Transparent per-token pricing
AI Gateway pricing table
Documents and questions to your knowledge: 1 credit each. Chat with any model: final per-token price — the table below is what you pay, all-inclusive.
Pay as you goNo subscriptionConfigurable caps
Small top-up
$50
5,000 credits
- All models, pay per token
- Per-key spend caps
- Email support
Most popular
Medium top-up
$250
25,000 credits
- All models, pay per token
- Usage alerts
- Priority support
Large top-up
$1,000
100,000 credits
- All models, pay per token
- MCP + API + full audit trail
- Dedicated support
Fixed monthly plans
Fixed USD price, credits included every month, and the full platform. If you run out, top up at 1¢ per credit. Annual payment = 10 months.
Dependencia
$199 USD/mo
Includes 25,000 credits/mo (worth $250)
Save 20% vs. one-off top-ups
Hard spend caps · live dashboard · Spanish support · 2-day activation
Most popular
Municipio
$490 USD/mo
Includes 60,000 credits/mo (worth $600)
Save 18% vs. one-off top-ups
Hard spend caps · live dashboard · Spanish support · 2-day activation
Ciudad
$990 USD/mo
Includes 130,000 credits/mo (worth $1300)
Save 24% vs. one-off top-ups
Hard spend caps · live dashboard · Spanish support · 2-day activation
Chatbase: $32/mo for just 10 MB · CustomGPT: from $89/mo · Azure integrator: ~$3,000/mo → Deployalo: from $199/mo, all-inclusive
Fixed USD price; CFDI issued in MXN at the exchange rate on payment day.
Final price, no hidden fees
CFDI invoicing in Mexico
Per-million-token pricing
No annual commitment
Model catalog
467 models available · final price
Prices in credits per 1M tokens. 1 credit = $0.01 USD. Billed in MXN at the exchange rate on payment day + VAT (CFDI).
| Model | Capabilities | Context | ≈ messages / 100 credits | ||
|---|---|---|---|---|---|
| AionLabs: Aion 3.5 aion-labs/aion-3.5 Aion 3.5 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each... Max out 33k | Text / LLM Tools Reasoning | 262k tokens | 330 cache read 83 | 660 | ≈ 150 |
| AionLabs: Aion 3.5 Mini aion-labs/aion-3.5-mini Aion 3.5 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It is the smaller, lower-cost sibling of Aion 3.5 and uses... Max out 33k | Text / LLM Tools Reasoning | 262k tokens | 77 cache read 20 | 154 | ≈ 650 |
| AionLabs: Aion-2.0 aion-labs/aion-2.0 Aion-2.0 is a variant of DeepSeek V3.2 optimized for immersive roleplaying and storytelling. It is particularly strong at introducing tension, crises, and conflict into stories, making narratives feel more engaging.... Max out 33k | Text / LLM Tools Reasoning | 131k tokens | 88 cache read 22 | 176 | ≈ 570 |
| AionLabs: Aion-3.0 aion-labs/aion-3.0 Aion-3.0 is a multi-model roleplaying and storytelling system from AionLabs, built on the GLM family of models. It uses a collaborative generation process in which multiple specialized models each contribute... Max out 33k | Text / LLM Tools Reasoning | 131k tokens | 330 cache read 83 | 660 | ≈ 150 |
| AionLabs: Aion-3.0-Mini aion-labs/aion-3.0-mini Aion-3.0 Mini is a multi-model roleplaying and storytelling system from AionLabs, built on the DeepSeek family of models. It uses a collaborative generation process in which multiple specialized models each... Max out 33k | Text / LLM Tools Reasoning | 131k tokens | 77 cache read 20 | 154 | ≈ 650 |
| AionLabs: Aion-RP 1.0 (8B) aion-labs/aion-rp-llama-3.1-8b Aion-RP-Llama-3.1-8B ranks the highest in the character evaluation portion of the RPBench-Auto benchmark, a roleplaying-specific variant of Arena-Hard-Auto, where LLMs evaluate each other’s responses. It is a fine-tuned base model... Knowledge cutoff 2023-12-31 Max out 29k | Text / LLM | 33k tokens | 88 | 176 | ≈ 570 |
| Amazon: Nova 2 Lite amazon/nova-2-lite-v1 Nova 2 Lite is a fast, cost-effective reasoning model for everyday workloads that can process text, images, and videos to generate text. Nova 2 Lite demonstrates standout capabilities in processing... Max out 66k | Text / LLM Vision / OCR Video Tools Reasoning | 1000k tokens | 33 | 275 | ≈ 590 |
