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

121 to 160 of 464 worlds

DeepSeek: DeepSeek V4 Flash 0731deepseek/deepseek-v4-flash-0731toolsjson1M context
Context 1M
In / 1M$0.00847up $0.0077
Out / 1M$1.408up $1.28
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5 Mini (batch)openai/gpt-5-mini:batchvisiontoolsjson400k context
Context 400k
In / 1M$0.1375up $0.125
Out / 1M$1.10up $1.00
Margin+10%
1st tokenunmeasured
OpenAI: GPT-4.1 Mini (batch)openai/gpt-4.1-mini:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.22up $0.2
Out / 1M$0.88up $0.8
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instructtoolsjson262k context
Context 262k
In / 1M$0.11up $0.1
Out / 1M$1.21up $1.10
Margin+10%
1st tokenunmeasured
TheDrummer: Cydonia 24B V4.1thedrummer/cydonia-24b-v4.1json131k context
Context 131k
In / 1M$0.33up $0.3
Out / 1M$0.55up $0.5
Margin+10%
1st tokenunmeasured
Qwen: Qwen3.5-35B-A3Bqwen/qwen3.5-35b-a3bvisiontoolsjson262k context
Context 262k
In / 1M$0.165up $0.15
Out / 1M$1.10up $1.00
Margin+10%
1st tokenunmeasured
Qwen: Qwen3.6 35B A3Bqwen/qwen3.6-35b-a3bvisiontoolsjson262k context
Context 262k
In / 1M$0.165up $0.15
Out / 1M$1.10up $1.00
Margin+10%
1st tokenunmeasured
MiniMax: MiniMax M2.7minimax/minimax-m2.7toolsjson205k context
Context 205k
In / 1M$0.231up $0.21
Out / 1M$0.924up $0.84
Margin+10%
1st tokenunmeasured
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instructtoolsjson33k context
Context 33k
In / 1M$0.396up $0.36
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
Venice: Uncensoredcognitivecomputations/dolphin-mistral-24b-venice-editionjson128k context
Context 128k
In / 1M$0.22up $0.2
Out / 1M$0.99up $0.9
Margin+10%
1st tokenunmeasured
Inception: Mercury 2inception/mercury-2toolsjson128k context
Context 128k
In / 1M$0.275up $0.25
Out / 1M$0.825up $0.75
Margin+10%
1st tokenunmeasured
Mistral: Mistral Large 3 2512 (batch)mistralai/mistral-large-2512:batchvisiontoolsjson262k context
Context 262k
In / 1M$0.275up $0.25
Out / 1M$0.825up $0.75
Margin+10%
1st tokenunmeasured
OpenAI: GPT-3.5 Turbo (batch)openai/gpt-3.5-turbo:batchtoolsjson16k context
Context 16k
In / 1M$0.275up $0.25
Out / 1M$0.825up $0.75
Margin+10%
1st tokenunmeasured
Arcee AI: Trinity Large Thinkingarcee-ai/trinity-large-thinkingtools262k context
Context 262k
In / 1M$0.275up $0.25
Out / 1M$0.88up $0.8
Margin+10%
1st tokenunmeasured
Qwen: Qwen-Plusqwen/qwen-plustoolsjson1M context
Context 1M
In / 1M$0.286up $0.26
Out / 1M$0.858up $0.78
Margin+10%
1st tokenunmeasured
Qwen: Qwen Plus 0728qwen/qwen-plus-2025-07-28toolsjson1M context
Context 1M
In / 1M$0.286up $0.26
Out / 1M$0.858up $0.78
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 Coder Flashqwen/qwen3-coder-flashtoolsjson1M context
Context 1M
In / 1M$0.2145up $0.195
Out / 1M$1.073up $0.975
Margin+10%
1st tokenunmeasured
Meta: Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instructtoolsjson131k context
Context 131k
In / 1M$0.44up $0.4
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
TheDrummer: UnslopNemo 12Bthedrummer/unslopnemo-12bjson1M context
Context 1M
In / 1M$0.44up $0.4
Out / 1M$0.44up $0.4
Margin+10%
1st tokenunmeasured
Mistral: Mistral Medium 3.1 (batch)mistralai/mistral-medium-3.1:batchvisiontoolsjson131k context
Context 131k
In / 1M$0.22up $0.2
Out / 1M$1.10up $1.00
