# QuickSilver Pro - Full LLM-facing documentation

> OpenAI-compatible inference API. This file is generated from the canonical model catalog plus locale-independent product prose.

Site: https://quicksilverpro.io
API base: https://api.quicksilverpro.io/v1
Authentication: `Authorization: Bearer sk-...`
Catalog version: 70
Catalog updated: 2026-11-04
Public models: 91

## Answer index

- Model IDs, context and capabilities: [public model catalog](https://quicksilverpro.io/model-catalog.json) and the generated model table below.
- API costs: [public pricing feed](https://quicksilverpro.io/pricing.json) and [pricing](https://quicksilverpro.io/pricing/).
- Cloud dev box specs, runtime pricing, trial and limits: [QuickSilver Machines](https://quicksilverpro.io/machines/) and the QuickSilver Machines section below.
- Setup: [API quickstart](https://quicksilverpro.io/docs/quickstart/) and [Claude Code and Codex cloud dev box guide](https://quicksilverpro.io/blog/claude-code-cloud-dev-box/).

Both JSON feeds are public machine-readable feeds and need no API key. The live `https://api.quicksilverpro.io/v1/models` endpoint requires an API key (`Authorization: Bearer sk-...`).

## API surface

Use the OpenAI SDK with `base_url=https://api.quicksilverpro.io/v1`. Authentication uses a bearer API key. The supported API and capability columns below are generated for each model; do not assume every model supports every endpoint or modality.

System One models (APIs column: System One) are not chat models. They answer typed questions about a JSON state in one forward pass — a choice with per-option probabilities, a score, or a yes-leaning probability — on `POST https://api.quicksilverpro.io/v1/systemone`, with the same API key and balance. They bill input tokens only; output tokens are free. A Chat Completions call to a System One model is rejected. Request/response schema and examples: [/docs/systemone](https://quicksilverpro.io/docs/systemone/).

## Complete model table

Prices are USD per million tokens unless a row says per image. Context and maximum output are exact token counts from the catalog.