| Amazon: Nova Lite 1.0 amazon/nova-lite-v1 Amazon Nova Lite 1.0 is a very low-cost multimodal model from Amazon that focused on fast processing of image, video, and text inputs to generate text output. Amazon Nova Lite... Knowledge cutoff 2024-10-31 Max out 5k | Text / LLM Vision / OCR Tools | 300k tokens | 6.6 | 26 | ≈ 5,100 |
| Amazon: Nova Micro 1.0 amazon/nova-micro-v1 Amazon Nova Micro 1.0 is a text-only model that delivers the lowest latency responses in the Amazon Nova family of models at a very low cost. With a context length... Knowledge cutoff 2024-10-31 Max out 5k | Text / LLM Tools | 128k tokens | 3.9 | 15 | ≈ 8,700 |
| Amazon: Nova Premier 1.0 amazon/nova-premier-v1 Amazon Nova Premier is the most capable of Amazon’s multimodal models for complex reasoning tasks and for use as the best teacher for distilling custom models. Max out 32k | Text / LLM Vision / OCR Tools | 1000k tokens | 275 cache read 69 | 1,375 | ≈ 100 |
| Amazon: Nova Pro 1.0 amazon/nova-pro-v1 Amazon Nova Pro 1.0 is a capable multimodal model from Amazon focused on providing a combination of accuracy, speed, and cost for a wide range of tasks. As of December... Knowledge cutoff 2024-10-31 Max out 5k | Text / LLM Vision / OCR Tools | 300k tokens | 88 | 352 | ≈ 380 |
| Anthropic: Claude Fable 5 anthropic/claude-fable-5 Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 1,100 cache read 110cache write 1,375 | 5,500 web 1,100,000 | ≈ 26 |
| Anthropic: Claude Fable 5 (batch) anthropic/claude-fable-5:batch Claude Fable 5 is a Mythos-class model from Anthropic, built for autonomous knowledge work and coding. It supports text, image, and file inputs with text output, with reasoning support and... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 550 cache read 55cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Fable 5.1 anthropic/claude-fable-5.1 Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 1,100 cache read 28cache write 1,375 | 5,500 web 1,100,000 | ≈ 26 |
| Anthropic: Claude Fable 5.1 (batch) anthropic/claude-fable-5.1:batch Claude Fable 5.1 improves on Claude Fable 5 across the board, with the biggest gains in agentic coding, long-running agentic workflows, and knowledge work: long code refactors, front-end and visual... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 550 cache read 14cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Fable Latest ~anthropic/claude-fable-latest This model always redirects to the latest model in the Claude Fable family. Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 1,100 cache read 28cache write 1,375 | 5,500 web 1,100,000 | ≈ 26 |
| Anthropic: Claude Haiku 4.5 anthropic/claude-haiku-4.5 Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... Max out 64k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 200k tokens | 110 cache read 11cache write 138 | 550 web 1,100,000 | ≈ 260 |
| Anthropic: Claude Haiku 4.5 (batch) anthropic/claude-haiku-4.5:batch Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance... Max out 64k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 200k tokens | 55 cache read 5.5cache write 69 | 275 web 1,100,000 | ≈ 520 |
| Anthropic: Claude Haiku 5.5 anthropic/claude-haiku-5.5 Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 11 cache read 1.1cache write 14 | 55 web 1,100,000 | ≈ 2,600 |
| Anthropic: Claude Haiku 5.5 (batch) anthropic/claude-haiku-5.5:batch Claude Haiku 5.5 is Anthropic's small, fast model for high-volume, cost-sensitive work such as summarization, subagents, and browser use. It succeeds Claude Haiku 4.5 with stronger coding, computer use, and... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 5.5 cache read 0.6cache write 6.9 | 28 web 1,100,000 | ≈ 5,200 |
| Anthropic: Claude Haiku Latest ~anthropic/claude-haiku-latest This model always redirects to the latest model in the Claude Haiku family. Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 11 cache read 1.1cache write 14 | 55 web 1,100,000 | ≈ 2,600 |
| Anthropic: Claude Opus 4.1 anthropic/claude-opus-4.1 Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains... Knowledge cutoff 2025-01-31 Max out 32k | Text / LLM Vision / OCR Tools Reasoning | 200k tokens | 1,650 cache read 165cache write 2,063 | 8,250 web 1,100,000 | ≈ 17 |
