Models
AI model API pricing. No fog on the rate card.
Estimate a workload against live vendor list prices across 64 models. One OpenAI-compatible key, 1-step integration, and a built-in optimizer that can cut cost by up to 40% with no quality loss. Rates as of 16 October 2026.
64
Routes
15
Providers
0%
Markup
LLM pricing calculator
Put a workload on the rate card.
Defaults are 10K input tokens, 1K output tokens, and 3,000 requests a month. Switch to the 100K / 10K agent turn to match the cheapest-models ranking. Optional 5.5% column is a top-up fee, not a token markup.
Workload calculator
Catalog rates · USD · no markup
Models in the estimate
3 selected| Route | Per request | Monthly | $100 buys |
|---|---|---|---|
| DeepSeek V4 Flash DeepSeek | $0.0011 | $3.24 | 92,592 req |
| GPT-5.6 Luna OpenAI | $0.0032 | $9.60 | 31,250 req |
| Claude Sonnet 4.6 Anthropic | $0.045 | $135.00 | 2,222 req |
Estimates apply live catalog input and output rates only. Actual spend follows the tokens your client sends and the model returns. Image-generation routes are omitted because they are not a chat turn.
Routing console
Find the right model.
Vendor list prices in USD. Long-context tiers and special billing rules remain attached to each model detail page.
| Model route | Capability | Context | Input | Output | Open |
|---|---|---|---|---|---|
Qwen3.6 Plus qwen3.6-plus | ChatVision | 1M | $0.50 | $3.00 | |
Qwen3.7 Max qwen3.7-max | Chat | 1M | $2.50 | $7.50 | |
Qwen3.7 Plus qwen3.7-plus | ChatVision | 1M | $0.32 | $1.28 | |
Qwen3.8 Flash qwen3.8-flash | Chat | 1M | $0.15 | $0.47 | |
Qwen3.8 Max qwen3.8-max | ChatVision | 1M | $2.00 | $6.00 | |
Claude Fable 5 claude-fable-5 | ChatVision | 1M | $10.00 | $50.00 | |
Claude Haiku 4.5 claude-haiku-4-5 | ChatVision | 256K | $1.00 | $5.00 | |
Claude Opus 4.6 claude-opus-4-6 | ChatVision | 1M | $5.00 | $25.00 | |
Claude Opus 4.7 claude-opus-4-7 | ChatVision | 1M | $5.00 | $25.00 | |
Claude Opus 4.8 claude-opus-4-8 | ChatVision | 1M | $5.00 | $25.00 | |
Claude Opus 5 claude-opus-5 | ChatVision | 1M | $5.00 | $25.00 | |
Claude Opus 5.5 claude-opus-5-5 | ChatVision | 1M | $4.00 | $20.00 | |
Claude Sonnet 4.6 claude-sonnet-4-6 | ChatVision | 1M | $3.00 | $15.00 | |
Claude Sonnet 5 claude-sonnet-5 | ChatVision | 1M | $2.00 | $10.00 | |
Doubao Seed 2.0 Code doubao-seed-2.0-code | ChatVision | 200K | $0.67 | $3.36 | |
Doubao Seed 2.0 Pro doubao-seed-2.0-pro | ChatVision | 128K | $0.67 | $3.36 | |
DeepSeek V4 Flash deepseek-v4-flash | Chat | 1M | $0.09 | $0.18 | |
DeepSeek V4 Flash Vision deepseek-v4-flash-vision-exp | ChatVision | 1M | $0.22 | $0.66 | |
DeepSeek V4 Pro deepseek-v4-pro | Chat | 1M | $0.435 | $0.87 | |
DeepSeek V4.1 Flash deepseek-v4.1-flash | ChatVision | 1M | $0.18 | $0.73 | |
Gemini 2.5 Flash gemini-2.5-flash | ChatVision | 1M | $0.30 | $2.50 | |
Gemini 2.5 Flash Lite gemini-2.5-flash-lite | ChatVision | 1M | $0.10 | $0.40 | |
Gemini 3 Flash gemini-3-flash | ChatVision | 1M | $0.50 | $3.00 | |
Gemini 3.1 Flash Lite gemini-3.1-flash-lite | ChatVision | 1M | $0.25 | $1.50 | |
Gemini 3.1 Pro gemini-3.1-pro | ChatVision | 1M | $2.00 | $12.00 | |
Gemini 3.5 Flash gemini-3.5-flash | ChatVision | 1M | $1.50 | $9.00 | |
Gemini 3.6 Flash gemini-3.6-flash | ChatVision | 1M | $0.75 | $3.75 | |
Gemini 3.7 Flash gemini-3.7-flash | ChatVision | 1M | $0.75 | $3.75 | |
Gemini 3.8 Flash gemini-3.8-flash | ChatVision | 1M | $0.75 | $3.75 | |
Gemini 4 Argon gemini-4-argon | ChatVision | 1M | $2.00 | $10.00 | |
LongCat 2.0 LongCat-2.0 | Chat | 1M | $0.30 | $1.20 | |
Muse Spark 1.2 Contributor muse-spark-1.2-contributor | Chat | 1M | $0.10 | $0.20 | |
Muse Spark 1.3 Contributor muse-spark-1.3-contributor | Chat | 1M | $0.10 | $0.20 | |
MiniMax M2.7 MiniMax-M2.7 | Chat | 196K | $0.30 | $1.20 | |
MiniMax M2.7 Highspeed MiniMax-M2.7-highspeed | Chat | 196K | $0.60 | $2.40 | |
MiniMax M3 MiniMax-M3 | ChatVision | 1M | $0.30 | $1.20 | |
MiniMax M3 Highspeed MiniMax-M3-highspeed | ChatVision | 1M | $0.45 | $1.80 | |
Kimi K2.6 kimi-k2.6 | ChatVision | 256K | $0.95 | $4.00 | |
Kimi K2.7 kimi-k2.7 | ChatVision | 256K | $0.95 | $4.00 | |
Kimi K3 kimi-k3 | ChatVision | 1M | $3.00 | $15.00 | |