| Model ID | Name | Input | Output | Context | Max output | APIs | Capabilities | Lifecycle | Description |
|---|---|---:|---:|---:|---:|---|---|---|---|
| `deepseek-v4-flash` | DeepSeek V4 Flash | $0.06 | $0.18 | 1M | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | official 0731 agent model, 1M context, Responses API |
| `deepseek-v4.1-flash` | DeepSeek V4.1 Flash | $0.125 | $0.55 | 1M | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | official DeepSeek V4.1 Flash — new architecture, faster, 1M context, Responses API |
| `deepseek-v4.1-flash-1017` | DeepSeek V4.1 Flash 1017 | $0.098 | $0.294 | 1M | 131,072 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | October 17 snapshot, 1M context, tools and optional reasoning |
| `deepseek-v4-pro` | DeepSeek V4 Pro | $0.70 | $2.10 | 1M | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | premium reasoning, 1M context |
| `qwen3.8-max` | Qwen3.8 Max | $2.00 | $6.00 | 1M | 131,072 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Qwen 3.8 flagship, 2.4T MoE, 1M context, autonomous coding |
| `qwen3.8-max-prime` | Qwen3.8 Max Prime | $4.00 | $12.00 | 1M | 131,072 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Qwen 3.8 top-tier flagship, deepest reasoning & autonomous coding, 1M context |
| `qwen3.8-omni-flash` | Qwen3.8 Omni Flash | $0.15 | $0.47 | 1M | 131,072 | Chat Completions, Responses | text input, text output, image input, audio input, video input, streaming, reasoning, tool calling, JSON Schema | active | Qwen's first agentic omni model: native image, audio and video understanding with tool use and reasoning, 1M context, at Alibaba's first-party price |
| `qwen3.7-max` | Qwen3.7 Max | $1.25 | $3.75 | 1M | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | Qwen 3.7 flagship, 1M context, thinks by default |
| `qwen3.7-plus` | Qwen3.7 Plus | $0.256 | $1.024 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling, JSON Schema | active | Qwen 3.7 agent flagship, 1M context, long-horizon coding |
| `qwen3.7-flash` | Qwen3.7 Flash | $0.024 | $0.104 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling, JSON Schema | active | fast multimodal agents, vision and tool use, 1M context |
| `qwen3.6-plus` | Qwen3.6 Plus | $0.26 | $1.56 | 1M | - | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | 1T-MoE flagship, 1M context, thinks by default |
| `qwen3.6-35b` | Qwen3.6-35B-A3B | $0.05 | $0.70 | 262K | - | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | 262K long-context, MoE, drop-in 3.5 upgrade |
| `qwen3.8-27b` | Qwen3.8 27B | $0.34 | $2.04 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling | active | Cloud-only Qwen 27B with a 1M-token context window |
| `qwen3.8-27b-decentered` | Qwen3.8 27B Decentered | $0.238 | $1.428 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling | active | Share Compute community Macs: 30% lower token prices; cloud fallback billed at Qwen3.8 27B prices |
| `qwen3.8-flash-next` | Qwen3.8 Flash Next | $0.12 | $0.376 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling | active | Qwen's open Qwen4-architecture preview: 6B-active MoE, fast and cheap, with a 1M-token context window |
| `kimi-k2.6` | Kimi K2.6 | $0.45 | $1.95 | 256K | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Opus-class reasoning, 256K context |
| `kimi-k2.7-code` | Kimi K2.7 Code | $0.6712 | $3.35 | 256K | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | Agentic-coding K2, 256K context, coding-tuned K2.6 successor |
| `kimi-k3.1-pro` | Kimi K3.1 Pro | $2.00 | $10.00 | 1M | 943,718 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | 1M context, image input, tools and optional reasoning |
| `kimi-k3.1-pro-highspeed` | Kimi K3.1 Pro Highspeed | $4.00 | $20.00 | 1M | 943,718 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | 1M context, image input, tools and optional reasoning |
| `kimi-k3` | Kimi K3 | $2.55 | $12.75 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | 2.8T multimodal reasoning flagship, 1M context |
| `muse-wonder` | Muse Wonder | $4.00 | $20.00 | 1M | 943,718 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Frontier reasoning for agentic personal and professional work, 1M context |
| `muse-spark-open` | Muse Spark Open | $1.25 | $4.25 | 1M | 262,144 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Meta open-weight model for coding and tools, 1M context |
| `muse-spark-1.3` | Muse Spark 1.3 | $1.00 | $3.40 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Coding & agentic reasoning model, 1M context |
| `muse-spark-1.2` | Muse Spark 1.2 | $1.00 | $3.40 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Coding-focused reasoning model, 1M context |
| `muse-glimmer-30b` | Muse Glimmer 30B | $0.30 | $1.20 | 131K | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Compact agentic multimodal model, distilled from Muse Spark |
| `glm-5.3` | GLM 5.3 | $0.60 | $2.20 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling | active | Z.ai latest reasoning flagship, 1M context, complex software engineering & long-horizon agents |
| `glm-5.3-prime` | GLM 5.3 Prime | $2.24 | $7.04 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling | active | Z.ai GLM 5.3 Prime, top reasoning flagship, 1M context, complex software engineering |
| `glm-5.3-flash` | GLM 5.3 Flash | $0.07 | $0.05 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling | active | Z.ai fast open-weights reasoning model, 1M context at workhorse pricing |
| `glm-5.2` | GLM 5.2 | $0.70 | $2.20 | 1M | - | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | Z.ai reasoning flagship, 1M context, long-horizon agents & coding |
| `nemotron-3-ultra` | Nemotron 3 Ultra | $0.50 | $2.20 | 262K | 16,384 | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | 550B-A55B open MoE for frontier reasoning and agent orchestration |
| `nemotron-3.5-lightning` | Nemotron 3.5 Lightning | $0.066 | $0.176 | 262K | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | 30B-A3B open MoE for fast, tool-heavy agents |
| `gpt-oss-120b` | GPT-OSS 120B | $0.03 | $0.15 | 131K | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling | active | OpenAI's open-weight 117B MoE, high-volume agents & reasoning, 131K context |
| `gpt-6-astra` | GPT-6 Astra | $10.00 ($20.00 >200,000) | $50.00 ($75.00 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | OpenAI's GPT-6 flagship, long-horizon agentic coding & deep research, 1M context |
| `gpt-6-luna` | GPT-6 Luna | $0.10 ($0.20 >200,000) | $0.50 ($0.75 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | OpenAI's cost-efficient GPT-6, high-volume chat & lightweight agentic work, 1M context |
| `gpt-6.1-sol` | GPT-6.1 Sol | $2.00 ($4.00 >200,000) | $10.00 ($15.00 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | OpenAI's GPT-6.1 Sol, near-Astra agentic coding at Sol pricing, 1M context |
| `gpt-6.1-terra` | GPT-6.1 Terra | $1.00 ($2.00 >200,000) | $5.00 ($7.50 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | OpenAI's GPT-6.1 Terra, mid-tier everyday agentic coding, writing, and screenshot understanding, 1M context |
| `gpt-6.1-terra-pro` | GPT-6.1 Terra Pro | $1.00 ($2.00 >200,000) | $5.00 ($7.50 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | GPT-6.1 Terra in pro reasoning mode -- same model, same per-token price, far more reasoning tokens per request on complex tasks |
| `gpt-6-sol` | GPT-6 Sol | $2.00 ($4.00 >200,000) | $10.00 ($15.00 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | OpenAI's GPT-6 mid-flagship, strong reasoning & agentic coding, 1M context |
| `gpt-5.6-luna` | GPT-5.6 Luna | $0.16 | $0.96 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | OpenAI's fast, cost-efficient GPT-5.6 tier, 1M context |
| `gpt-5.6-terra` | GPT-5.6 Terra | $1.60 | $9.60 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | OpenAI's balanced GPT-5.6 mid-tier, 1M context |
| `gpt-5.6-sol` | GPT-5.6 Sol | $1.60 | $8.00 | 1M | 131,072 | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | OpenAI's flagship GPT-5.6, complex reasoning & agentic coding, 1M context |
| `grok-4.5` | Grok 4.5 | $1.60 | $4.80 | 500K | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | xAI's smartest model, frontier coding, knowledge work & STEM, 500K context |
| `grok-4.6` | Grok 4.6 | $2.00 ($4.00 >200,000) | $6.00 ($12.00 >200,000) | 500K | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | frontier coding, knowledge work and STEM, vision, 500K context |
| `grok-4.7` | Grok 4.7 | $2.00 ($4.00 >200,000) | $6.00 ($12.00 >200,000) | 500K | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | frontier coding, knowledge work and STEM, vision, 500K context |
| `minimax-m3` | MiniMax M3 | $0.24 | $0.96 | 1M | - | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | MiniMax open-weight frontier model, 1M context, agentic coding |
