Skip to content

Pricing

Frontier and open models. One API. Priced below list.

Browse rates, estimate spend, compare providers, or use the CLI.

Pay with

Options at checkout depend on your country. Minimum top-up $5.

Published rates. A receipt on every call.

  • Prepaid credit
  • Top up from $5
  • x402 per call

QuickSilver Machines — Agents ready out of the box. One unified bill for the machine and AI usage at normal model prices. No API keys or config files. $0.02 per running hour, billed per minute; paused is free; 200 running hours/month cap; free trial on the $0.05 signup credit, no card

Sort
Filter

81 models · Sorted by Popular

Model
Context
Latency
Intelligence
InputUSD / 1M tokens
OutputUSD / 1M tokens
vs. list
Claude Opus 5.5claude-opus-5-5

coding, knowledge work and computer use

ReasoningToolsVision
1M
—
58
Input / 1M$1.00list price $4.00
Output / 1M$5.00list price $20.00
−75%
Claude Fable 5.2Newclaude-fable-5-2

coding, reasoning, and vision (5.2)

ReasoningToolsVision
1M
—
—
Input / 1M$2.00list price $8.00
Output / 1M$10.00list price $40.00
−75%
Claude Fable 5.1claude-fable-5-1

deep reasoning, long-horizon agentic (5.1)

ReasoningToolsVision
1M
—
57
Input / 1M$2.50list price $10.00
Output / 1M$12.50list price $50.00
−75%
Claude Sonnet 5.5claude-sonnet-5-5

newest Sonnet: faster, fewer tokens per task, strong coding

ReasoningToolsVision
1M
—
—
Input / 1M$0.50list price $2.00
Output / 1M$2.50list price $10.00
−75%
Claude Haiku 5.5claude-haiku-5-5

newest Haiku: small, fast, 1M context, built for subagents and high-volume work

ToolsVision
1M
—
—
Input / 1M$0.025list price $0.10$0.125 >200K
Output / 1M$0.125list price $0.50$0.625 >200K
−75%
Claude Opus 5claude-opus-5

demanding reasoning, end-to-end coding, visual analysis, long-horizon agents

ReasoningToolsVision
1M
—
54
Input / 1M$1.25list price $5.00
Output / 1M$6.25list price $25.00
−75%
Claude Fable 5claude-fable-5

deep reasoning, long-horizon agentic

ReasoningToolsVision
1M
—
53
Input / 1M$2.50list price $10.00
Output / 1M$12.50list price $50.00
−75%
Claude Opus 4.8claude-opus-4-8

top-tier reasoning, coding, agentic

ReasoningToolsVision
1M
—
—
Input / 1M$1.25list price $5.00
Output / 1M$6.25list price $25.00
−75%
Claude Sonnet 5claude-sonnet-5

newest Sonnet, stronger reasoning & coding, below list price

ReasoningToolsVision
1M
—
45
Input / 1M$0.50list price $2.00
Output / 1M$2.50list price $10.00
−75%
Claude Haiku 4.5claude-haiku-4-5

fast, low-cost, high-volume tasks

ToolsVision
200K
—
—
Input / 1M$0.25list price $1.00
Output / 1M$1.25list price $5.00
−75%
GPT-6.2 SolNewgpt-6.2-sol

Text, images, tools and structured output

ReasoningToolsVision
1M
—
—
Input / 1M$2.00$4.00 >200K
Output / 1M$10.00$15.00 >200K
GPT-6.2 AstraNewgpt-6.2-astra

Text, images, tools and structured output

ReasoningToolsVision
1M
—
—
Input / 1M$8.00$16.00 >200K
Output / 1M$40.00$60.00 >200K
GPT-6.1 Solgpt-6.1-sol

GPT-6.1 Sol: near-Astra agentic coding and computer use at Sol pricing

ReasoningToolsVision
1M
—
—
Input / 1M$2.00$4.00 >200K
Output / 1M$10.00$15.00 >200K
GPT-6.1 TerraNewgpt-6.1-terra

everyday agentic coding, writing, and screenshot understanding

ReasoningToolsVision
1M
—
—
Input / 1M$1.00$2.00 >200K
Output / 1M$5.00$7.50 >200K
GPT-6.1 Terra ProNewgpt-6.1-terra-pro

same model as Terra in pro reasoning mode — more reasoning tokens per request, same price