Margin+10%
1st tokenunmeasured
Mistral: Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructvisiontools128k context
Context 128k
In / 1M$0.3861up $0.351
Out / 1M$0.6105up $0.555
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek V4 Flash Latest~deepseek/deepseek-v4-flash-latesttoolsjson1M context
Context 1M
In / 1M$0.006352up $0.005775
Out / 1M$1.76up $1.60
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 Next 80B A3B Thinkingqwen/qwen3-next-80b-a3b-thinkingtoolsjson262k context
Context 262k
In / 1M$0.165up $0.15
Out / 1M$1.32up $1.20
Margin+10%
1st tokenunmeasured
Qwen: Qwen3.6 Flashqwen/qwen3.6-flashvisiontoolsjson1M context
Context 1M
In / 1M$0.2062up $0.1875
Out / 1M$1.238up $1.125
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek V3.1deepseek/deepseek-chat-v3.1toolsjson164k context
Context 164k
In / 1M$0.275up $0.25
Out / 1M$1.045up $0.95
Margin+10%
1st tokenunmeasured
Google: Gemini 2.5 Flash (batch)google/gemini-2.5-flash:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.165up $0.15
Out / 1M$1.375up $1.25
Margin+10%
1st tokenunmeasured
Google: Gemini 3.5 Flash Lite (batch)google/gemini-3.5-flash-lite:batchvisiontoolsjson1M context
Context 1M
In / 1M$0.165up $0.15
Out / 1M$1.375up $1.25
Margin+10%
1st tokenunmeasured
MiniMax: MiniMax-01minimax/minimax-01vision1M context
Context 1M
In / 1M$0.22up $0.2
Out / 1M$1.21up $1.10
Margin+10%
1st tokenunmeasured
ReMM SLERP 13Bundi95/remm-slerp-l2-13bjson6k context
Context 6k
In / 1M$0.385up $0.35
Out / 1M$0.715up $0.65
Margin+10%
1st tokenunmeasured
StepFun: Step 3.7 Flashstepfun/step-3.7-flashvisiontoolsjson262k context
Context 262k
In / 1M$0.22up $0.2
Out / 1M$1.265up $1.15
Margin+10%
1st tokenunmeasured
Mistral: Codestral 2508mistralai/codestral-2508toolsjson256k context
Context 256k
In / 1M$0.33up $0.3
Out / 1M$0.99up $0.9
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5.6 Lunaopenai/gpt-5.6-lunavisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.22up $0.2
Out / 1M$1.32up $1.20
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5.6 Luna Proopenai/gpt-5.6-luna-provisiontoolsjson1.1M context
Context 1.1M
In / 1M$0.22up $0.2
Out / 1M$1.32up $1.20
Margin+10%
1st tokenunmeasured
Z.ai: GLM 4.6Vz-ai/glm-4.6vvisiontoolsjson131k context
Context 131k
In / 1M$0.33up $0.3
Out / 1M$0.99up $0.9
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek V3deepseek/deepseek-chattoolsjson164k context
Context 164k
In / 1M$0.2831up $0.2574
Out / 1M$1.132up $1.029
Margin+10%
1st tokenunmeasured
OpenAI: GPT-5.4 Nanoopenai/gpt-5.4-nanovisiontoolsjson400k context
Context 400k
In / 1M$0.22up $0.2
Out / 1M$1.375up $1.25
Margin+10%
1st tokenunmeasured
MiniMax: MiniMax M2.5minimax/minimax-m2.5toolsjson205k context
Context 205k
In / 1M$0.297up $0.27
Out / 1M$1.188up $1.08
Margin+10%
1st tokenunmeasured
DeepSeek: DeepSeek V3.1 Terminusdeepseek/deepseek-v3.1-terminustoolsjson164k context
Context 164k
In / 1M$0.33up $0.3
Out / 1M$1.10up $1.00
Margin+10%
1st tokenunmeasured
Qwen: Qwen3 Coder 480B A35Bqwen/qwen3-codertoolsjson262k context
Context 262k
In / 1M$0.33up $0.3
Out / 1M$1.10up $1.00
Margin+10%
1st tokenunmeasured
Mancer: Weaver (alpha)mancer/weaverjson8k context
Context 8k
In / 1M$0.44up $0.4
Out / 1M$0.825up $0.75
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.