Pricing
Pay the tide, not the list price.
One rule: the API list price times the live multiplier, locked when your request starts. No subscriptions, no seats, no minimum spend.
Live multipliers
Standard
0.695×
30% below API list price
Low Tide
0.486×
51% below API list price
Today’s range: 0.720× → 0.504×
Updated 11:45 UTC
How a charge is computed
charge = API list cost × multiplier
1M output tokens of GLM 5.2 at 0.695×: $4.40 × 0.695 = $3.06
The multiplier is locked at admission and returned with every response, with the list cost and the charge. API list prices come from Venice’s published catalog.
Tide tables
Published in advance and never raised during the day. Tomorrow’s table appears at 12:00 UTC.
The Standard multiplier falls from 0.720× at 00:00 UTC to 0.504× at 24:00 UTC.
Level 0.72 · decay 0.30 · convexity 3 · Low Tide 0.70× Standard, floor 0.20
Every model, priced live
API list price and today’s Tokentide price for every model we serve. Token prices are per 1M tokens, input / output.
95 models
| Model | Privacy | API list price | Tokentide now | Low Tide |
|---|---|---|---|---|
| GLM 5.2zai-org-glm-5-21M contextReasoningToolsCodeWeb search | Private | $1.40 / $4.40per 1M tokens | $0.972 / $3.06−30% | $0.681 / $2.14 |
| DeepSeek V4.1 Flashdeepseek-v4-1-flash1M contextVisionReasoningToolsCode | Private | $0.30 / $1.20per 1M tokens | $0.208 / $0.833−30% | $0.146 / $0.583 |
| Kimi K3kimi-k31M contextVisionReasoningToolsCode | Private | $3.75 / $18.75per 1M tokens | $2.60 / $13.02−30% | $1.82 / $9.12 |
| Grok 4.7grok-4-7500K contextVisionReasoningToolsCode | Private | $2.27 / $6.80per 1M tokens | $1.58 / $4.72−30% | $1.10 / $3.31 |
| Clef (System One)clef-api | Private | $0.05 / $0.05per 1M tokens | $0.035 / $0.035−30% | $0.024 / $0.024 |
| FireRedfirered-image-edit | Private | $0.04per edit | $0.028−30% | $0.019 |
| Grok Imaginegrok-imagine-edit | Private | $0.03per edit | $0.021−30% | $0.015 |
| Grok Imagine 2.0grok-imagine-image-2-0-edit | Private | $0.07per edit | $0.049−30% | $0.034 |
| BGE-EN-ICLtext-embedding-bge-en-icl | Private | $0.013 / $0.013per 1M tokens | $0.0087 / $0.0087−30% | $0.0061 / $0.0061 |
| BGE-M3text-embedding-bge-m3 | Private | $0.15 / $0.60per 1M tokens | $0.104 / $0.417−30% | $0.073 / $0.292 |
| Multilingual E5 Large Instructtext-embedding-multilingual-e5-large-instruct | Private | $0.013 / $0.013per 1M tokens | $0.0087 / $0.0087−30% | $0.0061 / $0.0061 |
| Nemotron Embed VL 1B v2text-embedding-nemotron-embed-vl-1b-v2 | Private | $0.013 / $0.013per 1M tokens | $0.0087 / $0.0087−30% | $0.0061 / $0.0061 |
| Qwen3 Embedding 0.6Btext-embedding-qwen3-0-6b | Private | $0.013 / $0.013per 1M tokens | $0.0087 / $0.0087−30% | $0.0061 / $0.0061 |
| Qwen3 Embedding 8Btext-embedding-qwen3-8b | Private | $0.013 / $0.013per 1M tokens | $0.0087 / $0.0087−30% | $0.0061 / $0.0061 |
| Anime (WAI)wai-Illustrious | Private | $0.01per image | $0.0069−30% | $0.0049 |
| Chromachroma | Private | $0.01per image | $0.0069−30% | $0.0049 |
| Grok Imaginegrok-imagine-image | Private | $0.03per image | $0.021−30% | $0.015 |
| Grok Imagine 2.0grok-imagine-image-2-0 | Private | $0.07per image | $0.049−30% | $0.034 |