ReasoningToolsVision
1M
—
—
Input / 1M$1.00$2.00 >200K
Output / 1M$5.00$7.50 >200K
GPT-6 Astragpt-6-astra

long-horizon agentic coding, deep research, document work, image input

ReasoningToolsVision
1M
—
55
Input / 1M$10.00$20.00 >200K
Output / 1M$50.00$75.00 >200K
GPT-6 Solgpt-6-sol

GPT-6 mid-flagship: strong reasoning, agentic coding, a rung below Astra

ReasoningToolsVision
1M
—
—
Input / 1M$2.00$4.00 >200K
Output / 1M$10.00$15.00 >200K
GPT-6 Lunagpt-6-luna

cheapest GPT-6 tier: high-volume chat, classification, lightweight agents

ReasoningToolsVision
1M
—
—
Input / 1M$0.10$0.20 >200K
Output / 1M$0.50$0.75 >200K
GPT-OSS 120Bgpt-oss-120b

high-volume production agents, OpenAI open-weight MoE

ReasoningTools
131K
—
16
Input / 1M$0.03
Output / 1M$0.15
at list
GPT-5.6 Solgpt-5.6-sol

complex reasoning, agentic coding, long-horizon tasks

Tools
1M
—
51
Input / 1M$1.60list price $2.00
Output / 1M$8.00list price $10.00
−20%
GPT-5.6 Lunagpt-5.6-luna

high-volume chat, classification, lightweight agentic

Tools
1M
—
43
Input / 1M$0.16list price $0.20
Output / 1M$0.96list price $1.20
−20%
GPT Image 2gpt-image-2

OpenAI image generation at a fixed ~1.5MP output

Image
—
—
—
Input / 1M—
Output · per image$0.01per image
—
GPT Image 2.5 Flaregpt-image-2.5-flare

OpenAI GPT Image 2.5, speed tier, at medium quality

Image
—
—
—
Input / 1M—
Output · per image$0.018per image
—
GPT Image 2.5 Sunburstgpt-image-2.5-sunburst

OpenAI GPT Image 2.5, precision tier, at medium quality

Image
—
—
—
Input / 1M—
Output · per image$0.018per image
—
Gemini 3.8 Flashgemini-3.8-flash

most capable Flash for agents; 1M context

ReasoningToolsVision
1M
—
47
Input / 1M$0.6375list price $0.75
Output / 1M$3.1875list price $3.75
−15%
Gemini 4 HydrogenNewgemini-4-hydrogen

Efficient coding and agent workflows.

ReasoningToolsVision
1M
—
—
Input / 1M$1.50
Output / 1M$7.50
Gemini 4 NeonNewgemini-4-neon

Coding and agentic work with 1M context.

ReasoningToolsVision
1M
—
—
Input / 1M$3.00
Output / 1M$15.00
Gemini 4 CarbonNewgemini-4-carbon

Coding, agents and mandatory reasoning with 1M context, tools and structured output

ReasoningTools
1M
—
—
Input / 1M$2.00
Output / 1M$10.00
Gemini 4 Argongemini-4-argon

Always-on reasoning, 1M context, text and images, tools and structured output

ReasoningToolsVision
1M
—
—
Input / 1M$2.00
Output / 1M$10.00
at list
Gemini 3.5 Flash-Litegemini-3.5-flash-lite

current low-cost, high-volume workloads

ToolsVision
1M
—
28
Input / 1M$0.255list price $0.30
Output / 1M$2.125list price $2.50
−15%
Gemini 3.1 Pro Previewgemini-3.1-pro-preview

flagship reasoning

ReasoningToolsVision
1M
—
37
Input / 1M$1.70list price $2.00
Output / 1M$10.20list price $12.00
−15%

GA pro-grade image generation

Image
—
—
—
Input / 1M—
Output · per image$0.114list price $0.134per image
Nano Banana 2.1gemini-nano-banana-2.1

Google's newest Flash-tier image generation and editing, 1K to 4K

Image
—
—
—
Input / 1M—
Output · per image$0.036per image
—
DeepSeek V4.1 Flash 1017deepseek-v4.1-flash-1017