| `mimo-v2.6-pro` | MiMo-V2.6-Pro | $0.426 | $0.861 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling, JSON Schema | active | Xiaomi flagship open-weight MiMo-V2.6-Pro, top open model on AA Intelligence Index, coding & agentic, vision, 1M context |
| `mimo-v2.6-flash` | MiMo-V2.6-Flash | $0.112 | $0.224 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling, JSON Schema | active | Xiaomi open-weight MiMo-V2.6-Flash, fast low-cost coding & agentic, vision, 1M context |
| `mimo-v2.5` | MiMo-V2.5 | $0.112 | $0.224 | 1M | - | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | Xiaomi open-weight MiMo-V2.5, cost-efficient coding & agentic, 1M context |
| `hy4-preview` | Hy4 Preview | $0.6672 | $2.0008 | 1M | - | Chat Completions, Responses | text input, text output, streaming, reasoning, tool calling, JSON Schema | active | Tencent Hy4 (preview), reasoning & agentic coding, 1M context |
| `hy3` | Hy3 | $0.091 | $0.363 | 262K | - | Chat Completions, Responses | text input, text output, streaming, tool calling, JSON Schema | active | Tencent Hy3, selectable reasoning & agentic coding, 262K context |
| `step-5-preview` | Step 5 Preview | $1.00 | $2.70 | 1M | 65,536 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | StepFun reasoning model for tools and image understanding, 1M context |
| `mistral-large-4` | Mistral Large 4 | $0.68 | $2.09 | 524K | 131,072 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Mistral's frontier multimodal model for coding and agents, 524K context |
| `jev-1.13` | Jev 1.13 | $0.042 | $0 (free) | 32K | 8,192 | System One | text input, text output | active | Typed decisions with calibrated probabilities from a single forward pass: routing, classification and scoring without text generation |
| `trio-spark-v1.3` | Trio-Spark v1.3 | $0.042 | $0 (free) | 1K | - | System One | text input, text output | active | System-1 decision model: one forward pass, calibrated probabilities, no generated tokens |
| `claude-opus-5-5` | Claude Opus 5.5 | $1.00 | $5.00 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic's most capable Claude: agentic coding, knowledge work & computer use, 1M context |
| `claude-opus-5` | Claude Opus 5 | $1.25 | $6.25 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic Opus 5 for demanding reasoning, coding & long-horizon agentic work, 1M context |
| `claude-fable-5-1` | Claude Fable 5.1 | $2.50 | $12.50 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic Mythos-class model for deep reasoning and long-horizon agentic work (5.1) |
| `claude-fable-5` | Claude Fable 5 | $2.50 | $12.50 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic Mythos-class flagship, most capable reasoning |
| `claude-opus-4-8` | Claude Opus 4.8 | $1.25 | $6.25 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic flagship, top-tier reasoning & agentic |
| `claude-sonnet-5-5` | Claude Sonnet 5.5 | $0.50 | $2.50 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic's newest Sonnet, faster and fewer tokens per task, 1M context |
| `claude-sonnet-5` | Claude Sonnet 5 | $0.50 | $2.50 | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling | active | Anthropic's newest Sonnet tier, 1M context |
| `claude-haiku-5-5` | Claude Haiku 5.5 | $0.025 ($0.125 >200,000) | $0.125 ($0.625 >200,000) | 1M | 128,000 | Chat Completions, Responses | text input, text output, image input, streaming, tool calling | active | Anthropic's newest small, fast model for subagents and high-volume work, 1M context |
| `claude-haiku-4-5` | Claude Haiku 4.5 | $0.25 | $1.25 | 200K | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling | active | fast, low-cost Anthropic, high-volume |
| `gemini-4-argon` | Gemini 4 Argon | $2.00 | $10.00 | 1M | 65,536 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Google's new flagship reasoning model, 1M context; introductory price |
| `gemini-3.7-flash` | Gemini 3.7 Flash | $0.6375 | $3.1875 | 1M | 65,536 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | fast multimodal Flash for agents; promotional pricing through 2026-12-31 |
| `gemini-3.8-flash` | Gemini 3.8 Flash | $0.6375 | $3.1875 | 1M | 65,536 | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | most capable Flash for agents; promotional pricing through 2026-12-31 |
| `gemini-3.6-flash` | Gemini 3.6 Flash | $0.6375 | $3.1875 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | current general-purpose Flash GA, 1M context |
| `gemini-3.5-flash-lite` | Gemini 3.5 Flash-Lite | $0.255 | $2.125 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling, JSON Schema | active | current low-cost Flash-Lite GA, 1M context |
| `gemini-3.5-flash` | Gemini 3.5 Flash | $1.275 | $7.65 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Google's next-gen Flash GA, 1M context, thinking |
| `gemini-3.1-pro-preview` | Gemini 3.1 Pro Preview | $1.70 | $10.20 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | active | Google's flagship reasoning, 1M context, thinking |
| `gemini-3-pro-image` | Nano Banana Pro (Gemini 3 Pro Image) | - | $0.114/image | - | - | Images Generations | text input, image output | active | Google's Nano Banana Pro at 1K, billed per image |
| `gemini-nano-banana-2.1` | Nano Banana 2.1 | - | $0.036/image | - | - | Images Generations | text input, image output | active | Google's newest Nano Banana at 1K, billed per image |
| `gemini-3-flash-preview` | Gemini 3 Flash Preview | $0.425 | $2.55 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, reasoning, tool calling, JSON Schema | deprecated | legacy compatibility; migrate to Gemini 3.6 Flash |
| `gemini-3.1-flash-lite` | Gemini 3.1 Flash Lite | $0.2125 | $1.275 | 1M | - | Chat Completions, Responses | text input, text output, image input, streaming, tool calling, JSON Schema | deprecated | legacy compatibility; migrate to Gemini 3.5 Flash-Lite |
| `flux.2-pro` | FLUX.2 Pro | - | $0.027/image | - | - | Images Generations | text input, image output | active | flagship image generation, billed per image |
| `flux.1-schnell` | FLUX.1 Schnell | - | $0.003/image | - | - | Images Generations | text input, image output | active | ultra-fast open image generation, billed per image |
| `sdxl-turbo` | SDXL Turbo | - | $0.003/image | - | - | Images Generations | text input, image output | active | fast open image generation (SDXL Turbo), billed per image |
| `flux.2-klein` | FLUX.2 Klein | - | $0.02/image | - | - | Images Generations | text input, image output | active | open FLUX.2 image generation, billed per image |
| `qwen-image-3.0` | Qwen Image 3.0 | - | $0.04/image | - | - | Images Generations | text input, image output | active | Alibaba text-to-image, 512x512 to 2560x2560, flat $0.04 per image; optional prompt_extend |
| `seedream-5.0-pro` | Seedream 5.0 Pro | - | $0.07/image | - | - | Images Generations | text input, image output | active | ByteDance's Seedream 5.0 Pro: flagship photorealistic image generation, billed per image |
| `seedream-4` | Seedream 4 | - | $0.055/image | - | - | Images Generations | text input, image output | active | ByteDance Seedream 4: fast, high-quality image generation, billed per image |
| `bria-fibo-1.5` | Bria FIBO 1.5 | - | $0.055/image | - | - | Images Generations | text input, image output | active | Bria FIBO 1.5: image generation trained on fully licensed data (commercially safe), billed per image |
| `bria-fibo-2.0` | Bria FIBO 2.0 | - | $0.055/image | - | - | Images Generations | text input, image output | active | Bria FIBO 2.0: Bria reports training on fully licensed data for commercially safe image generation, billed per image |
| `gpt-image-2` | GPT Image 2 | - | $0.01/image | - | - | Images Generations | text input, image output | active | OpenAI's GPT Image 2 at a fixed ~1.5MP standard output, billed per image |
| `gpt-image-2.5-flare` | GPT Image 2.5 Flare | - | $0.018/image | - | - | Images Generations | text input, image output | active | OpenAI's GPT Image 2.5, speed tier, at medium quality, billed per image |
| `gpt-image-2.5-sunburst` | GPT Image 2.5 Sunburst | - | $0.018/image | - | - | Images Generations | text input, image output | active | OpenAI's GPT Image 2.5, precision tier, at medium quality, billed per image |
| `qwen3-asr` | Qwen3 ASR | $0.0006/minute | - | - | - | Audio Transcriptions | audio input, text output | active | Speech to text |
| `nemotron-3.5-asr` | Nemotron 3.5 ASR | $0.0003/minute | - | - | - | Audio Transcriptions | audio input, text output | active | Speech to text |
| `whisper-large-v3-turbo` | Whisper Large v3 Turbo | $0.0003/minute | - | - | - | Audio Transcriptions | audio input, text output | active | Speech to text |
| `chatterbox-turbo` | Chatterbox Turbo | $1.50/1M characters | - | - | - | Audio Speech | text input, audio output, streaming | active | English text to speech |
| `qwen3-tts` | Qwen3 TTS | $25.00/1M characters | - | - | - | Audio Speech | text input, audio output, streaming | active | Chinese and English text to speech |