| Hunyuan Image 3.0hunyuan-image-v3 | Private | $0.09per image | $0.063−30% | $0.044 |
| Krea 2 Turbokrea-2-turbo | Private | $0.04per image | $0.028−30% | $0.019 |
| Venice SD35venice-sd35 | Private | $0.01per image | $0.0069−30% | $0.0049 |
| Z-Image Turboz-image-turbo | Private | $0.01per image | $0.0069−30% | $0.0049 |
| Parakeet ASRnvidia/parakeet-tdt-0.6b-v3 | Private | $0.0001per audio second | $0.000069−30% | $0.000049 |
| Whisper Large V3openai/whisper-large-v3 | Private | $0.0001per audio second | $0.000069−30% | $0.000049 |
| Wizper (Whisper v3)fal-ai/wizper | Private | $0.0001per audio second | $0.000069−30% | $0.000049 |
| DeepSeek V3.2deepseek-v3.2160K contextReasoningToolsWeb searchStructured output | Private | $0.33 / $0.48per 1M tokens | $0.229 / $0.333−30% | $0.16 / $0.233 |
| DeepSeek V4 Flashe2ee-deepseek-v4-flash1M contextReasoningToolsCodeWeb search | E2EE | $0.182 / $0.373per 1M tokens | $0.126 / $0.259−30% | $0.088 / $0.181 |
| DeepSeek V4 Flash 0423deepseek-v4-flash1M contextReasoningToolsCodeWeb search | Private | $0.138 / $0.275per 1M tokens | $0.096 / $0.191−30% | $0.067 / $0.134 |
| DeepSeek V4 Flash 0731deepseek-v4-flash-07311M contextReasoningToolsCodeWeb search | Private | $0.13 / $0.26per 1M tokens | $0.09 / $0.181−30% | $0.063 / $0.126 |
| DeepSeek V4 Flash 0731 Fastdeepseek-v4-flash-0731-fast1M contextReasoningToolsCodeWeb search | Private | $0.35 / $0.70per 1M tokens | $0.243 / $0.486−30% | $0.17 / $0.34 |
| DeepSeek V4 Prodeepseek-v4-pro1M contextReasoningToolsCodeWeb search | Private | $1.65 / $3.30per 1M tokens | $1.15 / $2.29−30% | $0.802 / $1.60 |
| DeepSeek V4 Pro 0813deepseek-v4-pro-08131M contextReasoningToolsCodeWeb search | Private | $1.65 / $4.95per 1M tokens | $1.15 / $3.44−30% | $0.802 / $2.41 |
| DeepSeek v4.1 Flash (1017)deepseek-v4-1-flash-10171M contextVisionReasoningToolsCode | Private | $0.30 / $1.20per 1M tokens | $0.208 / $0.833−30% | $0.146 / $0.583 |
| GLM 4.6zai-org-glm-4.6198K contextReasoningToolsWeb searchStructured output | Private | $0.43 / $1.75per 1M tokens | $0.299 / $1.22−30% | $0.209 / $0.851 |
| GLM 4.7zai-org-glm-4.7198K contextReasoningToolsWeb searchStructured output | Private | $0.55 / $2.65per 1M tokens | $0.382 / $1.84−30% | $0.267 / $1.29 |
| GLM 4.7 Flash Hereticolafangensan-glm-4.7-flash-heretic200K contextReasoningToolsWeb searchStructured output | Private | $0.07 / $0.40per 1M tokens | $0.049 / $0.278−30% | $0.034 / $0.194 |
| GLM 5zai-org-glm-5198K contextReasoningToolsCodeWeb search | Private | $1.00 / $3.20per 1M tokens | $0.695 / $2.22−30% | $0.486 / $1.56 |
| GLM 5.1zai-org-glm-5-1200K contextReasoningToolsWeb searchStructured output | Private | $1.54 / $4.84per 1M tokens | $1.07 / $3.36−30% | $0.749 / $2.35 |
| GLM 5.2e2ee-glm-5-2-p524.3K contextReasoningToolsCodeWeb search | E2EE | $1.75 / $5.75per 1M tokens | $1.22 / $3.99−30% | $0.851 / $2.80 |
| GLM 5.3z-ai-glm-5-31M contextReasoningToolsCodeWeb search | Private | $1.75 / $5.50per 1M tokens | $1.22 / $3.82−30% | $0.851 / $2.67 |
| GLM 5.3e2ee-glm-5-3-p1M contextReasoningToolsCodeWeb search | E2EE | $1.75 / $5.50per 1M tokens | $1.22 / $3.82−30% | $0.851 / $2.67 |
