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.

margin over upstream

+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.

worlds: 464
priced: 458
makers: 65

1 to 40 of 464 worlds

Mistral: Mistral Nemomistralai/mistral-nemotoolsjson131k context
Context 131k
In / 1M$0.0209up $0.019
Out / 1M$0.033up $0.03
Margin+10%
1st token361 ms
inclusionAI: Ling 3.0 Flash VLinclusionai/ling-3.0-flash-vlvisiontoolsjson262k context
Context 262k
In / 1M$0.0231up $0.021
Out / 1M$0.06776up $0.0616
Margin+10%
1st tokenunmeasured
inclusionAI: Ling 3.0 Flashinclusionai/ling-3.0-flashtoolsjson262k context
Context 262k
In / 1M$0.0231up $0.021
Out / 1M$0.0693up $0.063
Margin+10%
1st tokenunmeasured
OpenAI: gpt-oss-20bopenai/gpt-oss-20btools ✓json ✓131k context
Context 131k
In / 1M$0.0198up $0.018
Out / 1M$0.099up $0.09
Margin+10%
1st token397 ms
IBM: Granite 4.0 Microibm-granite/granite-4.0-h-microjson131k context
Context 131k
In / 1M$0.0187up $0.017
Out / 1M$0.1232up $0.112
Margin+10%
1st tokenunmeasured
Sao10K: Llama 3 8B Lunarissao10k/l3-lunaris-8bjson8k context
Context 8k
In / 1M$0.044up $0.04
Out / 1M$0.055up $0.05
Margin+10%
1st tokenunmeasured
Nex AGI: Nex-N2.5-Mininex-agi/nex-n2.5-minivisionjson262k context
Context 262k
In / 1M$0.0275up $0.025
Out / 1M$0.11up $0.1
Margin+10%
1st tokenunmeasured
OpenAI: gpt-oss-20b (batch)openai/gpt-oss-20b:batchtoolsjson131k context
Context 131k
In / 1M$0.0264up $0.024
Out / 1M$0.1232up $0.112
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek V4 Flash 0423deepseek/deepseek-v4-flashtoolsjson1M context
Context 1M
In / 1M$0.0462up $0.042
Out / 1M$0.0924up $0.084
Margin+10%
1st token10.4 s
Qwen: Qwen3.7 Flashqwen/qwen3.7-flashvisiontoolsjson1M context
Context 1M
In / 1M$0.033up $0.03
Out / 1M$0.143up $0.13
Margin+10%
1st token563 ms
OpenAI: gpt-oss-120b (batch)openai/gpt-oss-120b:batchtoolsjson131k context
Context 131k
In / 1M$0.03256up $0.0296
Out / 1M$0.1496up $0.136
Margin+10%
1st tokenunmeasured
Meta: Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instructtoolsjson131k context
Context 131k
In / 1M$0.055up $0.05
Out / 1M$0.088up $0.08
Margin+10%
1st tokenunmeasured
Mistral: Mistral Small 3mistralai/mistral-small-24b-instruct-2501json33k context
Context 33k
In / 1M$0.055up $0.05
Out / 1M$0.088up $0.08
Margin+10%
1st tokenunmeasured
Inference.net: Schematron V2 Turboinference-net/schematron-v2-turbojson128k context
Context 128k
In / 1M$0.033up $0.03
Out / 1M$0.165up $0.15
Margin+10%
1st tokenunmeasured
Amazon: Nova Micro 1.0amazon/nova-micro-v1tools128k context
Context 128k
In / 1M$0.0385up $0.035
Out / 1M$0.154up $0.14
Margin+10%
1st tokenunmeasured
Google: Gemma 3 4Bgoogle/gemma-3-4b-itvisionjson131k context
Context 131k
In / 1M$0.055up $0.05
Out / 1M$0.11up $0.1
Margin+10%
1st tokenunmeasured
Cohere: Command R7B (12-2024)cohere/command-r7b-12-2024json128k context
Context 128k
In / 1M$0.04125up $0.0375
Out / 1M$0.165up $0.15
Margin+10%
1st tokenunmeasured
Inception: Mercury 2.5inception/mercury-2.5toolsjson260k context
Context 260k
In / 1M$0.044up $0.04
Out / 1M$0.165up $0.15
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5 Nano (batch)openai/gpt-5-nano:batchvisiontoolsjson400k context
Context 400k
In / 1M$0.0275up $0.025
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
OpenAI: gpt-oss-120bopenai/gpt-oss-120btoolsjson131k context
Context 131k
In / 1M$0.0407up $0.037
Out / 1M$0.187up $0.17
Margin+10%
1st tokenunmeasured
