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

41 to 80 of 397 worlds (of 464)

OpenAI: GPT-4o-mini (batch)openai/gpt-4o-mini:batchvisiontoolsjson128k context
Context 128k
In / 1M$0.0825up $0.075
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
OpenAI: gpt-oss-safeguard-20bopenai/gpt-oss-safeguard-20btoolsjson131k context
Context 131k
In / 1M$0.0825up $0.075
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
Mistral: Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instructvisiontoolsjson256k context
Context 256k
In / 1M$0.1031up $0.09375
Out / 1M$0.275up $0.25
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5 Nanoopenai/gpt-5-nanovisiontoolsjson400k context
Context 400k
In / 1M$0.055up $0.05
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-itvisiontoolsjson262k context
Context 262k
In / 1M$0.099up $0.09
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
Z.ai: GLM 4.7 Flashz-ai/glm-4.7-flashtoolsjson200k context
Context 200k
In / 1M$0.06655up $0.0605
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
Meta: Llama 4 Scoutmeta-llama/llama-4-scoutvisiontoolsjson1.3M context
Context 1.3M
In / 1M$0.11up $0.1
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
Mistral: Ministral 3 8B 2512mistralai/ministral-8b-2512visiontoolsjson262k context
Context 262k
In / 1M$0.165up $0.15
Out / 1M$0.165up $0.15
Margin+10%
1st tokenunmeasured
Mistral: Voxtral Small 24B 2507mistralai/voxtral-small-24b-2507toolsjson33k context
Context 33k
In / 1M$0.11up $0.1
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 14Bqwen/qwen3-14btoolsjson131k context
Context 131k
In / 1M$0.132up $0.12
Out / 1M$0.264up $0.24
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507toolsjson262k context
Context 262k
In / 1M$0.11up $0.1
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
StepFun: Step 3.5 Flashstepfun/step-3.5-flashtools262k context
Context 262k
In / 1M$0.11up $0.1
Out / 1M$0.33up $0.3
Margin+10%
1st tokenunmeasured
Google: Gemma 4 31Bgoogle/gemma-4-31b-itvisiontoolsjson262k context
Context 262k
In / 1M$0.099up $0.09
Out / 1M$0.374up $0.34
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507toolsjson262k context
Context 262k
In / 1M$0.09625up $0.0875
Out / 1M$0.385up $0.35
Margin+10%
1st tokenunmeasured
Meta: Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructtoolsjson131k context
Context 131k
In / 1M$0.11up $0.1
Out / 1M$0.352up $0.32
Margin+10%
1st tokenunmeasured
Upstage: Solar Pro 4upstage/solar-pro4toolsjson524k context
Context 524k
In / 1M$0.099up $0.09
Out / 1M$0.396up $0.36
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek V4.1 Flash (batch)deepseek/deepseek-v4.1-flash:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.1232up $0.112
Out / 1M$0.3696up $0.336
Margin+10%
1st tokenunmeasured
Google: Gemma 3 27Bgoogle/gemma-3-27b-itvisiontoolsjson131k context
Context 131k
In / 1M$0.088up $0.08
Out / 1M$0.495up $0.45
Margin+10%
1st tokenunmeasured
NVIDIA: Nemotron 3 Supernvidia/nemotron-3-super-120b-a12btoolsjson262k context
Context 262k
In / 1M$0.088up $0.08
Out / 1M$0.495up $0.45
Margin+10%
1st tokenunmeasured
ByteDance Seed: Seed-2.0-Minibytedance-seed/seed-2.0-minivisiontoolsjson262k context
Context 262k
In / 1M$0.11up $0.1
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
Google: Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-litevisiontoolsjson1M context
Context 1M
In / 1M$0.11up $0.1
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
OpenAI: GPT-4.1 Nanoopenai/gpt-4.1-nanovisiontoolsjson1M context
Context 1M
In / 1M$0.11up $0.1
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
Xiaomi: MiMo-V2.5xiaomi/mimo-v2.5visiontoolsjson1.1M context
Context 1.1M
In / 1M$0.154up $0.14
Out / 1M$0.308up $0.28
Margin+10%
1st tokenunmeasured
Xiaomi: MiMo-V2.6-Flashxiaomi/mimo-v2.6-flashvisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.154up $0.14
Out / 1M$0.308up $0.28
Margin+10%
1st tokenunmeasured
PrismML: Ternary Bonsai 2 27Bprism-ml/ternary-bonsai-2-27bvisiontoolsjson262k context
Context 262k
In / 1M$0.0825up $0.075
Out / 1M$0.55up $0.5
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 VL 32B Instructqwen/qwen3-vl-32b-instructvisiontoolsjson131k context
Context 131k
In / 1M$0.1144up $0.104
Out / 1M$0.4576up $0.416
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek Pro Latest~deepseek/deepseek-pro-latesttoolsjson1M context
Context 1M
In / 1M$0.1452up $0.132
Out / 1M$0.4356up $0.396
Margin+10%
1st tokenunmeasured
Mistral: Ministral 3 14B 2512mistralai/ministral-14b-2512visiontoolsjson262k context
Context 262k
In / 1M$0.22up $0.2
Out / 1M$0.22up $0.2
Margin+10%
1st tokenunmeasured
OpenAI: GPT Luna Latest~openai/gpt-luna-latestvisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.11up $0.1
Out / 1M$0.55up $0.5
Margin+10%
1st tokenunmeasured
OpenAI: GPT-6 Lunaopenai/gpt-6-lunavisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.11up $0.1
Out / 1M$0.55up $0.5
Margin+10%
1st tokenunmeasured
OpenAI: GPT-6 Luna Proopenai/gpt-6-luna-provisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.11up $0.1
Out / 1M$0.55up $0.5
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 8Bqwen/qwen3-8btoolsjson131k context
Context 131k
In / 1M$0.1287up $0.117
Out / 1M$0.5005up $0.455
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 VL 8B Instructqwen/qwen3-vl-8b-instructvisiontoolsjson262k context
Context 262k
In / 1M$0.1287up $0.117
Out / 1M$0.5005up $0.455
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 30B A3Bqwen/qwen3-30b-a3btoolsjson131k context
Context 131k
In / 1M$0.132up $0.12
Out / 1M$0.55up $0.5
Margin+10%
1st tokenunmeasured
Mistral: Codestral 2508 (batch)mistralai/codestral-2508:batchtoolsjson256k context
Context 256k
In / 1M$0.165up $0.15
Out / 1M$0.495up $0.45
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5.6 Luna Pro (batch)openai/gpt-5.6-luna-pro:batchvisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.11up $0.1
Out / 1M$0.66up $0.6
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5.6 Luna (batch)openai/gpt-5.6-luna:batchvisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.11up $0.1
Out / 1M$0.66up $0.6
Margin+10%
1st tokenunmeasured
Qwen: Qwen3.8 Flashqwen/qwen3.8-flashvisiontoolsjson1M context
Context 1M
In / 1M$0.165up $0.15
Out / 1M$0.517up $0.47
Margin+10%
1st tokenunmeasured
Qwen: Qwen3.8 Omni Flashqwen/qwen3.8-omni-flashvisiontoolsjson1M context
Context 1M
In / 1M$0.165up $0.15
Out / 1M$0.517up $0.47
Margin+10%
1st tokenunmeasured
Tencent: Hy3tencent/hy3toolsjson262k context
Context 262k
In / 1M$0.1452up $0.132
Out / 1M$0.5808up $0.528
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.

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.