| GLM 5.3 Flashz-ai-glm-5-3-flash1M contextVisionReasoningToolsCode | Private | $0.15 / $0.50per 1M tokens | $0.104 / $0.347−30% | $0.073 / $0.243 |
| GLM 5.3 Flashe2ee-glm-5-3-flash1M contextVisionReasoningToolsCode | E2EE | $0.16 / $0.54per 1M tokens | $0.111 / $0.375−30% | $0.078 / $0.263 |
| Google Gemma 3 27B Instructgoogle-gemma-3-27b-it198K contextVisionToolsWeb searchStructured output | Private | $0.12 / $0.20per 1M tokens | $0.083 / $0.139−30% | $0.058 / $0.097 |
| Google Gemma 4 26B A4B Instructgoogle-gemma-4-26b-a4b-it256K contextVisionReasoningToolsWeb search | Private | $0.13 / $0.40per 1M tokens | $0.09 / $0.278−30% | $0.063 / $0.194 |
| Google Gemma 4 31B Instructgoogle-gemma-4-31b-it256K contextVisionReasoningToolsWeb search | Private | $0.12 / $0.36per 1M tokens | $0.083 / $0.25−30% | $0.058 / $0.175 |
| GPT OSS 120Be2ee-gpt-oss-120b-p128K contextReasoningWeb search | E2EE | $0.13 / $0.65per 1M tokens | $0.09 / $0.451−30% | $0.063 / $0.316 |
| Grok 4.20grok-4-202M contextVisionReasoningToolsWeb search | Private | $1.42 / $2.83per 1M tokens | $0.986 / $1.97−30% | $0.69 / $1.38 |
| Grok 4.20 Multi-Agentgrok-4-20-multi-agent2M contextVisionReasoningWeb searchStructured output | Private | $1.42 / $2.83per 1M tokens | $0.986 / $1.97−30% | $0.69 / $1.38 |
| Grok 4.3grok-4-31M contextVisionReasoningToolsWeb search | Private | $1.42 / $2.83per 1M tokens | $0.986 / $1.97−30% | $0.69 / $1.38 |
| Grok 4.5grok-4-5500K contextVisionReasoningToolsCode | Private | $2.27 / $6.80per 1M tokens | $1.58 / $4.72−30% | $1.10 / $3.31 |
| Grok 4.6grok-4-6500K contextVisionReasoningToolsCode | Private | $2.27 / $6.80per 1M tokens | $1.58 / $4.72−30% | $1.10 / $3.31 |
| Grok Build 0.1grok-build-0-1256K contextVisionReasoningToolsCode | Private | $1.00 / $2.00per 1M tokens | $0.695 / $1.39−30% | $0.486 / $0.972 |
| Hermes 3 Llama 3.1 405bhermes-3-llama-3.1-405b128K contextWeb search | Private | $1.10 / $3.00per 1M tokens | $0.764 / $2.08−30% | $0.535 / $1.46 |
| Hy4 Previewhy4-preview1M contextReasoningToolsCodeWeb search | Private | $1.04 / $3.13per 1M tokens | $0.724 / $2.17−30% | $0.507 / $1.52 |
| Kimi K2.5kimi-k2-5256K contextVisionReasoningToolsCode | Private | $0.56 / $3.50per 1M tokens | $0.389 / $2.43−30% | $0.272 / $1.70 |
| Kimi K2.6kimi-k2-6256K contextVisionReasoningToolsCode | Private | $0.75 / $3.50per 1M tokens | $0.521 / $2.43−30% | $0.365 / $1.70 |
| Kimi K2.6e2ee-kimi-k2-6262.1K contextVisionReasoningToolsCode | E2EE | $0.87 / $4.12per 1M tokens | $0.604 / $2.86−30% | $0.423 / $2.00 |
| Kimi K2.7 Codekimi-k2-7-code256K contextVisionReasoningToolsCode | Private | $0.75 / $3.50per 1M tokens | $0.521 / $2.43−30% | $0.365 / $1.70 |
| Kimi K3e2ee-kimi-k3-p1M contextVisionReasoningToolsCode | E2EE | $3.75 / $18.75per 1M tokens | $2.60 / $13.02−30% | $1.82 / $9.12 |
| Kimi K3 Fastkimi-k3-fast-api1M contextVisionReasoningToolsCode | Private | $4.50 / $22.50per 1M tokens | $3.13 / $15.63−30% | $2.19 / $10.94 |
| Llama 3.2 3Bllama-3.2-3b128K contextToolsWeb search | Private | $0.15 / $0.60per 1M tokens | $0.104 / $0.417−30% | $0.073 / $0.292 |