Meta: Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct60k context
Context 60k
In / 1M$0.0297up $0.027
Out / 1M$0.2211up $0.201
Margin+10%
1st tokenunmeasured
Google: Gemma 3 12Bgoogle/gemma-3-12b-itvisiontoolsjson131k context
Context 131k
In / 1M$0.055up $0.05
Out / 1M$0.165up $0.15
Margin+10%
1st tokenunmeasured
Mistral: Ministral 3 8B 2512 (batch)mistralai/ministral-8b-2512:batchvisiontoolsjson262k context
Context 262k
In / 1M$0.0825up $0.075
Out / 1M$0.0825up $0.075
Margin+10%
1st tokenunmeasured
Poolside: Laguna XS 2.1poolside/laguna-xs-2.1tools262k context
Context 262k
In / 1M$0.066up $0.06
Out / 1M$0.132up $0.12
Margin+10%
1st tokenunmeasured
Tencent: Hy-MT2-1.8Btencent/hy-mt2-1.8b8k context
Context 8k
In / 1M$0.0484up $0.044
Out / 1M$0.1947up $0.177
Margin+10%
1st tokenunmeasured
NVIDIA: Nemotron 3.5 Lightningnvidia/nemotron-3.5-lightningtoolsjson262k context
Context 262k
In / 1M$0.066up $0.06
Out / 1M$0.176up $0.16
Margin+10%
1st tokenunmeasured
Google: Gemini 2.5 Flash Lite (batch)google/gemini-2.5-flash-lite:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.055up $0.05
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
MythoMax 13Bgryphe/mythomax-l2-13bjson8k context
Context 8k
In / 1M$0.088up $0.08
Out / 1M$0.121up $0.11
Margin+10%
1st tokenunmeasured
Microsoft: Phi 4microsoft/phi-4json16k context
Context 16k
In / 1M$0.077up $0.07
Out / 1M$0.154up $0.14
Margin+10%
1st tokenunmeasured
NVIDIA: Nemotron 3 Nano 30B A3Bnvidia/nemotron-3-nano-30b-a3btoolsjson262k context
Context 262k
In / 1M$0.055up $0.05
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
OpenAI: GPT-4.1 Nano (batch)openai/gpt-4.1-nano:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.055up $0.05
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
Upstage: Solar Mini 4upstage/solar-mini4toolsjson524k context
Context 524k
In / 1M$0.055up $0.05
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
inclusionAI: Ling 3.0 Flash Fininclusionai/ling-3.0-flash-fintoolsjson262k context
Context 262k
In / 1M$0.066up $0.06
Out / 1M$0.198up $0.18
Margin+10%
1st tokenunmeasured
Inference.net: Schematron V2 Smallinference-net/schematron-v2-smalljson128k context
Context 128k
In / 1M$0.055up $0.05
Out / 1M$0.253up $0.23
Margin+10%
1st tokenunmeasured
Z.ai: GLM 5.3 Flash (batch)z-ai/glm-5.3-flash:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.066up $0.06
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
Mistral: Ministral 3 3B 2512mistralai/ministral-3b-2512visiontoolsjson131k context
Context 131k
In / 1M$0.11up $0.1
Out / 1M$0.11up $0.1
Margin+10%
1st tokenunmeasured
Reka Edgerekaai/reka-edgevisiontoolsjson16k context
Context 16k
In / 1M$0.11up $0.1
Out / 1M$0.11up $0.1
Margin+10%
1st tokenunmeasured
OpenAI: GPT-6 Luna Pro (batch)openai/gpt-6-luna-pro:batchvisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.055up $0.05
Out / 1M$0.275up $0.25
Margin+10%
1st tokenunmeasured
OpenAI: GPT-6 Luna (batch)openai/gpt-6-luna:batchvisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.055up $0.05
Out / 1M$0.275up $0.25
Margin+10%
1st tokenunmeasured
Amazon: Nova Lite 1.0amazon/nova-lite-v1visiontools300k context
Context 300k
In / 1M$0.066up $0.06
Out / 1M$0.264up $0.24
Margin+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.

tokens intokens out

how many

What a thousand of 1200 tokens in and 350 tokens out costs on each world
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.