## Per-model records

### DeepSeek V4 Flash (`deepseek-v4-flash`)

official 0731 agent model, 1M context, Responses API

- Lifecycle: active
- Provider family: deepseek
- Input price: $0.06
- Output price: $0.18
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-07-31

### DeepSeek V4.1 Flash (`deepseek-v4.1-flash`)

official DeepSeek V4.1 Flash — new architecture, faster, 1M context, Responses API

- Lifecycle: active
- Provider family: deepseek
- Input price: $0.125
- Output price: $0.55
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-08

### DeepSeek V4.1 Flash 1017 (`deepseek-v4.1-flash-1017`)

October 17 snapshot, 1M context, tools and optional reasoning

- Lifecycle: active
- Provider family: deepseek
- Input price: $0.098
- Output price: $0.294
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-17

### DeepSeek V4 Pro (`deepseek-v4-pro`)

premium reasoning, 1M context

- Lifecycle: active
- Provider family: deepseek
- Input price: $0.70
- Output price: $2.10
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Qwen3.8 Max (`qwen3.8-max`)

Qwen 3.8 flagship, 2.4T MoE, 1M context, autonomous coding

- Lifecycle: active
- Provider family: qwen
- Input price: $2.00
- Output price: $6.00
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-08-03

### Qwen3.8 Max Prime (`qwen3.8-max-prime`)

Qwen 3.8 top-tier flagship, deepest reasoning & autonomous coding, 1M context

- Lifecycle: active
- Provider family: qwen
- Input price: $4.00
- Output price: $12.00
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-25

### Qwen3.8 Omni Flash (`qwen3.8-omni-flash`)

Qwen's first agentic omni model: native image, audio and video understanding with tool use and reasoning, 1M context, at Alibaba's first-party price

- Lifecycle: active
- Provider family: qwen
- Input price: $0.15
- Output price: $0.47
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, audio input, video input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-18

### Qwen3.7 Max (`qwen3.7-max`)

Qwen 3.7 flagship, 1M context, thinks by default

- Lifecycle: active
- Provider family: qwen
- Input price: $1.25
- Output price: $3.75
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Qwen3.7 Plus (`qwen3.7-plus`)

Qwen 3.7 agent flagship, 1M context, long-horizon coding

- Lifecycle: active
- Provider family: qwen
- Input price: $0.256
- Output price: $1.024
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling, JSON Schema
- Released: not specified

### Qwen3.7 Flash (`qwen3.7-flash`)

fast multimodal agents, vision and tool use, 1M context

- Lifecycle: active
- Provider family: qwen
- Input price: $0.024
- Output price: $0.104
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling, JSON Schema
- Released: not specified

### Qwen3.6 Plus (`qwen3.6-plus`)

1T-MoE flagship, 1M context, thinks by default

- Lifecycle: active
- Provider family: qwen
- Input price: $0.26
- Output price: $1.56
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### Qwen3.6-35B-A3B (`qwen3.6-35b`)

262K long-context, MoE, drop-in 3.5 upgrade

- Lifecycle: active
- Provider family: qwen
- Input price: $0.05
- Output price: $0.70
- Context tokens: 262K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### Qwen3.8 27B (`qwen3.8-27b`)

Cloud-only Qwen 27B with a 1M-token context window

- Lifecycle: active
- Provider family: qwen
- Input price: $0.34
- Output price: $2.04
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling
- Released: 2026-08-14

### Qwen3.8 27B Decentered (`qwen3.8-27b-decentered`)

Share Compute community Macs: 30% lower token prices; cloud fallback billed at Qwen3.8 27B prices

- Lifecycle: active
- Provider family: qwen
- Input price: $0.238
- Output price: $1.428
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling
- Released: 2026-10-15

### Qwen3.8 Flash Next (`qwen3.8-flash-next`)

Qwen's open Qwen4-architecture preview: 6B-active MoE, fast and cheap, with a 1M-token context window

- Lifecycle: active
- Provider family: qwen
- Input price: $0.12
- Output price: $0.376
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling
- Released: 2026-08-26

### Kimi K2.6 (`kimi-k2.6`)

Opus-class reasoning, 256K context

- Lifecycle: active
- Provider family: moonshot
- Input price: $0.45
- Output price: $1.95
- Context tokens: 256K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Kimi K2.7 Code (`kimi-k2.7-code`)

Agentic-coding K2, 256K context, coding-tuned K2.6 successor

- Lifecycle: active
- Provider family: moonshot
- Input price: $0.6712
- Output price: $3.35
- Context tokens: 256K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Kimi K3.1 Pro (`kimi-k3.1-pro`)

1M context, image input, tools and optional reasoning

- Lifecycle: active
- Provider family: moonshot
- Input price: $2.00
- Output price: $10.00
- Context tokens: 1M
- Maximum output tokens: 943,718
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-23

### Kimi K3.1 Pro Highspeed (`kimi-k3.1-pro-highspeed`)

1M context, image input, tools and optional reasoning

- Lifecycle: active
- Provider family: moonshot
- Input price: $4.00
- Output price: $20.00
- Context tokens: 1M
- Maximum output tokens: 943,718
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-23

### Kimi K3 (`kimi-k3`)

2.8T multimodal reasoning flagship, 1M context

- Lifecycle: active
- Provider family: moonshot
- Input price: $2.55
- Output price: $12.75
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Muse Wonder (`muse-wonder`)

Frontier reasoning for agentic personal and professional work, 1M context

- Lifecycle: active
- Provider family: meta
- Input price: $4.00
- Output price: $20.00
- Context tokens: 1M
- Maximum output tokens: 943,718
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-12