| Llama 3.3 70Bllama-3.3-70b128K contextToolsWeb search | Private | $0.70 / $2.80per 1M tokens | $0.486 / $1.94−30% | $0.34 / $1.36 |
| MiMo-V2.5xiaomi-mimo-v2-51M contextVisionReasoningToolsCode | Private | $0.40 / $2.00per 1M tokens | $0.278 / $1.39−30% | $0.194 / $0.972 |
| MiMo-V2.6-Flashxiaomi-mimo-v2-6-flash1M contextVisionReasoningToolsCode | Private | $0.175 / $0.35per 1M tokens | $0.122 / $0.243−30% | $0.085 / $0.17 |
| MiniMax M2.5minimax-m25198K contextReasoningToolsCodeWeb search | Private | $0.27 / $0.95per 1M tokens | $0.188 / $0.66−30% | $0.131 / $0.462 |
| MiniMax M2.7minimax-m27198K contextReasoningToolsCodeWeb search | Private | $0.375 / $1.50per 1M tokens | $0.26 / $1.04−30% | $0.182 / $0.729 |
| MiniMax M3 Previewminimax-m3-preview524.3K contextVisionReasoningToolsCode | Private | $0.30 / $1.20per 1M tokens | $0.208 / $0.833−30% | $0.146 / $0.583 |
| MiniMax M3.1 Flashminimax-m3-1-flash1M contextVisionReasoningToolsCode | Private | $0.188 / $0.75per 1M tokens | $0.13 / $0.521−30% | $0.091 / $0.365 |
| Mistral Small 3.2 24B Instructmistral-small-3-2-24b-instruct256K contextVisionToolsWeb searchStructured output | Private | $0.094 / $0.25per 1M tokens | $0.065 / $0.174−30% | $0.046 / $0.122 |
| Muse Spark Openmuse-spark-open1M contextVisionReasoningToolsCode | Private | $1.56 / $5.31per 1M tokens | $1.09 / $3.69−30% | $0.76 / $2.58 |
| NVIDIA Nemotron 3 Nano 30Bnvidia-nemotron-3-nano-30b-a3b128K contextToolsWeb searchStructured output | Private | $0.075 / $0.30per 1M tokens | $0.052 / $0.208−30% | $0.036 / $0.146 |
| NVIDIA Nemotron 3 Ultranvidia-nemotron-3-ultra-550b-a55b256K contextReasoningToolsWeb searchStructured output | Private | $0.625 / $3.13per 1M tokens | $0.434 / $2.17−30% | $0.304 / $1.52 |
| NVIDIA Nemotron 3.5 Super VL 120Bnvidia-nemotron-3-5-super-vl-120b-a12b262.1K contextVisionReasoningToolsCode | Private | $0.20 / $0.50per 1M tokens | $0.139 / $0.347−30% | $0.097 / $0.243 |
| OpenAI GPT OSS 120Bopenai-gpt-oss-120b128K contextReasoningToolsWeb search | Private | $0.07 / $0.30per 1M tokens | $0.049 / $0.208−30% | $0.034 / $0.146 |
| Qwen 2.5 7Be2ee-qwen-2-5-7b-p32K contextWeb search | E2EE | $0.05 / $0.13per 1M tokens | $0.035 / $0.09−30% | $0.024 / $0.063 |
| Qwen 3 235B A22B Instruct 2507qwen3-235b-a22b-instruct-2507128K contextToolsWeb searchStructured output | Private | $0.15 / $0.75per 1M tokens | $0.104 / $0.521−30% | $0.073 / $0.365 |
| Qwen 3 235B A22B Thinking 2507qwen3-235b-a22b-thinking-2507128K contextReasoningToolsWeb searchStructured output | Private | $0.45 / $3.50per 1M tokens | $0.313 / $2.43−30% | $0.219 / $1.70 |
| Qwen 3 Coder 480B Turboqwen3-coder-480b-a35b-instruct-turbo256K contextToolsCodeWeb searchStructured output | Private | $0.35 / $1.50per 1M tokens | $0.243 / $1.04−30% | $0.17 / $0.729 |
| Qwen 3 Next 80bqwen3-next-80b256K contextToolsWeb searchStructured output | Private | $0.35 / $1.90per 1M tokens | $0.243 / $1.32−30% | $0.17 / $0.924 |
| Qwen 3.5 35B A3Bqwen3-5-35b-a3b256K contextVisionReasoningToolsCode | Private | $0.15 / $1.00per 1M tokens | $0.104 / $0.695−30% | $0.073 / $0.486 |