Long-context text and images, tools and structured output with optional reasoning

ReasoningToolsVision
1M
—
—
Input / 1M$0.098
Output / 1M$0.294
at list
DeepSeek V4.1 Flashdeepseek-v4.1-flash

newest DeepSeek Flash architecture, faster than V4 Flash

ReasoningTools
1M
—
—
Input / 1M$0.154list price $0.30
Output / 1M$0.462list price $1.20
−49–62%
DeepSeek V4 Prodeepseek-v4-pro

premium reasoning

ReasoningTools
1M
—
42
Input / 1M$0.70list price $1.32
Output / 1M$2.10list price $3.96
−47%
DeepSeek V4 Flashdeepseek-v4-flash

fast chat & coding, thinking on by default

ReasoningTools
1M
—
41
Input / 1M$0.06
Output / 1M$0.18
at list

Meta 5 · StepFun 1 · xAI 1 · Alibaba / Qwen 10 · Z.ai 4 · Moonshot AI 4 · thinkingmachines 2 · MiniMax 1 · Xiaomi 3 · NVIDIA 1 · Tencent 2 · System One 2 · Black Forest Labs 3 · Stability AI 1 · ByteDance 2 · BRIA 2

Muse Spark Openmuse-spark-open

Coding agents, tools, structured output and image understanding

ReasoningToolsVision
1M
—
—
Input / 1M$1.25
Output / 1M$4.25
at list
Muse EmberNewmuse-ember

Agent subtasks, extraction and long-document parsing.

ReasoningToolsVision
1M
—
—
Input / 1M$0.10
Output / 1M$0.50
Muse Wondermuse-wonder

Agentic personal and professional work, mandatory reasoning, 1M context

ReasoningToolsVision
1M
—
—
Input / 1M$4.00
Output / 1M$20.00
at list
Muse Spark 1.3muse-spark-1.3

Flagship coding & agentic reasoning, 1M context

ReasoningToolsVision
1M
—
53
Input / 1M$1.00list price $1.25
Output / 1M$3.40list price $4.25
−20%
Muse Glimmer 30Bmuse-glimmer-30b

Budget agents, everyday coding, open weights

ReasoningToolsVision
131K
—
24
Input / 1M$0.30
Output / 1M$1.20
at list
Step 5 Previewstep-5-preview

Reasoning, tools, structured output and image understanding

ReasoningToolsVision
1M
—
—
Input / 1M$1.00
Output / 1M$2.70
at list
Grok 4.7grok-4.7

long-running agentic coding, knowledge work, self-verification, image input

ReasoningToolsVision
500K
—
—
Input / 1M$2.00$4.00 >200K
Output / 1M$6.00$12.00 >200K
—
Qwen4-MaxNewqwen4-max

Qwen4 flagship for coding and agent workflows.

ReasoningToolsVision
1M
—
—
Input / 1M$1.50
Output / 1M$4.50
Qwen3.8 Maxqwen3.8-max

Qwen 3.8 flagship, autonomous coding

ReasoningToolsVision
1M
—
47
Input / 1M$2.00
Output / 1M$6.00
Qwen3.8 Max Primeqwen3.8-max-prime

Qwen top-tier flagship: deepest reasoning, autonomous coding

ReasoningToolsVision
1M
—
—
Input / 1M$4.00
Output / 1M$12.00
Qwen3.8 27Bqwen3.8-27b

1M-context coding agents at small-model prices

Tools
1M
—
41
Input / 1M$0.34list price $0.425
Output / 1M$2.04list price $2.55
−20%
Qwen3.8 Flash Nextqwen3.8-flash-next

Cheapest next-gen Qwen: 6B-active Qwen4 preview on a 1M-token window

Tools
1M
—
—
Input / 1M$0.12list price $0.15
Output / 1M$0.376list price $0.47
−20%
Qwen3.8 Omni Flashqwen3.8-omni-flash

Qwen's first agentic omni model: image, audio + video understanding with tool use, at flash pricing

ReasoningToolsVision
1M
—
—
Input / 1M$0.15
Output / 1M$0.47
Qwen3.7 Flashqwen3.7-flash

fast multimodal agents, visual coding, search

ToolsVision
1M
—
—
Input / 1M$0.024list price $0.03
Output / 1M$0.104list price $0.13
−20%
Qwen3.6-35B-A3Bqwen3.6-35b

long-context RAG, 35B MoE

Tools
262K
—
—
Input / 1M$0.05
Output / 1M$0.70
at list
Qwen Image 3.0qwen-image-3.0

Alibaba text-to-image with optional prompt extension.