### Muse Spark Open (`muse-spark-open`)

Meta open-weight model for coding and tools, 1M context

- Lifecycle: active
- Provider family: meta
- Input price: $1.25
- Output price: $4.25
- Context tokens: 1M
- Maximum output tokens: 262,144
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-15

### Muse Spark 1.3 (`muse-spark-1.3`)

Coding & agentic reasoning model, 1M context

- Lifecycle: active
- Provider family: meta
- Input price: $1.00
- Output price: $3.40
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-02

### Muse Spark 1.2 (`muse-spark-1.2`)

Coding-focused reasoning model, 1M context

- Lifecycle: active
- Provider family: meta
- Input price: $1.00
- Output price: $3.40
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-08-05

### Muse Glimmer 30B (`muse-glimmer-30b`)

Compact agentic multimodal model, distilled from Muse Spark

- Lifecycle: active
- Provider family: meta
- Input price: $0.30
- Output price: $1.20
- Context tokens: 131K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-08-10

### GLM 5.3 (`glm-5.3`)

Z.ai latest reasoning flagship, 1M context, complex software engineering & long-horizon agents

- Lifecycle: active
- Provider family: z-ai
- Input price: $0.60
- Output price: $2.20
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling
- Released: 2026-08-18

### GLM 5.3 Prime (`glm-5.3-prime`)

Z.ai GLM 5.3 Prime, top reasoning flagship, 1M context, complex software engineering

- Lifecycle: active
- Provider family: z-ai
- Input price: $2.24
- Output price: $7.04
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling
- Released: 2026-09-25

### GLM 5.3 Flash (`glm-5.3-flash`)

Z.ai fast open-weights reasoning model, 1M context at workhorse pricing

- Lifecycle: active
- Provider family: z-ai
- Input price: $0.07
- Output price: $0.05
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling
- Released: 2026-08-26

### GLM 5.2 (`glm-5.2`)

Z.ai reasoning flagship, 1M context, long-horizon agents & coding

- Lifecycle: active
- Provider family: z-ai
- Input price: $0.70
- Output price: $2.20
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### Nemotron 3 Ultra (`nemotron-3-ultra`)

550B-A55B open MoE for frontier reasoning and agent orchestration

- Lifecycle: active
- Provider family: nvidia
- Input price: $0.50
- Output price: $2.20
- Context tokens: 262K
- Maximum output tokens: 16,384
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: 2026-06-04

### Nemotron 3.5 Lightning (`nemotron-3.5-lightning`)

30B-A3B open MoE for fast, tool-heavy agents

- Lifecycle: active
- Provider family: nvidia
- Input price: $0.066
- Output price: $0.176
- Context tokens: 262K
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: 2026-08-11

### GPT-OSS 120B (`gpt-oss-120b`)

OpenAI's open-weight 117B MoE, high-volume agents & reasoning, 131K context

- Lifecycle: active
- Provider family: openai
- Input price: $0.03
- Output price: $0.15
- Context tokens: 131K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling
- Released: 2025-08-05

### GPT-6 Astra (`gpt-6-astra`)

OpenAI's GPT-6 flagship, long-horizon agentic coding & deep research, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $10.00 ($20.00 >200,000)
- Output price: $50.00 ($75.00 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-03

### GPT-6 Luna (`gpt-6-luna`)

OpenAI's cost-efficient GPT-6, high-volume chat & lightweight agentic work, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $0.10 ($0.20 >200,000)
- Output price: $0.50 ($0.75 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-25

### GPT-6.1 Sol (`gpt-6.1-sol`)

OpenAI's GPT-6.1 Sol, near-Astra agentic coding at Sol pricing, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $2.00 ($4.00 >200,000)
- Output price: $10.00 ($15.00 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-29

### GPT-6.1 Terra (`gpt-6.1-terra`)

OpenAI's GPT-6.1 Terra, mid-tier everyday agentic coding, writing, and screenshot understanding, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $1.00 ($2.00 >200,000)
- Output price: $5.00 ($7.50 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-26

### GPT-6.1 Terra Pro (`gpt-6.1-terra-pro`)

GPT-6.1 Terra in pro reasoning mode -- same model, same per-token price, far more reasoning tokens per request on complex tasks

- Lifecycle: active
- Provider family: openai
- Input price: $1.00 ($2.00 >200,000)
- Output price: $5.00 ($7.50 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-26

### GPT-6 Sol (`gpt-6-sol`)

OpenAI's GPT-6 mid-flagship, strong reasoning & agentic coding, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $2.00 ($4.00 >200,000)
- Output price: $10.00 ($15.00 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-25

### GPT-5.6 Luna (`gpt-5.6-luna`)

OpenAI's fast, cost-efficient GPT-5.6 tier, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $0.16
- Output price: $0.96
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### GPT-5.6 Terra (`gpt-5.6-terra`)

OpenAI's balanced GPT-5.6 mid-tier, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $1.60
- Output price: $9.60
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### GPT-5.6 Sol (`gpt-5.6-sol`)

OpenAI's flagship GPT-5.6, complex reasoning & agentic coding, 1M context

- Lifecycle: active
- Provider family: openai
- Input price: $1.60
- Output price: $8.00
- Context tokens: 1M
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### Grok 4.5 (`grok-4.5`)

xAI's smartest model, frontier coding, knowledge work & STEM, 500K context

- Lifecycle: active
- Provider family: xai
- Input price: $1.60
- Output price: $4.80
- Context tokens: 500K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Grok 4.6 (`grok-4.6`)

frontier coding, knowledge work and STEM, vision, 500K context

- Lifecycle: active
- Provider family: xai
- Input price: $2.00 ($4.00 >200,000)
- Output price: $6.00 ($12.00 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 500K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-08-12

### Grok 4.7 (`grok-4.7`)

frontier coding, knowledge work and STEM, vision, 500K context

- Lifecycle: active
- Provider family: xai
- Input price: $2.00 ($4.00 >200,000)
- Output price: $6.00 ($12.00 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 500K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-21

### MiniMax M3 (`minimax-m3`)

MiniMax open-weight frontier model, 1M context, agentic coding

- Lifecycle: active
- Provider family: minimax
- Input price: $0.24
- Output price: $0.96
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### MiMo-V2.6-Pro (`mimo-v2.6-pro`)

Xiaomi flagship open-weight MiMo-V2.6-Pro, top open model on AA Intelligence Index, coding & agentic, vision, 1M context

- Lifecycle: active
- Provider family: xiaomi
- Input price: $0.426
- Output price: $0.861
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling, JSON Schema
- Released: 2026-09-21