| Qwen 3.6 27Bqwen3-6-27b256K contextVisionReasoningToolsCode | Private | $0.325 / $3.25per 1M tokens | $0.226 / $2.26−30% | $0.158 / $1.58 |
| Qwen 3.6 35B A3Bqwen3-6-35b-a3b256K contextVisionReasoningToolsCode | Private | $0.10 / $1.00per 1M tokens | $0.069 / $0.695−30% | $0.049 / $0.486 |
| Qwen 3.6 35B A3B FP8e2ee-qwen3-6-35b-a3b32K contextReasoningToolsCodeWeb search | E2EE | $0.182 / $1.18per 1M tokens | $0.126 / $0.82−30% | $0.088 / $0.574 |
| Qwen 3.8 2.4Tqwen-3-8-2-4t-a95b262.1K contextReasoningToolsCodeWeb search | Private | $2.50 / $7.50per 1M tokens | $1.74 / $5.21−30% | $1.22 / $3.65 |
| Qwen 3.8 27Bqwen-3-8-27b262.1K contextVisionReasoningToolsCode | Private | $0.45 / $3.20per 1M tokens | $0.313 / $2.22−30% | $0.219 / $1.56 |
| Qwen 3.8 27Be2ee-qwen3-8-27b262.1K contextVisionReasoningToolsCode | E2EE | $0.47 / $3.53per 1M tokens | $0.326 / $2.45−30% | $0.229 / $1.72 |
| Qwen3 VL 235Bqwen3-vl-235b-a22b128K contextVisionToolsWeb searchStructured output | Private | $0.21 / $1.90per 1M tokens | $0.146 / $1.32−30% | $0.102 / $0.924 |
| Qwen3 VL 30B A3Be2ee-qwen3-vl-30b-a3b-p128K contextVisionToolsWeb search | E2EE | $0.25 / $0.90per 1M tokens | $0.174 / $0.625−30% | $0.122 / $0.438 |
| Chatterbox HD (Resemble AI)tts-chatterbox-hd | Private | $50.00per 1M characters | $34.73−30% | $24.31 |
| Kokoro Text to Speechtts-kokoro | Private | $3.50per 1M characters | $2.43−30% | $1.70 |
| Orpheus TTStts-orpheus | Private | $62.50per 1M characters | $43.41−30% | $30.39 |
| Qwen 3 TTS 0.6Btts-qwen3-0-6b | Private | $87.50per 1M characters | $60.77−30% | $42.54 |
| Qwen 3 TTS 1.7Btts-qwen3-1-7b | Private | $112.50per 1M characters | $78.14−30% | $54.70 |
| Upscalerupscaler | Private | $0.01per image | $0.0069−30% | $0.0049 |
Low Tide
Low Tide rules
Low Tide sells only capacity that would otherwise go unused. It is opt-in, best-effort and fenced so it can’t undercut interactive traffic.
Opt in per request
Send X-Tokentide-Lane: lowtide, or set it as a key’s default lane.
Non-streaming only
Streaming requests get 400 lowtide_requires_non_streaming; text-to-speech must use streaming: false.
Lowest priority
Shed first under congestion, with no latency target. Rejected requests are never charged.
Per-account caps
An hourly cap and a daily allowance that grows with your Standard spend.
Automatic fallback
X-Tokentide-Lowtide-Fallback: standard reroutes to Standard when Low Tide is closed or capped.
When it’s closed
409 lowtide_closed with Retry-After and X-Tokentide-Lowtide-Opens-At when a forecast exists.
Payment rails and fees
What each way to pay costs you, and who sells it.
| Rail | Minimum top-up | Fees you pay | Tax and receipts |
|---|---|---|---|
| Card (Stripe Checkout) | $10 | None beyond tax | Local tax added at checkout; receipt and invoice by e-mail |
About tax
Card purchases are sold either by Stripe, as merchant of record, or by Tokentide; the checkout page and your invoice show which. Either way, the tax for your location is added at checkout. Automatic top-ups are sold by Tokentide, and businesses can add a VAT ID. Credits are usable only on Tokentide. This is not tax advice.