 (batch) (`anthropic/claude-fable-5.2:batch`): Input $4.00/1M, Output $20.00/1M, Context 1M — https://tokenpulse.pages.dev/models/anthropic-claude-fable-5-2-batch/ - Anthropic: Claude Fable 5.2 (`anthropic/claude-fable-5.2`): Input $8.00/1M, Output $40.00/1M, Context 1M — https://tokenpulse.pages.dev/models/anthropic-claude-fable-5-2/ - Meta: Muse Ember (`meta/muse-ember`): Input $0.100/1M, Output $0.500/1M, Context 1.0M — https://tokenpulse.pages.dev/models/meta-muse-ember/ - LiquidAI: LFM3-1.7B (free) (`liquid/lfm-3-1.7b:free`): Input $0.00/1M, Output $0.00/1M, Context 262K — https://tokenpulse.pages.dev/models/liquid-lfm-3-1-7b-free/ - LiquidAI: LFM3-1.7B (`liquid/lfm-3-1.7b`): Input $0.080/1M, Output $0.200/1M, Context 262K — https://tokenpulse.pages.dev/models/liquid-lfm-3-1-7b/ - Google: Gemini Omni 1.2 Flash (`google/gemini-omni-1.2-flash`): Input $1.50/1M, Output $9.00/1M, Context 131K — https://tokenpulse.pages.dev/models/google-gemini-omni-1-2-flash/