GPT-5.4 gpt-5.4 | ChatVision | 1M | $2.50 | $15.00 | |
GPT-5.5 gpt-5.5 | ChatVision | 256K | $5.00 | $30.00 | |
GPT-5.6 Luna gpt-5.6-luna | ChatVision | 258K | $0.20 | $1.20 | |
GPT-5.6 Sol gpt-5.6-sol | ChatVision | 258K | $5.00 | $30.00 | |
GPT-5.6 Terra gpt-5.6-terra | ChatVision | 258K | $2.00 | $12.00 | |
GPT-6 Astra gpt-6-astra | ChatVision | 922K | $10.00 | $50.00 | |
GPT-6 Luna gpt-6-luna | ChatVision | 922K | $0.10 | $0.50 | |
GPT-6 Sol gpt-6-sol | ChatVision | 922K | $2.00 | $10.00 | |
GPT-6.1 Sol gpt-6.1-sol | ChatVision | 922K | $2.00 | $10.00 | |
GPT Image 2 gpt-image-2 | GenerateVision | — | $5.00 | $30.00 | |
Step 3.7 Flash step-3.7-flash | ChatVision | 256K | $0.20 | $1.15 | |
Hy3 hy3 | Chat | 256K | $0.20 | $0.80 | |
Hy4 Preview hy4-preview | Chat | 1M | $0.834 | $2.501 | |
MiMo V2.5 mimo-v2.5 | ChatVision | 1M | $0.11 | $0.28 | |
MiMo V2.5 Pro mimo-v2.5-pro | Chat | 1M | $0.44 | $0.87 | |
MiMo V2.6 Flash mimo-v2.6-flash | ChatVision | 1M | $0.14 | $0.28 | |
MiMo V2.6 Pro mimo-v2.6-pro | ChatVision | 1M | $0.435 | $0.87 | |
GLM-5.1 glm-5.1 | Chat | 256K | $1.40 | $4.40 | |
GLM-5.2 glm-5.2 | Chat | 1M | $1.40 | $4.40 | |
GLM-5.3 glm-5.3 | Chat | 1M | $1.40 | $4.40 | |
GLM-5.3 Flash glm-5.3-flash | ChatVision | 1M | $0.15 | $0.50 | |
Grok 4.5 grok-4.5 | ChatVision | 500K | $2.00 | $6.00 | |
Grok 4.6 grok-4.6 | ChatVision | 500K | $2.00 | $6.00 | |
Grok 4.7 grok-4.7 | ChatVision | 500K | $2.00 | $6.00 |
Decision modelsFree for a limited time
Typed answers, not generated text.
Send a state and typed questions (choice, noul, score) to POST /v1/systemone and get answers with probabilities and confidence in one pass. Billed on input tokens only; output is free.
Struck-through rates are the list price RouterPlex will charge when the launch promotion ends. Decision calls still need an active balance.
Decision layer
Price is one signal. Use the rest.
Rank costs against a fixed workload, inspect benchmark evidence, or put two live responses side by side before moving production traffic.
Cost rankings
Compare one fixed 100K-in / 10K-out agent turn.
Open ledgerOpenAI pricing
GPT family rates, calculator, and catalog FAQ.
OpenAI hubAnthropic pricing
Claude family rates, calculator, and catalog FAQ.
Anthropic hubQuality evidence
Read blind preferences beside cited external scores.
View benchmarksBlind Arena
Run one prompt through two routes without brand bias.
Start comparisonPricing questions
What the rate card does not hide.
01How much does an LLM API cost?+
It depends on the model and the tokens you send. As of 16 October 2026, the cheapest comparable route on RouterPlex is DeepSeek V4 Flash at $0.09 / $0.18 per 1M tokens — about $0.011 for a 100K-in / 10K-out agent turn. Use the calculator on this page for your own mix.
02How does the pricing calculator work?+
It multiplies the live catalog input and output rates by the token counts you enter, then by requests per month. Defaults are 10K input, 1K output, and 3,000 requests. The agent-turn preset uses the same 100K / 10K profile as the cheapest-models ranking so the two pages stay comparable.
03Are these official vendor prices?+
They are the rates RouterPlex bills today — vendor list prices with 0% markup, pulled from the live catalog on 16 October 2026. If a vendor's marketing page lists a different promotional rate, the catalog is still what a request on this key costs.
04How does this compare to OpenRouter?+
Per-token prices are the same vendor list rates. RouterPlex is a 1-step drop-in with $0 top-up fees (OpenRouter: 5.5% by card), always-on hosted reliability, a built-in optimizer that can cut cost by up to 40% with no quality loss, and a balance that never goes negative. The calculator's optional 5.5% column is that fee, not a token markup.
05Can I switch models without changing code?+
One step: keep the same OpenAI-compatible base URL and API key. Changing route is a one-line model ID change. New models go live on the gateway as they ship. Per-key spend budgets still apply across every model on the key.
Start routing
Every route here. One balance, one key.
Top up from $5 with no subscription and no RouterPlex token markup.