| Anthropic: Claude Opus 4.1 (batch) anthropic/claude-opus-4.1:batch Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains... Knowledge cutoff 2025-01-31 Max out 32k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 200k tokens | 825 cache read 83cache write 1,031 | 4,125 web 1,100,000 | ≈ 35 |
| Anthropic: Claude Opus 4.5 anthropic/claude-opus-4.5 Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and... Max out 64k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 200k tokens | 550 cache read 55cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Opus 4.5 (batch) anthropic/claude-opus-4.5:batch Claude Opus 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and... Max out 64k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 200k tokens | 275 cache read 28cache write 344 | 1,375 web 1,100,000 | ≈ 100 |
| Anthropic: Claude Opus 4.6 anthropic/claude-opus-4.6 Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 550 cache read 55cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Opus 4.6 (batch) anthropic/claude-opus-4.6:batch Opus 4.6 is Anthropic’s strongest model for coding and long-running professional tasks. It is built for agents that operate across entire workflows rather than single prompts, making it especially effective... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 275 cache read 28cache write 344 | 1,375 web 1,100,000 | ≈ 100 |
| Anthropic: Claude Opus 4.7 anthropic/claude-opus-4.7 Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 550 cache read 55cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Opus 4.7 (batch) anthropic/claude-opus-4.7:batch Opus 4.7 is the next generation of Anthropic's Opus family, built for long-running, asynchronous agents. Building on the coding and agentic strengths of Opus 4.6, it delivers stronger performance on... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 275 cache read 28cache write 344 | 1,375 web 1,100,000 | ≈ 100 |
| Anthropic: Claude Opus 4.8 anthropic/claude-opus-4.8 Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 550 cache read 55cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Opus 4.8 (batch) anthropic/claude-opus-4.8:batch Claude Opus 4.8 is Anthropic's most capable generally available model in the Opus family. It supports text, image, and file inputs with text output, with reasoning support and a 1M-token... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 275 cache read 28cache write 344 | 1,375 web 1,100,000 | ≈ 100 |
| Anthropic: Claude Opus 5 anthropic/claude-opus-5 Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 550 cache read 55cache write 688 | 2,750 web 1,100,000 | ≈ 52 |
| Anthropic: Claude Opus 5 (batch) anthropic/claude-opus-5:batch Claude Opus 5 is Anthropic’s flagship model for demanding reasoning, coding, and long-horizon agentic work. It is particularly strong at end-to-end software tasks, code review and bug finding, visual analysis... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 275 cache read 28cache write 344 | 1,375 web 1,100,000 | ≈ 100 |
| Anthropic: Claude Opus 5.5 anthropic/claude-opus-5.5 Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 440 cache read 22cache write 550 | 2,200 web 1,100,000 | ≈ 65 |
| Anthropic: Claude Opus 5.5 (batch) anthropic/claude-opus-5.5:batch Claude Opus 5.5 is Anthropic's flagship model for demanding reasoning, coding, and long-horizon agentic work, succeeding Claude Opus 5. It is particularly strong at multi-step changes in large codebases, code... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 220 cache read 11cache write 275 | 1,100 web 1,100,000 | ≈ 130 |
| Anthropic: Claude Opus Latest ~anthropic/claude-opus-latest This model always redirects to the latest model in the Claude Opus family. Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 440 cache read 22cache write 550 | 2,200 web 1,100,000 | ≈ 65 |