### MiMo-V2.6-Flash (`mimo-v2.6-flash`)

Xiaomi open-weight MiMo-V2.6-Flash, fast low-cost coding & agentic, vision, 1M context

- Lifecycle: active
- Provider family: xiaomi
- Input price: $0.112
- Output price: $0.224
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling, JSON Schema
- Released: 2026-09-21

### MiMo-V2.5 (`mimo-v2.5`)

Xiaomi open-weight MiMo-V2.5, cost-efficient coding & agentic, 1M context

- Lifecycle: active
- Provider family: xiaomi
- Input price: $0.112
- Output price: $0.224
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### Hy4 Preview (`hy4-preview`)

Tencent Hy4 (preview), reasoning & agentic coding, 1M context

- Lifecycle: active
- Provider family: tencent
- Input price: $0.6672
- Output price: $2.0008
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-08-28

### Hy3 (`hy3`)

Tencent Hy3, selectable reasoning & agentic coding, 262K context

- Lifecycle: active
- Provider family: tencent
- Input price: $0.091
- Output price: $0.363
- Context tokens: 262K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, streaming, tool calling, JSON Schema
- Released: not specified

### Step 5 Preview (`step-5-preview`)

StepFun reasoning model for tools and image understanding, 1M context

- Lifecycle: active
- Provider family: stepfun
- Input price: $1.00
- Output price: $2.70
- Context tokens: 1M
- Maximum output tokens: 65,536
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-08

### Mistral Large 4 (`mistral-large-4`)

Mistral's frontier multimodal model for coding and agents, 524K context

- Lifecycle: active
- Provider family: mistral
- Input price: $0.68
- Output price: $2.09
- Context tokens: 524K
- Maximum output tokens: 131,072
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-06

### Jev 1.13 (`jev-1.13`)

Typed decisions with calibrated probabilities from a single forward pass: routing, classification and scoring without text generation

- Lifecycle: active
- Provider family: typesafe
- Input price: $0.042
- Output price: $0 (free)
- Context tokens: 32K
- Maximum output tokens: 8,192
- APIs: System One
- Capabilities: text input, text output
- Released: 2026-09-17

### Trio-Spark v1.3 (`trio-spark-v1.3`)

System-1 decision model: one forward pass, calibrated probabilities, no generated tokens

- Lifecycle: active
- Provider family: machinefi
- Input price: $0.042
- Output price: $0 (free)
- Context tokens: 1K
- Maximum output tokens: -
- APIs: System One
- Capabilities: text input, text output
- Released: 2026-10-15

### Claude Opus 5.5 (`claude-opus-5-5`)

Anthropic's most capable Claude: agentic coding, knowledge work & computer use, 1M context

- Lifecycle: active
- Provider family: anthropic
- Input price: $1.00
- Output price: $5.00
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: 2026-09-22

### Claude Opus 5 (`claude-opus-5`)

Anthropic Opus 5 for demanding reasoning, coding & long-horizon agentic work, 1M context

- Lifecycle: active
- Provider family: anthropic
- Input price: $1.25
- Output price: $6.25
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: not specified

### Claude Fable 5.1 (`claude-fable-5-1`)

Anthropic Mythos-class model for deep reasoning and long-horizon agentic work (5.1)

- Lifecycle: active
- Provider family: anthropic
- Input price: $2.50
- Output price: $12.50
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: 2026-09-01

### Claude Fable 5 (`claude-fable-5`)

Anthropic Mythos-class flagship, most capable reasoning

- Lifecycle: active
- Provider family: anthropic
- Input price: $2.50
- Output price: $12.50
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: not specified

### Claude Opus 4.8 (`claude-opus-4-8`)

Anthropic flagship, top-tier reasoning & agentic

- Lifecycle: active
- Provider family: anthropic
- Input price: $1.25
- Output price: $6.25
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: not specified

### Claude Sonnet 5.5 (`claude-sonnet-5-5`)

Anthropic's newest Sonnet, faster and fewer tokens per task, 1M context

- Lifecycle: active
- Provider family: anthropic
- Input price: $0.50
- Output price: $2.50
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: 2026-09-28

### Claude Sonnet 5 (`claude-sonnet-5`)

Anthropic's newest Sonnet tier, 1M context

- Lifecycle: active
- Provider family: anthropic
- Input price: $0.50
- Output price: $2.50
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling
- Released: 2026-08-06

### Claude Haiku 5.5 (`claude-haiku-5-5`)

Anthropic's newest small, fast model for subagents and high-volume work, 1M context

- Lifecycle: active
- Provider family: anthropic
- Input price: $0.025 ($0.125 >200,000)
- Output price: $0.125 ($0.625 >200,000)
- Long-context pricing applies when prompt tokens exceed 200,000
- Context tokens: 1M
- Maximum output tokens: 128,000
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling
- Released: 2026-10-07

### Claude Haiku 4.5 (`claude-haiku-4-5`)

fast, low-cost Anthropic, high-volume

- Lifecycle: active
- Provider family: anthropic
- Input price: $0.25
- Output price: $1.25
- Context tokens: 200K
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling
- Released: 2025-10-01

### Gemini 4 Argon (`gemini-4-argon`)

Google's new flagship reasoning model, 1M context; introductory price

- Lifecycle: active
- Provider family: google
- Input price: $2.00
- Output price: $10.00
- Context tokens: 1M
- Maximum output tokens: 65,536
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-10-13

### Gemini 3.7 Flash (`gemini-3.7-flash`)

fast multimodal Flash for agents; promotional pricing through 2026-12-31

- Lifecycle: active
- Provider family: google
- Input price: $0.6375
- Output price: $3.1875
- Context tokens: 1M
- Maximum output tokens: 65,536
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-08-13

### Gemini 3.8 Flash (`gemini-3.8-flash`)

most capable Flash for agents; promotional pricing through 2026-12-31

- Lifecycle: active
- Provider family: google
- Input price: $0.6375
- Output price: $3.1875
- Context tokens: 1M
- Maximum output tokens: 65,536
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: 2026-09-02

### Gemini 3.6 Flash (`gemini-3.6-flash`)

current general-purpose Flash GA, 1M context

- Lifecycle: active
- Provider family: google
- Input price: $0.6375
- Output price: $3.1875
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Gemini 3.5 Flash-Lite (`gemini-3.5-flash-lite`)

current low-cost Flash-Lite GA, 1M context

- Lifecycle: active
- Provider family: google
- Input price: $0.255
- Output price: $2.125
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling, JSON Schema
- Released: not specified

