Price list
Every world, priced in the open
Each row shows what the upstream publishes and what Antimatter charges, side by side. The difference is the margin, and it is stated, not hidden in a rate.
+10%
The upstream's published price plus 10%. That is the whole margin, on every world.
The same for every account. No fee to add credit: what you send is what you are credited. It is not cheaper than buying direct and does not pretend to be: it is the upstream's price plus this, for one key, one wire and every world.
- 464
- 458
- 65
- Arcee AI: Trinity Large Thinkingarcee-ai/trinity-large-thinkingtools262k contextIn / 1M$0.275up $0.25Out / 1M$0.88up $0.8Margin+10%1st tokenunmeasured
- Qwen: Qwen-Plusqwen/qwen-plustoolsjson1M contextIn / 1M$0.286up $0.26Out / 1M$0.858up $0.78Margin+10%1st tokenunmeasured
- Qwen: Qwen Plus 0728qwen/qwen-plus-2025-07-28toolsjson1M contextIn / 1M$0.286up $0.26Out / 1M$0.858up $0.78Margin+10%1st tokenunmeasured
- Qwen: Qwen3 Coder Flashqwen/qwen3-coder-flashtoolsjson1M contextIn / 1M$0.2145up $0.195Out / 1M$1.073up $0.975Margin+10%1st tokenunmeasured
- TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12bjson1M contextIn / 1M$0.44up $0.4Out / 1M$0.44up $0.4Margin+10%1st tokenunmeasured
- Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinkingtoolsjson262k contextIn / 1M$0.165up $0.15Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- Qwen: Qwen3.6 Flashqwen/qwen3.6-flashvisiontoolsjson1M contextIn / 1M$0.2062up $0.1875Out / 1M$1.238up $1.125Margin+10%1st tokenunmeasured
- Google: Gemini 2.5 Flash (batch)google/gemini-2.5-flash:batchvisiontoolsjson1M contextIn / 1M$0.165up $0.15Out / 1M$1.375up $1.25Margin+10%1st tokenunmeasured
- Google: Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batchvisiontoolsjson1M contextIn / 1M$0.165up $0.15Out / 1M$1.375up $1.25Margin+10%1st tokenunmeasured
- MiniMax: MiniMax-01minimax/minimax-01vision1M contextIn / 1M$0.22up $0.2Out / 1M$1.21up $1.10Margin+10%1st tokenunmeasured
- StepFun: Step 3.7 Flashstepfun/step-3.7-flashvisiontoolsjson262k contextIn / 1M$0.22up $0.2Out / 1M$1.265up $1.15Margin+10%1st tokenunmeasured
- Mistral: Codestral 2508mistralai/codestral-2508toolsjson256k contextIn / 1M$0.33up $0.3Out / 1M$0.99up $0.9Margin+10%1st tokenunmeasured
- OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-lunavisiontoolsjson1.1M contextIn / 1M$0.22up $0.2Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-provisiontoolsjson1.1M contextIn / 1M$0.22up $0.2Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nanovisiontoolsjson400k contextIn / 1M$0.22up $0.2Out / 1M$1.375up $1.25Margin+10%1st tokenunmeasured
- MiniMax: MiniMax M2.5minimax/minimax-m2.5toolsjson205k contextIn / 1M$0.297up $0.27Out / 1M$1.188up $1.08Margin+10%1st tokenunmeasured
- Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-codertoolsjson262k contextIn / 1M$0.33up $0.3Out / 1M$1.10up $1.00Margin+10%1st tokenunmeasured
- DeepSeek: DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashvisiontoolsjson1M contextIn / 1M$0.33up $0.3Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- Meituan: LongCat 2.0meituan/longcat-2.0tools1M contextIn / 1M$0.33up $0.3Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- MiniMax: MiniMax M2minimax/minimax-m2toolsjson205k contextIn / 1M$0.33up $0.3Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- MiniMax: MiniMax M2.1minimax/minimax-m2.1toolsjson205k contextIn / 1M$0.33up $0.3Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- MiniMax: MiniMax M3minimax/minimax-m3visiontoolsjson1M contextIn / 1M$0.33up $0.3Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- Qwen: Qwen3.5-27Bqwen/qwen3.5-27bvisiontoolsjson262k contextIn / 1M$0.2145up $0.195Out / 1M$1.716up $1.56Margin+10%1st tokenunmeasured
- Xiaomi: MiMo-V2.5-Proxiaomi/mimo-v2.5-protoolsjson1.1M contextIn / 1M$0.4785up $0.435Out / 1M$0.957up $0.87Margin+10%1st tokenunmeasured
- Xiaomi: MiMo-V2.6-Proxiaomi/mimo-v2.6-provisiontoolsjson1.1M contextIn / 1M$0.4785up $0.435Out / 1M$0.957up $0.87Margin+10%1st tokenunmeasured
- Qwen: Qwen3.7 Plusqwen/qwen3.7-plusvisiontoolsjson1M contextIn / 1M$0.352up $0.32Out / 1M$1.408up $1.28Margin+10%1st tokenunmeasured