| Anthropic: Claude Sonnet 4 anthropic/claude-sonnet-4 Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),... Knowledge cutoff 2025-01-31 Max out 64k | Text / LLM Vision / OCR Tools Reasoning | 200k tokens | 330 cache read 33cache write 413 | 1,650 web 1,100,000 | ≈ 87 |
| Anthropic: Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with... Knowledge cutoff 2025-01-31 Max out 64k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 330 cache read 33cache write 413 | 1,650 web 1,100,000 | ≈ 87 |
| Anthropic: Claude Sonnet 4.5 (batch) anthropic/claude-sonnet-4.5:batch Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with... Knowledge cutoff 2025-01-31 Max out 64k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 165 cache read 17cache write 206 | 825 web 1,100,000 | ≈ 170 |
| Anthropic: Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 330 cache read 33cache write 413 | 1,650 web 1,100,000 | ≈ 87 |
| Anthropic: Claude Sonnet 4.6 (batch) anthropic/claude-sonnet-4.6:batch Sonnet 4.6 is Anthropic's most capable Sonnet-class model yet, with frontier performance across coding, agents, and professional work. It excels at iterative development, complex codebase navigation, end-to-end project management with... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 165 cache read 17cache write 206 | 825 web 1,100,000 | ≈ 170 |
| Anthropic: Claude Sonnet 5 anthropic/claude-sonnet-5 Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 220 cache read 22cache write 275 | 1,100 web 1,100,000 | ≈ 130 |
| Anthropic: Claude Sonnet 5 (batch) anthropic/claude-sonnet-5:batch Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 110 cache read 11cache write 138 | 550 web 1,100,000 | ≈ 260 |
| Anthropic: Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 220 cache read 11cache write 275 | 1,100 web 1,100,000 | ≈ 130 |
| Anthropic: Claude Sonnet 5.5 (batch) anthropic/claude-sonnet-5.5:batch Claude Sonnet 5.5 is Anthropic's Sonnet-class model for well-scoped everyday work, succeeding Claude Sonnet 5 as a direct upgrade. It is especially strong at building features, fixing bugs, and producing... Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 110 cache read 5.5cache write 138 | 550 web 1,100,000 | ≈ 260 |
| Anthropic: Claude Sonnet Latest ~anthropic/claude-sonnet-latest This model always redirects to the latest model in the Claude Sonnet family. Max out 128k | Text / LLM Vision / OCR Tools JSON mode Reasoning | 1000k tokens | 220 cache read 11cache write 275 | 1,100 web 1,100,000 | ≈ 130 |
| Apodex: Apodex 1.1 Mini (free) apodex/apodex-1.1-mini:free Apodex 1.1 Mini is a reasoning-first model from Apodex, built for complex, long-horizon research and forecasting tasks. It works directly with files, data, code, and tools to produce verifiable results,... Max out 236k | Text / LLM Tools JSON mode Reasoning | 262k tokens | 0 | 0 | — |
| Arcee AI: Trinity Large Thinking arcee-ai/trinity-large-thinking Trinity Large Thinking is a powerful open source reasoning model from the team at Arcee AI. It shows strong performance in PinchBench, agentic workloads, and reasoning tasks. Launch video: https://youtu.be/Gc82AXLa0Rg?si=4RLn6WBz33qT--B7... Max out 80k | Text / LLM Tools Reasoning | 262k tokens | 28 cache read 6.6 | 88 | ≈ 1,400 |
| Auto Router openrouter/auto The Auto Router automatically selects the best model for your prompt, powered by the wisdom of the market. It routes you based on what the OpenRouter community collectively spends on... | Text / LLM Image Vision / OCR Audio Video Tools JSON mode Reasoning | 2000k tokens | 0 | 0 | — |
| Auto Router (Beta) openrouter/auto-beta The experimental version of our Auto Router where we test new improvements. Use it to get the latest and greatest version of our general purpose auto router, but expect beta... | Text / LLM Image Vision / OCR Audio Video Tools JSON mode Reasoning | 2000k tokens | 0 | 0 | — |
Showing 50 of 467 models (467 total). Credits per million tokens, subject to change without notice.
Page 1 of 10
Browse the full catalog with search and filters
Ready to start?
Create your first API key, set a spend cap and start consuming models in minutes.