### Gemini 3.5 Flash (`gemini-3.5-flash`)

Google's next-gen Flash GA, 1M context, thinking

- Lifecycle: active
- Provider family: google
- Input price: $1.275
- Output price: $7.65
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Gemini 3.1 Pro Preview (`gemini-3.1-pro-preview`)

Google's flagship reasoning, 1M context, thinking

- Lifecycle: active
- Provider family: google
- Input price: $1.70
- Output price: $10.20
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Nano Banana Pro (Gemini 3 Pro Image) (`gemini-3-pro-image`)

Google's Nano Banana Pro at 1K, billed per image

- Lifecycle: active
- Provider family: google
- Input price: -
- Output price: $0.114/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-05-28

### Nano Banana 2.1 (`gemini-nano-banana-2.1`)

Google's newest Nano Banana at 1K, billed per image

- Lifecycle: active
- Provider family: google
- Input price: -
- Output price: $0.036/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-10-06

### Gemini 3 Flash Preview (`gemini-3-flash-preview`)

legacy compatibility; migrate to Gemini 3.6 Flash

- Lifecycle: deprecated
- Provider family: google
- Input price: $0.425
- Output price: $2.55
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, reasoning, tool calling, JSON Schema
- Released: not specified

### Gemini 3.1 Flash Lite (`gemini-3.1-flash-lite`)

legacy compatibility; migrate to Gemini 3.5 Flash-Lite

- Lifecycle: deprecated
- Provider family: google
- Input price: $0.2125
- Output price: $1.275
- Context tokens: 1M
- Maximum output tokens: -
- APIs: Chat Completions, Responses
- Capabilities: text input, text output, image input, streaming, tool calling, JSON Schema
- Released: not specified

### FLUX.2 Pro (`flux.2-pro`)

flagship image generation, billed per image

- Lifecycle: active
- Provider family: black-forest-labs
- Input price: -
- Output price: $0.027/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: not specified

### FLUX.1 Schnell (`flux.1-schnell`)

ultra-fast open image generation, billed per image

- Lifecycle: active
- Provider family: black-forest-labs
- Input price: -
- Output price: $0.003/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: not specified

### SDXL Turbo (`sdxl-turbo`)

fast open image generation (SDXL Turbo), billed per image

- Lifecycle: active
- Provider family: stability-ai
- Input price: -
- Output price: $0.003/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: not specified

### FLUX.2 Klein (`flux.2-klein`)

open FLUX.2 image generation, billed per image

- Lifecycle: active
- Provider family: black-forest-labs
- Input price: -
- Output price: $0.02/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: not specified

### Qwen Image 3.0 (`qwen-image-3.0`)

Alibaba text-to-image, 512x512 to 2560x2560, flat $0.04 per image; optional prompt_extend

- Lifecycle: active
- Provider family: qwen
- Input price: -
- Output price: $0.04/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-10-12

### Seedream 5.0 Pro (`seedream-5.0-pro`)

ByteDance's Seedream 5.0 Pro: flagship photorealistic image generation, billed per image

- Lifecycle: active
- Provider family: bytedance
- Input price: -
- Output price: $0.07/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-09-18

### Seedream 4 (`seedream-4`)

ByteDance Seedream 4: fast, high-quality image generation, billed per image

- Lifecycle: active
- Provider family: bytedance
- Input price: -
- Output price: $0.055/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-09-18

### Bria FIBO 1.5 (`bria-fibo-1.5`)

Bria FIBO 1.5: image generation trained on fully licensed data (commercially safe), billed per image

- Lifecycle: active
- Provider family: bria
- Input price: -
- Output price: $0.055/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-09-18

### Bria FIBO 2.0 (`bria-fibo-2.0`)

Bria FIBO 2.0: Bria reports training on fully licensed data for commercially safe image generation, billed per image

- Lifecycle: active
- Provider family: bria
- Input price: -
- Output price: $0.055/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-10-18

### GPT Image 2 (`gpt-image-2`)

OpenAI's GPT Image 2 at a fixed ~1.5MP standard output, billed per image

- Lifecycle: active
- Provider family: openai
- Input price: -
- Output price: $0.01/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-10-09

### GPT Image 2.5 Flare (`gpt-image-2.5-flare`)

OpenAI's GPT Image 2.5, speed tier, at medium quality, billed per image

- Lifecycle: active
- Provider family: openai
- Input price: -
- Output price: $0.018/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-09-09

### GPT Image 2.5 Sunburst (`gpt-image-2.5-sunburst`)

OpenAI's GPT Image 2.5, precision tier, at medium quality, billed per image

- Lifecycle: active
- Provider family: openai
- Input price: -
- Output price: $0.018/image
- Context tokens: -
- Maximum output tokens: -
- APIs: Images Generations
- Capabilities: text input, image output
- Released: 2026-09-09

### Qwen3 ASR (`qwen3-asr`)

Speech to text

- Lifecycle: active
- Provider family: qwen
- Input price: $0.0006/minute
- Output price: -
- Context tokens: -
- Maximum output tokens: -
- APIs: Audio Transcriptions
- Capabilities: audio input, text output
- Released: 2026-10-12

### Nemotron 3.5 ASR (`nemotron-3.5-asr`)

Speech to text

- Lifecycle: active
- Provider family: nvidia
- Input price: $0.0003/minute
- Output price: -
- Context tokens: -
- Maximum output tokens: -
- APIs: Audio Transcriptions
- Capabilities: audio input, text output
- Released: 2026-10-12

### Whisper Large v3 Turbo (`whisper-large-v3-turbo`)

Speech to text

- Lifecycle: active
- Provider family: openai
- Input price: $0.0003/minute
- Output price: -
- Context tokens: -
- Maximum output tokens: -
- APIs: Audio Transcriptions
- Capabilities: audio input, text output
- Released: 2026-10-12

### Chatterbox Turbo (`chatterbox-turbo`)

English text to speech

- Lifecycle: active
- Provider family: resembleai
- Input price: $1.50/1M characters
- Output price: -
- Context tokens: -
- Maximum output tokens: -
- APIs: Audio Speech
- Capabilities: text input, audio output, streaming
- Released: 2026-10-12

