Pricing
Every model, priced in the open
You pay the provider's published price plus 10%. That is the whole margin, on every model.
| Model | Price per 1M | Input per 1M | Output per 1M | Last 90 days | Context | Margin | Speed |
|---|---|---|---|---|---|---|---|
| Aion 3.5aion-labs/aion-3.5 | $3.30 in$6.60 out | $3.30list $3.00 | $6.60list $6.00 | no history yet | 262k | +10%$0.60 out | unmeasured |
| Solar Mini 4upstage/solar-mini4 | $0.055 in$0.22 out | $0.055list $0.05 | $0.22list $0.20 | no history yet | 524k | +10%$0.02 out | unmeasured |
| Command A+cohere/command-a-plus | $0.33 in$1.65 out | $0.33list $0.30 | $1.65list $1.50 | no history yet | 192k | +10%$0.15 out | unmeasured |
| MiMo-V2.6-Pro-UltraSpeedxiaomi/mimo-v2.6-pro-ultraspeed | $4.785 in$9.57 out | $4.785list $4.35 | $9.57list $8.70 | no history yet | 1M | +10%$0.87 out | unmeasured |
| MiMo-V2.6-Flashxiaomi/mimo-v2.6-flash | $0.154 in$0.308 out | $0.154list $0.14 | $0.308list $0.28 | no history yet | 1M | +10%$0.028 out | unmeasured |
| MiMo-V2.6-Proxiaomi/mimo-v2.6-pro | $0.4785 in$0.957 out | $0.4785list $0.435 | $0.957list $0.87 | no history yet | 1M | +10%$0.087 out | unmeasured |
| Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27b | $0.0825 in$0.55 out | $0.0825list $0.075 | $0.55list $0.50 | no history yet | 262k | +10%$0.05 out | unmeasured |
| Schematron V2 Turboinference-net/schematron-v2-turbo | $0.033 in$0.165 out | $0.033list $0.03 | $0.165list $0.15 | no history yet | 128k | +10%$0.015 out | unmeasured |
| Schematron V2 Smallinference-net/schematron-v2-small | $0.055 in$0.253 out | $0.055list $0.05 | $0.253list $0.23 | no history yet | 128k | +10%$0.023 out | unmeasured |
| Fugu Ultra v2sakana/fugu-ultra-v2 | $5.50 in$33.00 out | $5.50list $5.00 | $33.00list $30.00 | no history yet | 1M | +10%$3.00 out | unmeasured |
| Fugu Maxsakana/fugu-max | $2.20 in$6.60 out | $2.20list $2.00 | $6.60list $6.00 | no history yet | 1M | +10%$0.60 out | unmeasured |
| Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vl | $0.066 in$0.198 out | $0.066list $0.06 | $0.198list $0.18 | no history yet | 131k | +10%$0.018 out | unmeasured |
| Nex-N2.5-Mininex-agi/nex-n2.5-mini | $0.0275 in$0.11 out | $0.0275list $0.025 | $0.11list $0.10 | no history yet | 262k | +10%$0.01 out | unmeasured |
| Nex-N2.5-Pronex-agi/nex-n2.5-pro | $0.0825 in$0.275 out | $0.0825list $0.075 | $0.275list $0.25 | no history yet | 262k | +10%$0.025 out | unmeasured |
| Muse Spark 1.3meta/muse-spark-1.3 | $1.375 in$4.675 out | $1.375list $1.25 | $4.675list $4.25 | no history yet | 1M | +10%$0.425 out | unmeasured |
| Granite 4.2 8Bibm-granite/granite-4.2-8b | $0.066 in$0.165 out | $0.066list $0.06 | $0.165list $0.15 | no history yet | 131k | +10%$0.015 out | unmeasured |
| Hy4 previewtencent/hy4-preview | $0.82566 in$2.47599 out | $0.82566list $0.7506 | $2.47599list $2.2509 | no history yet | 1M | +10%$0.22509 out | unmeasured |
| Hy-MT2-1.8Btencent/hy-mt2-1.8b | $0.0484 in$0.1947 out | $0.0484list $0.044 | $0.1947list $0.177 | no history yet | 8k | +10%$0.0177 out | unmeasured |
| Hy-MT2-30B-A3Btencent/hy-mt2-30b-a3b | $0.0814 in$0.3245 out | $0.0814list $0.074 | $0.3245list $0.295 | no history yet | 8k | +10%$0.0295 out | unmeasured |
| Hy-MT2-7Btencent/hy-mt2-7b | $0.0814 in$0.3245 out | $0.0814list $0.074 | $0.3245list $0.295 | no history yet | 8k | +10%$0.0295 out | unmeasured |
| Seed 2.1 Turbobytedance-seed/seed-2-1-turbo | $0.55 in$2.75 out | $0.55list $0.50 | $2.75list $2.50 | no history yet | 262k | +10%$0.25 out | unmeasured |
| Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningAlso:free | $0.077 in$0.22 out | $0.077list $0.07 | $0.22list $0.20 | no history yet | 262k | +10%$0.02 out | unmeasured |
| Solar Pro 4upstage/solar-pro4 | $0.165 in$0.66 out | $0.165list $0.15 | $0.66list $0.60 | no history yet | 524k | +10%$0.06 out | unmeasured |
| Muse Glimmer 30Bmeta/muse-glimmer-30bAlso:batch | $0.33 in$1.32 out | $0.33list $0.30 | $1.32list $1.20 | no history yet | 131k | +10%$0.12 out | unmeasured |
| Ling 3.0 Tinyinclusionai/ling-3.0-tiny | $0.0165 in$0.0495 out | $0.0165list $0.015 | $0.0495list $0.045 | no history yet | 262k | +10%$0.0045 out | unmeasured |
| Muse Spark 1.2meta/muse-spark-1.2 | $1.375 in$4.675 out | $1.375list $1.25 | $4.675list $4.25 | no history yet | 1M | +10%$0.425 out | unmeasured |
| Inkling Smallthinkingmachines/inkling-smallAlso:batch | $0.495 in$1.32 out | $0.495list $0.45 | $1.32list $1.20 | no history yet | 524k | +10%$0.12 out | unmeasured |