Image
—
—
—
Input / 1M—
Output · per image$0.04per image
—
Qwen3.8 27B Decenteredqwen3.8-27b-decentered

Community Macs for coding agents and long documents at 30% lower token prices.

Tools
1M
—
—
Input / 1M$0.238
Output / 1M$1.428
—
GLM 5.3glm-5.3

complex software engineering, long-horizon agents

ReasoningTools
1M
—
49
Input / 1M$0.60
Output / 1M$2.20
at list
GLM 5.3 Primeglm-5.3-prime

top reasoning flagship, complex software engineering

ReasoningTools
1M
—
—
Input / 1M$2.24list price $2.80
Output / 1M$7.04list price $8.80
−20%
GLM 5.3 Flashglm-5.3-flash

high-volume agents and coding at workhorse pricing

ReasoningTools
1M
—
46
Input / 1M$0.0284
Output / 1M$0.0923
at list
GLM 5.2glm-5.2

long-horizon agents, project-level coding

Tools
1M
—
—
Input / 1M$0.70
Output / 1M$2.20
at list
Kimi K3.1 Prokimi-k3.1-pro

Long-context coding and image-based workflows.

ReasoningToolsVision
1M
—
—
Input / 1M$2.00
Output / 1M$10.00
at list
Kimi K3.1 Pro Highspeedkimi-k3.1-pro-highspeed

Long-context coding and image-based workflows.

ReasoningToolsVision
1M
—
—
Input / 1M$4.00
Output / 1M$20.00
at list
Kimi K3kimi-k3

Multimodal reasoning, agentic coding

ReasoningToolsVision
1M
—
50
Input / 1M$2.55
Output / 1M$12.75
—
Kimi K2.6kimi-k2.6

Opus-class agentic / planning

ReasoningToolsVision
256K
—
—
Input / 1M$0.45
Output / 1M$1.95
at list
Inkling 2 MiniNewinkling-2-mini

Lowest-priced Inkling for text, images and automatic tools.

ReasoningToolsVision
1M
—
—
Input / 1M$0.11
Output / 1M$0.44
—
Inkling 2 SmallNewinkling-2-small

Open-weight multimodal reasoning with 594B total and 17B active parameters.

ReasoningToolsVision
1M
—
—
Input / 1M$0.165
Output / 1M$0.55
—
MiniMax M3minimax-m3

long-horizon agentic coding, tool use

Tools
1M
—
36
Input / 1M$0.24list price $0.30
Output / 1M$0.96list price $1.20
−20%
MiMo-V2.6-Promimo-v2.6-pro

flagship open-weight coding, agentic workflows, image input

ToolsVision
1M
—
46
Input / 1M$0.426
Output / 1M$0.861
—
MiMo-V2.6-Flashmimo-v2.6-flash

fast low-cost coding, agents, image input

ToolsVision
1M
—
—
Input / 1M$0.112list price $0.14
Output / 1M$0.224list price $0.28
−20%
MiMo-V2.5mimo-v2.5

cost-efficient everyday coding, agentic workflows

Tools
1M
—
33
Input / 1M$0.32list price $0.40
Output / 1M$1.60list price $2.00
−20%
Nemotron 3.5 Lightningnemotron-3.5-lightning

fast, tool-heavy agents and high-volume automation

Tools
262K
—
—
Input / 1M$0.066
Output / 1M$0.176
—
Hy4 FlashNewhy4-flash

Lowest-priced Tencent option: text, images and automatic tools

ReasoningToolsVision
1M
—
—
Input / 1M$0.0385
Output / 1M$0.1546
—
Hy4Newhy4

GA multimodal reasoning & agentic coding, 1M context

ReasoningToolsVision
1M
—
—
Input / 1M$0.459
Output / 1M$1.375
—
Trio-Spark v1.3trio-spark-v1.3

System One typed decisions on POST /v1/systemone: choice, score and noul with calibrated probabilities. Text input only on QSP, 1,024-token input limit (Jev: 32K). $0.042 per 1M input tokens; output free.

