Antimatter

Pricing

Every model, priced in the open

You pay the provider's published price plus 10%. That is the whole margin, on every model.

161 to 200 of 336 models

ModelPrice per 1MInput per 1MOutput per 1MLast 90 daysContextMarginSpeed
GPT-4.1 Nanoopenai/gpt-4.1-nanovisionreads filestools, declaredjson, declared$0.11 in$0.44 out$0.11list $0.10$0.44list $0.40no history yet1M+10%$0.04 outunmeasured
Llama 4 Maverickmeta-llama/llama-4-maverickvisiontools, declaredjson, declared$0.385 in$1.10 out$0.385list $0.35$1.10list $1.00no history yet524k+10%$0.10 outunmeasured
Llama 4 Scoutmeta-llama/llama-4-scoutvisiontools, declaredjson, declared$0.11 in$0.33 out$0.11list $0.10$0.33list $0.30no history yet327k+10%$0.03 outunmeasured
DeepSeek V3 0324deepseek/deepseek-chat-v3-0324tools, declaredjson, declared$0.319 in$1.254 out$0.319list $0.29$1.254list $1.14no history yet163k+10%$0.114 outunmeasured
Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instructvisiontools, declaredjson, declared$0.3861 in$0.6105 out$0.3861list $0.351$0.6105list $0.555no history yet128k+10%$0.0555 outunmeasured
Gemma 3 4Bgoogle/gemma-3-4b-itvisionjson, declared$0.055 in$0.11 out$0.055list $0.05$0.11list $0.10no history yet131k+10%$0.01 outunmeasured
Gemma 3 12Bgoogle/gemma-3-12b-itvisiontools, declaredjson, declared$0.055 in$0.165 out$0.055list $0.05$0.165list $0.15no history yet131k+10%$0.015 outunmeasured
Gemma 3 27Bgoogle/gemma-3-27b-itvisiontools, declaredjson, declared$0.088 in$0.385 out$0.088list $0.08$0.385list $0.35no history yet131k+10%$0.035 outunmeasured
Sabamistralai/mistral-sabareads filestools, declaredjson, declared$0.22 in$0.66 out$0.22list $0.20$0.66list $0.60no history yet32k+10%$0.06 outunmeasured
Qwen2.5 VL 72B Instructqwen/qwen2.5-vl-72b-instructvisionjson, declared$0.88 in$1.10 out$0.88list $0.80$1.10list $1.00no history yet128k+10%$0.10 outunmeasured
Qwen-Plusqwen/qwen-plustools, declaredjson, declared$0.286 in$0.858 out$0.286list $0.26$0.858list $0.78no history yet1M+10%$0.078 outunmeasured
Mistral Small 3mistralai/mistral-small-24b-instruct-2501json, declared$0.055 in$0.088 out$0.055list $0.05$0.088list $0.08no history yet32k+10%$0.008 outunmeasured
DeepSeek V3deepseek/deepseek-chattools, declaredjson, declared$0.28314 in$1.13157 out$0.28314list $0.2574$1.13157list $1.0287no history yet163k+10%$0.10287 outunmeasured
Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instructtools, declaredjson, declared$0.781 in$0.781 out$0.781list $0.71$0.781list $0.71no history yet131k+10%$0.071 outunmeasured
Qwen2.5 Coder 32B Instructqwen/qwen-2.5-coder-32b-instructjson, declared$0.726 in$1.10 out$0.726list $0.66$1.10list $1.00no history yet32k+10%$0.10 outunmeasured
Llama 3.2 1B Instructmeta-llama/llama-3.2-1b-instruct$0.0297 in$0.2211 out$0.0297list $0.027$0.2211list $0.201no history yet60k+10%$0.0201 outunmeasured
Llama 3.2 3B Instructmeta-llama/llama-3.2-3b-instructjson, declared$0.05599 in$0.3685 out$0.05599list $0.0509$0.3685list $0.335no history yet131k+10%$0.0335 outunmeasured
Qwen2.5 72B Instructqwen/qwen-2.5-72b-instructtools, declaredjson, declared$0.396 in$0.44 out$0.396list $0.36$0.44list $0.40no history yet32k+10%$0.04 outunmeasured
Llama 3.1 70B Instructmeta-llama/llama-3.1-70b-instructtools, declared$0.792 in$0.792 out$0.792list $0.72$0.792list $0.72no history yet131k+10%$0.072 outunmeasured
Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instructtools, declaredjson, declared$0.022 in$0.044 out$0.022list $0.02$0.044list $0.04no history yet131k+10%$0.004 outunmeasured
Mistral Nemomistralai/mistral-nemotools, declaredjson, declared$0.0319 in$0.033 out$0.0319list $0.029$0.033list $0.03no history yet131k+10%$0.003 outunmeasured