- Google: Gemini 3 Flash Preview (batch)google/gemini-3-flash-preview:batchvisiontoolsjson1M contextIn / 1M$0.275up $0.25Out / 1M$1.65up $1.50Margin+10%1st tokenunmeasured
- Google: Gemini 3.1 Flash Litegoogle/gemini-3.1-flash-litevisiontoolsjson1M contextIn / 1M$0.275up $0.25Out / 1M$1.65up $1.50Margin+10%1st tokenunmeasured
- Google: Gemini 3.1 Flash Lite Previewgoogle/gemini-3.1-flash-lite-previewvisiontoolsjson1M contextIn / 1M$0.275up $0.25Out / 1M$1.65up $1.50Margin+10%1st tokenunmeasured
- Qwen: Qwen3.5 Plus 2026-02-15qwen/qwen3.5-plus-02-15visiontoolsjson1M contextIn / 1M$0.286up $0.26Out / 1M$1.716up $1.56Margin+10%1st tokenunmeasured
- Z.ai: GLM 5.3 FlashXz-ai/glm-5.3-flashxvisiontoolsjson1M contextIn / 1M$0.407up $0.37Out / 1M$1.375up $1.25Margin+10%1st tokenunmeasured
- Qwen: Qwen3 VL 235B A22B Instructqwen/qwen3-vl-235b-a22b-instructvisiontoolsjson262k contextIn / 1M$0.231up $0.21Out / 1M$2.09up $1.90Margin+10%1st tokenunmeasured
- Thinking Machines: Inkling Smallthinkingmachines/inkling-smallvisiontools524k contextIn / 1M$0.495up $0.45Out / 1M$1.32up $1.20Margin+10%1st tokenunmeasured
- Qwen: Qwen3.5 Plus 2026-04-20qwen/qwen3.5-plus-20260420visiontoolsjson1M contextIn / 1M$0.33up $0.3Out / 1M$1.98up $1.80Margin+10%1st tokenunmeasured
- ByteDance Seed: Seed 1.6bytedance-seed/seed-1.6visiontoolsjson262k contextIn / 1M$0.275up $0.25Out / 1M$2.20up $2.00Margin+10%1st tokenunmeasured
- ByteDance Seed: Seed-2.0-Litebytedance-seed/seed-2.0-litevisiontoolsjson262k contextIn / 1M$0.275up $0.25Out / 1M$2.20up $2.00Margin+10%1st tokenunmeasured
- OpenAI: GPT-5 Miniopenai/gpt-5-minivisiontoolsjson400k contextIn / 1M$0.275up $0.25Out / 1M$2.20up $2.00Margin+10%1st tokenunmeasured
- OpenAI: GPT-5.1-Codex-Miniopenai/gpt-5.1-codex-minivisiontoolsjson400k contextIn / 1M$0.275up $0.25Out / 1M$2.20up $2.00Margin+10%1st tokenunmeasured
- OpenAI: GPT-4.1 Miniopenai/gpt-4.1-minivisiontoolsjson1M contextIn / 1M$0.44up $0.4Out / 1M$1.76up $1.60Margin+10%1st token803 ms
- Qwen: Qwen3.5-122B-A10Bqwen/qwen3.5-122b-a10bvisiontoolsjson262k contextIn / 1M$0.286up $0.26Out / 1M$2.288up $2.08Margin+10%1st tokenunmeasured
“up” is the upstream's published rate, read from its catalog. A tag with a tick was measured working by a probe on this deployment; one without is the upstream's own word. First token is the median measured here over the last week, from real traffic and probes. Prices follow the upstream: when it changes a rate, this list and the bill change with it.
Calculator
What a request costs
The three cheapest worlds in the list as it is filtered now. Add up to four of your own with Compare. Computed with the same function the gateway bills with. Token counts are yours to set; the tasks are round numbers to start from.
| World | Antimatter | Upstream | Margin |
|---|---|---|---|
| inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl | $0.0514 | $0.0468 | $0.004676 |
| inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flash | $0.0520 | $0.0473 | $0.004725 |
| Nex AGI: Nex-N2.5-Mininex-agi/nex-n2.5-mini | $0.0715 | $0.0650 | $0.006500 |
A thousand requests of 1,200 tokens in and 350 out. A cached prompt token costs less where the upstream publishes a cache rate.
By need
The cheapest world for a need
The worlds that read images, hold a long context, call tools or return JSON, ranked by what a typical message costs at these prices.
Autopilot
Let the router choose
An autopilot id picks a world per request and is billed at that world's price from this list, with the same margin. The answer names the world in x-antimatter-model.
antimatter/autoBalanced: price, measured speed and measured quality, scored together.antimatter/auto:cheapThe lowest blended price in the catalog.antimatter/auto:fastThe lowest measured time to first token.antimatter/auto:codeTool calls measured working and a context sized for code.antimatter/auto:longA long context window, from the catalog.antimatter/auto:visionA world that takes images as input.antimatter/auto:toolsA world whose tool calls were measured working.antimatter/auto:jsonA world whose structured output was measured holding.