System One
1K
—
—
Input / 1M$0.042
Output / 1MFree
—
Jev 1.13jev-1.13

Typed decisions, not chat: routing, classification and scoring with calibrated probabilities via /v1/systemone

System One
32K
—
—
Input / 1M$0.042
Output / 1MFree
FLUX.2 Proflux.2-pro

flagship image generation

Image
—
—
—
Input / 1M—
Output · per image$0.027list price $0.031per image
FLUX.1 Schnellflux.1-schnell

fast, high-volume image drafts

Image
—
—
—
Input / 1M—
Output · per image$0.003per image
FLUX.2 Kleinflux.2-klein

balanced open FLUX.2 image generation

Image
—
—
—
Input / 1M—
Output · per image$0.02per image
SDXL Turbosdxl-turbo

cheapest, fastest image previews

Image
—
—
—
Input / 1M—
Output · per image$0.003per image
Seedream 5.0 Proseedream-5.0-pro

ByteDance's flagship photorealistic image model

Image
—
—
—
Input / 1M—
Output · per image$0.07per image
—
Seedream 4seedream-4

fast, high-quality ByteDance image generation

Image
—
—
—
Input / 1M—
Output · per image$0.055per image
—
Bria FIBO 1.5bria-fibo-1.5

trained on fully licensed, commercially safe data

Image
—
—
—
Input / 1M—
Output · per image$0.055per image
—
Bria FIBO 2.0bria-fibo-2.0

licensed training data, according to Bria

Image
—
—
—
Input / 1M—
Output · per image$0.055per image
—

Prices are exact per-token rates, not rounded — some carry more decimals than others. Each struck-through figure is that row's reference list price. "At list" means we sell at the reference price; "mixed" means we are below it on one side and above on the other.

Every row checkable, every model verifiable →

Building an agent? Fund a key programmatically with USDC — no account, no card.

x402 docs →

How a dollar becomes a receipt

  1. Top up creditCard, wallet or USDC. $0.05 starter credit · no card.
  2. Call any modelTokens, images, audio seconds and characters, each at its published unit rate.
  3. Get usage.cost backEvery response reports its own cost, computed from those rates.
  4. Reconcile anytimeCheck against /pricing.json. Price changes are dated in the changelog.

How usage.cost is computed

Rates that aren’t one number

Long-context tiers, flat-rate speech and per-image pricing, stated in full. The same conditions appear inline in Models.

Long context · prompt > 200K tokens

ModelBase>200K
gpt-6.2-astra$8.00 / $40.00$16.00 / $60.00
gpt-6-astra$10.00 / $50.00$20.00 / $75.00
gpt-6-luna$0.10 / $0.50$0.20 / $0.75
gpt-6.2-sol$2.00 / $10.00$4.00 / $15.00
gpt-6.1-sol$2.00 / $10.00$4.00 / $15.00
gpt-6.1-terragpt-6.1-terra-pro$1.00 / $5.00$2.00 / $7.50
gpt-6-sol$2.00 / $10.00$4.00 / $15.00
grok-4.7$2.00 / $6.00$4.00 / $12.00
claude-haiku-5-5$0.025 / $0.125$0.125 / $0.625

Speech

ModelQSP
Qwen3 ASR$0.0006 per minute of audio
Nemotron 3.5 ASR$0.0003 per minute of audio
Whisper Large v3 Turbo$0.0003 per minute of audio
Chatterbox Turbo$1.50 per 1M characters
Qwen3 TTS$25.00 per 1M characters

OpenAI list prices: whisper-1 $0.006 per minute; tts-1 $15 per 1M characters.

Change the base URL. Keep your code.

The official OpenAI SDKs work as they are — point them at QuickSilver Pro.

python
# Two lines. That is the whole migration.
from openai import OpenAI
 
client = OpenAI(
    base_url="https://api.quicksilverpro.io/v1",
    api_key="your-api-key",
)

FAQ

Common questions

QuickSilver Pro is an OpenAI-compatible inference API with 86 models, one endpoint and one API key. Browse models →

See all questions

Get your API key

Create an account, get your API key in 30 seconds.