### Qwen3 TTS (`qwen3-tts`)

Chinese and English text to speech

- Lifecycle: active
- Provider family: qwen
- Input price: $25.00/1M characters
- Output price: -
- Context tokens: -
- Maximum output tokens: -
- APIs: Audio Speech
- Capabilities: text input, audio output, streaming
- Released: 2026-10-12

## Pricing and commercial terms

- Priced below the standard published per-token list rate on most of the catalog. Every row of the pricing table on the site names its reference list price and links to the page that publishes it, so any claim here can be checked at its source.
- Where we are not below list, the pricing table says so on that row rather than leaving it out.
- Pay-as-you-go from a prepaid balance. No subscription, no per-seat fee, no expiry on purchased credit.
- Minimum top-up: $5.
- **First top-up bonus (one-time)**: we match 100% of your first credit purchase, up to $50 in bonus credits. The bonus is added to your balance the next time you top up (any amount from $5) — pay $20, then top up $5, and $20 of bonus arrives with it. A larger first payment still receives the $50 maximum. One per customer and payment card; standard pay-as-you-go after that.
- Usage is billed per token from the response's own `usage` block, which includes a `cost` field on every call.

## QuickSilver Machines

QuickSilver Machines (beta): A dev box for your agents. Agents ready out of the box. One unified bill. Zero friction.

- Ready out of the box: Claude Code, Codex, OpenCode and Hermes are preinstalled and already signed in to QuickSilver Pro models. Open the terminal and type `claude`.
- One unified bill: the machine and the models your agents call use one QuickSilver balance. AI usage is charged at normal model prices; no separate cloud, Anthropic or OpenAI bills.
- Zero friction: no API keys to create or paste, no config files. About 30 seconds from Create to a running machine, measured on a new trial account on 2026-11-04; startup time can vary.

QuickSilver Machines (beta) is a private Linux desktop and terminal in your browser for AI agents, operated by MachineFi Inc.

- Standard machine: 2 vCPU, 4 GB RAM and a 20 GB home disk; Chromium and Docker included.
- Claude Code, Codex, OpenCode and Hermes are preinstalled and connected to QuickSilver Pro.
- Santa Clara, California, United States, with a US IP.
- $0.02 per running hour, billed per minute from your QuickSilver Pro balance. Paused machines are free. Each account has a cap of 200 running hours per month.
- Free trial on the $0.05 signup credit, no card. AI usage is billed separately at normal API rates from the same balance, so the credit is shared with machine runtime. After the trial, add $5 by card.
- Trial accounts can have 1 machine; paid accounts can have up to 2 machines, both running at the same time. Each continuous session stops after 8 hours.
- Trial machines are deleted 24 hours after last use; paid machines 30 days after last use. Paid machine owners receive email warnings 7 days and 1 day before deletion. Deletion is permanent. Recovery copies kept for operations are purged within 7 days of deletion and are not available for restore on request.
- Beta: no backup or durability guarantee. Keep important work elsewhere; machine data may be lost.

[QuickSilver Machines](https://quicksilverpro.io/machines/) · [Run Claude Code and Codex on a cloud dev box](https://quicksilverpro.io/blog/claude-code-cloud-dev-box/)

Learn more: https://quicksilverpro.io/machines/ — Create: https://quicksilverpro.io/dashboard/machines/


## Trying it without an API key

[quicksilverpro.io/chat](https://quicksilverpro.io/chat/) gives every registered account a free trial balance to use in the browser — no card and no API key. Each reply shows the exact cost of that turn, at the same per-token rate the API charges.

## Trust and verification

We commit to serving the model you asked for, at the publisher's reference precision — no silent substitution of a cheaper model, and no quantized copy billed as the original. [quicksilverpro.io/trust](https://quicksilverpro.io/trust/) states the commitments in full and describes probes you can run yourself to check what is actually being served, including the statistical Model Equality Testing method for the open-weight models.

## Comparisons and migration

Per-model comparisons against each provider's published list rates: [/compare](https://quicksilverpro.io/compare/). Migration from another OpenAI-compatible provider changes two lines — the API base and the API key — with model IDs dropping the `provider/` prefix: [/migrate/from-openrouter](https://quicksilverpro.io/migrate/from-openrouter/) and the sibling guides.

## Operational links

- [Quickstart](https://quicksilverpro.io/docs/quickstart/)
- [Models](https://quicksilverpro.io/docs/models/)
- [Images API](https://quicksilverpro.io/docs/images/)
- [System One decisions API](https://quicksilverpro.io/docs/systemone/)
- [Rate limits](https://quicksilverpro.io/docs/rate-limits/)
- [Streaming](https://quicksilverpro.io/docs/streaming/)
- [Tool calling](https://quicksilverpro.io/docs/tools/)
- [Structured output](https://quicksilverpro.io/docs/json-schema/)
- [Errors](https://quicksilverpro.io/docs/errors/)
- [Integrations](https://quicksilverpro.io/docs/integrations/)
- [Status](https://quicksilverpro.io/status/)
- [Dashboard](https://quicksilverpro.io/dashboard/)

## Legal and operator

- Operator: MachineFi Inc., 68 Willow Rd, Menlo Park, CA 94205, USA. Payments are processed by Stripe and appear on statements as MACHINEFI INC.
- [Terms of Service](https://quicksilverpro.io/terms/) · [Privacy Policy](https://quicksilverpro.io/privacy/) · [Data Processing Addendum](https://quicksilverpro.io/dpa/)
- Contact: hello@quicksilverpro.io

Catalog facts in this file are generated. For programmatic consumption, use <https://quicksilverpro.io/pricing.json>.

## Machines comparisons

As of 2026-11-04: Claude Code, Codex, OpenCode and Hermes are preinstalled and signed in to QuickSilver Pro models. No API keys or config files; one balance for machine time and inference (AI usage is additional). A new trial account reached Running ~32 s after Create in the latest measured test; this is not a provisioning guarantee. New accounts can start a trial machine on signup credit without a card or $1 balance; after the trial, $1.00 available balance is required to start.

- [QuickSilver Machines vs DigitalOcean](https://quicksilverpro.io/vs/digitalocean/): agent setup, Droplet billing and retained-workspace costs.
- [QuickSilver Machines vs AWS](https://quicksilverpro.io/vs/aws/): EC2 and Lightsail setup, stopped-state charges and cost examples.
- [QuickSilver Machines vs GitHub Codespaces](https://quicksilverpro.io/vs/github-codespaces/): connected agents, browser desktop vs IDE, personal allowances and storage costs.