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
- IBM: Granite 4.2 8Bibm-granite/granite-4.2-8btoolsjson131k contextIn / 1M$0.066up $0.06Out / 1M$0.275up $0.25Margin+10%1st tokenunmeasured
- Qwen: Qwen3.5-9Bqwen/qwen3.5-9bvisiontoolsjson262k contextIn / 1M$0.11up $0.1Out / 1M$0.165up $0.15Margin+10%1st tokenunmeasured
- Poolside: Laguna S 2.1poolside/laguna-s-2.1tools1M contextIn / 1M$0.099up $0.09Out / 1M$0.198up $0.18Margin+10%1st tokenunmeasured
- Qwen: Qwen3.5-Flashqwen/qwen3.5-flash-02-23visiontoolsjson1M contextIn / 1M$0.0715up $0.065Out / 1M$0.286up $0.26Margin+10%1st tokenunmeasured
- Nex AGI: Nex-N2.5-Pronex-agi/nex-n2.5-provisiontoolsjson262k contextIn / 1M$0.0825up $0.075Out / 1M$0.275up $0.25Margin+10%1st tokenunmeasured
- Meta: Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructjson131k contextIn / 1M$0.055up $0.05Out / 1M$0.363up $0.33Margin+10%1st tokenunmeasured
- Qwen: Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instructtoolsjson262k contextIn / 1M$0.077up $0.07Out / 1M$0.308up $0.28Margin+10%1st tokenunmeasured
- ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7bvisionjson128k contextIn / 1M$0.11up $0.1Out / 1M$0.22up $0.2Margin+10%1st tokenunmeasured
- Meta: Muse Spark 1.2 Contributormeta/muse-spark-1.2-contributorvisiontoolsjson1M contextIn / 1M$0.11up $0.1Out / 1M$0.22up $0.2Margin+10%1st tokenunmeasured
- Meta: Muse Spark 1.3 Contributormeta/muse-spark-1.3-contributorvisiontoolsjson1M contextIn / 1M$0.11up $0.1Out / 1M$0.22up $0.2Margin+10%1st tokenunmeasured
- Qwen: Qwen2.5 7B Instructqwen/qwen-2.5-7b-instructtoolsjson33k contextIn / 1M$0.11up $0.1Out / 1M$0.22up $0.2Margin+10%1st tokenunmeasured
- Reka Flash 3rekaai/reka-flash-3json66k contextIn / 1M$0.11up $0.1Out / 1M$0.22up $0.2Margin+10%1st tokenunmeasured
- Tencent: Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3bjson8k contextIn / 1M$0.0814up $0.074Out / 1M$0.3245up $0.295Margin+10%1st tokenunmeasured
- Tencent: Hy-MT2-7Btencent/hy-mt2-7bjson8k contextIn / 1M$0.0814up $0.074Out / 1M$0.3245up $0.295Margin+10%1st tokenunmeasured
- Qwen: Qwen3 32Bqwen/qwen3-32btoolsjson131k contextIn / 1M$0.088up $0.08Out / 1M$0.308up $0.28Margin+10%1st tokenunmeasured
- ByteDance Seed: Seed 1.6 Flashbytedance-seed/seed-1.6-flashvisiontoolsjson262k contextIn / 1M$0.0825up $0.075Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- Mistral: Mistral Small 4 (batch)mistralai/mistral-small-2603:batchvisiontoolsjson262k contextIn / 1M$0.0825up $0.075Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batchvisiontoolsjson128k contextIn / 1M$0.0825up $0.075Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20btoolsjson131k contextIn / 1M$0.0825up $0.075Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructvisiontoolsjson256k contextIn / 1M$0.1031up $0.09375Out / 1M$0.275up $0.25Margin+10%1st tokenunmeasured
- OpenAI: GPT-5 Nanoopenai/gpt-5-nanovisiontoolsjson400k contextIn / 1M$0.055up $0.05Out / 1M$0.44up $0.4Margin+10%1st tokenunmeasured
- Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-itvisiontoolsjson262k contextIn / 1M$0.099up $0.09Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flashtoolsjson200k contextIn / 1M$0.06655up $0.0605Out / 1M$0.44up $0.4Margin+10%1st tokenunmeasured
- Meta: Llama 4 Scoutmeta-llama/llama-4-scoutvisiontoolsjson1.3M contextIn / 1M$0.11up $0.1Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512visiontoolsjson262k contextIn / 1M$0.165up $0.15Out / 1M$0.165up $0.15Margin+10%1st tokenunmeasured
- Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507toolsjson33k contextIn / 1M$0.11up $0.1Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- Qwen: Qwen3 14Bqwen/qwen3-14btoolsjson131k contextIn / 1M$0.132up $0.12Out / 1M$0.264up $0.24Margin+10%1st tokenunmeasured
- Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507toolsjson262k contextIn / 1M$0.11up $0.1Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- StepFun: Step 3.5 Flashstepfun/step-3.5-flashtools262k contextIn / 1M$0.11up $0.1Out / 1M$0.33up $0.3Margin+10%1st tokenunmeasured
- Google: Gemma 4 31Bgoogle/gemma-4-31b-itvisiontoolsjson262k contextIn / 1M$0.099up $0.09Out / 1M$0.374up $0.34Margin+10%1st tokenunmeasured
- Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507toolsjson262k contextIn / 1M$0.09625up $0.0875Out / 1M$0.385up $0.35Margin+10%1st tokenunmeasured
- Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructtoolsjson131k contextIn / 1M$0.11up $0.1Out / 1M$0.352up $0.32Margin+10%1st tokenunmeasured
- Upstage: Solar Pro 4upstage/solar-pro4toolsjson524k contextIn / 1M$0.099up $0.09Out / 1M$0.396up $0.36Margin+10%1st tokenunmeasured
- DeepSeek: DeepSeek V4.1 Flash (batch)deepseek/deepseek-v4.1-flash:batchvisiontoolsjson1M contextIn / 1M$0.1232up $0.112Out / 1M$0.3696up $0.336Margin+10%1st tokenunmeasured
- Google: Gemma 3 27Bgoogle/gemma-3-27b-itvisiontoolsjson131k contextIn / 1M$0.088up $0.08Out / 1M$0.495up $0.45Margin+10%1st tokenunmeasured
- NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12btoolsjson262k contextIn / 1M$0.088up $0.08Out / 1M$0.495up $0.45Margin+10%1st tokenunmeasured
- ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-minivisiontoolsjson262k contextIn / 1M$0.11up $0.1Out / 1M$0.44up $0.4Margin+10%1st tokenunmeasured
- Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-litevisiontoolsjson1M contextIn / 1M$0.11up $0.1Out / 1M$0.44up $0.4Margin+10%1st tokenunmeasured
- OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nanovisiontoolsjson1M contextIn / 1M$0.11up $0.1Out / 1M$0.44up $0.4Margin+10%1st tokenunmeasured
- Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5visiontoolsjson1.1M contextIn / 1M$0.154up $0.14Out / 1M$0.308up $0.28Margin+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 |
|---|---|---|---|
| Mistral: Mistral Nemomistralai/mistral-nemo | $0.0366 | $0.0333 | $0.003330 |
| 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 |
A thousand requests of 1,200 tokens in and 350 out. A cached prompt token costs less where the upstream publishes a cache rate.
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.