| Ling 3.0 Flashinclusionai/ling-3.0-flash | $0.0231 in$0.0693 out | $0.0231list $0.021 | $0.0693list $0.063 | no history yet | 262k | +10%$0.0063 out | unmeasured |
| LongCat 2.0meituan/longcat-2.0 | $0.33 in$1.32 out | $0.33list $0.30 | $1.32list $1.20 | no history yet | 1M | +10%$0.12 out | unmeasured |
| Inklingthinkingmachines/inkling | $1.10 in$4.455 out | $1.10list $1.00 | $4.455list $4.05 | no history yet | 524k | +10%$0.405 out | unmeasured |
| Muse Spark 1.1meta/muse-spark-1.1 | $1.375 in$4.675 out | $1.375list $1.25 | $4.675list $4.25 | no history yet | 1M | +10%$0.425 out | unmeasured |
| Aion-3.0-Miniaion-labs/aion-3.0-mini | $0.77 in$1.54 out | $0.77list $0.70 | $1.54list $1.40 | no history yet | 131k | +10%$0.14 out | unmeasured |
| Aion-3.0aion-labs/aion-3.0 | $3.30 in$6.60 out | $3.30list $3.00 | $6.60list $6.00 | no history yet | 131k | +10%$0.60 out | unmeasured |
| Hy3tencent/hy3 | $0.09075 in$0.363 out | $0.09075list $0.0825 | $0.363list $0.33 | no history yet | 262k | +10%$0.033 out | unmeasured |
| Fugu Ultrasakana/fugu-ultra | $5.50 in$33.00 out | $5.50list $5.00 | $33.00list $30.00 | no history yet | 1M | +10%$3.00 out | unmeasured |
| Nemotron 3.5 Content Safetynvidia/nemotron-3.5-content-safety | $0.22 in$0.22 out | $0.22list $0.20 | $0.22list $0.20 | no history yet | 131k | +10%$0.02 out | unmeasured |
| Nemotron 3 Ultranvidia/nemotron-3-ultra-550b-a55bAlso:free | $0.66 in$2.64 out | $0.66list $0.60 | $2.64list $2.40 | no history yet | 262k | +10%$0.24 out | unmeasured |
| MiniMax M3minimax/minimax-m3Also:batch | $0.33 in$1.32 out | $0.33list $0.30 | $1.32list $1.20 | no history yet | 1M | +10%$0.12 out | unmeasured |
| Step 3.7 Flashstepfun/step-3.7-flash | $0.22 in$1.265 out | $0.22list $0.20 | $1.265list $1.15 | no history yet | 262k | +10%$0.115 out | unmeasured |
| Perceptron Mk1perceptron/perceptron-mk1 | $0.165 in$1.65 out | $0.165list $0.15 | $1.65list $1.50 | no history yet | 32k | +10%$0.15 out | unmeasured |
“list” is the provider's published rate, read from its catalog. A tag with a tick was measured working by a probe here. One without is the provider's own claim. First token is the median measured here over the last week, from real traffic and probes. Prices follow the provider. When it changes a rate, this list and your bill change with it.
Calculator
Cost of a request
The three cheapest models in the list as filtered now. Add up to four of your own with Compare. This uses the same function the gateway bills with. You set the token counts, and the tasks are round numbers to start from.
| Model | Antimatter | Provider | Margin |
|---|---|---|---|
| Ling 3.0 Tinyinclusionai/ling-3.0-tiny | $0.0371 | $0.0338 | $0.00338 |
| Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct | $0.0418 | $0.038 | $0.0038 |
| Mistral Nemomistralai/mistral-nemo | $0.0498 | $0.0453 | $0.00453 |
A thousand requests of 1,200 tokens in and 350 out. A cached prompt token costs less where the provider publishes a cache rate.
The margin
+10%
You pay the provider's published price plus 10%. That is the whole margin, on every model.
It is the same for every account. There is no fee to add credit, so what you send is what you are credited. This is not cheaper than buying direct. You pay the provider's price plus this margin for one key, one API and every model.
- 336
- 333
- 60
Autopilot
Let Autopilot choose
An Autopilot id picks a model for each request. It is billed at that model's price from this list, with the same margin. The answer names the model in x-antimatter-model.
antimatter/autoBalances price, measured speed and measured quality.antimatter/auto:cheapThe lowest blended price in the catalog.antimatter/auto:fastThe lowest measured time to first token.antimatter/auto:codeModels whose code passed the gateway's own tests, with enough context for code.antimatter/auto:extractModels measured pulling fields out of text exactly.antimatter/auto:reasonModels measured solving short puzzles correctly.antimatter/auto:longA long context window, from the catalog.antimatter/auto:visionA model that takes images as input.antimatter/auto:toolsA model whose tool calls were measured working.antimatter/auto:jsonA model whose structured output was measured working.
Start with a key
A key is free to create on the dashboard, and a new account's first requests are covered by a free allowance of $0.25. After that, requests are billed at the prices above.
Coming from OpenRouter? What changes and what stays the same.