Gemma 2 27Bgoogle/gemma-2-27b-itjson, declared$0.715 in$0.715 out$0.715list $0.65$0.715list $0.65no history yet8k+10%$0.065 outunmeasured
Mixtral 8x22B Instructmistralai/mixtral-8x22b-instructreads filestools, declaredjson, declared$2.20 in$6.60 out$2.20list $2.00$6.60list $6.00no history yet65k+10%$0.60 outunmeasured
Mistral Largemistralai/mistral-largeAlso:25122407reads filestools, declaredjson, declared$2.20 in$6.60 out$2.20list $2.00$6.60list $6.00no history yet128k+10%$0.60 outunmeasured
GPT-3.5 Turbo (older v0613)openai/gpt-3.5-turbo-0613tools, declaredjson, declared$1.10 in$2.20 out$1.10list $1.00$2.20list $2.00no history yet4k+10%$0.20 outunmeasured
GPT-3.5 Turbo 16kopenai/gpt-3.5-turbo-16ktools, declaredjson, declared$3.30 in$4.40 out$3.30list $3.00$4.40list $4.00no history yet16k+10%$0.40 outunmeasured
GPT-4openai/gpt-4tools, declaredjson, declared$33.00 in$66.00 out$33.00list $30.00$66.00list $60.00no history yet8k+10%$6.00 outunmeasured
gpt-4.1openai/gpt-4.1vision$2.20 in$8.80 out$2.20list $2.00$8.80list $8.00no history yet1M+10%$0.80 outunmeasured
gpt-4.1-miniopenai/gpt-4.1-minivision$0.44 in$1.76 out$0.44list $0.40$1.76list $1.60no history yet1M+10%$0.16 outunmeasured
gpt-4oopenai/gpt-4oAlso:2024-11-202024-08-062024-05-13vision$2.75 in$11.00 out$2.75list $2.50$11.00list $10.00no history yet128k+10%$1.00 outunmeasured
gpt-4o-miniopenai/gpt-4o-miniAlso:2024-07-18vision$0.165 in$0.66 out$0.165list $0.15$0.66list $0.60no history yet128k+10%$0.06 outunmeasured
gpt-5openai/gpt-5vision$1.375 in$11.00 out$1.375list $1.25$11.00list $10.00no history yet400k+10%$1.00 outunmeasured
gpt-5-miniopenai/gpt-5-minivision$0.275 in$2.20 out$0.275list $0.25$2.20list $2.00no history yet400k+10%$0.20 outunmeasured
gpt-5-nanoopenai/gpt-5-nanoAlso:batchvision$0.055 in$0.44 out$0.055list $0.05$0.44list $0.40no history yet400k+10%$0.04 outunmeasured
gpt-5-proopenai/gpt-5-provision$16.50 in$132.00 out$16.50list $15.00$132.00list $120.00no history yet400k+10%$12.00 outunmeasured
gpt-5.1openai/gpt-5.1vision$1.375 in$11.00 out$1.375list $1.25$11.00list $10.00no history yet400k+10%$1.00 outunmeasured
gpt-5.2openai/gpt-5.2vision$1.925 in$15.40 out$1.925list $1.75$15.40list $14.00no history yet400k+10%$1.40 outunmeasured
gpt-5.2-proopenai/gpt-5.2-provision$23.10 in$184.80 out$23.10list $21.00$184.80list $168.00no history yet400k+10%$16.80 outunmeasured
gpt-5.3-codexopenai/gpt-5.3-codexvision$1.925 in$15.40 out$1.925list $1.75$15.40list $14.00no history yet400k+10%$1.40 outunmeasured
gpt-5.4openai/gpt-5.4vision$2.75 in$16.50 out$2.75list $2.50$16.50list $15.00no history yet1M+10%$1.50 outunmeasured

“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.

how many
What a thousand of 1,200 tokens in and 350 tokens out costs on each model
ModelAntimatterMargin
Ling 3.0 Tinyinclusionai/ling-3.0-tiny$0.0371$0.00338
Llama 3.1 8B Instructmeta-llama/llama-3.1-8b-instruct$0.0418$0.0038
Mistral Nemomistralai/mistral-nemo$0.0498$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
333 priced models, by what a token costs (three in to one out) and how much each can hold. 3 more with no published price are in the list but not on the axis. Out of 336 models. The list below has all of them, with search.

margin over the provider's price

+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.

models
336
priced
333
labs
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.
Keys are free. A lifetime allowance of $0.25 covers the first requests of an account that has never deposited.
We take only $ANTI right now: ANTI on Robinhood Chain. Send it, then claim the transaction from your account. It is credited in dollars at the credit price when you claim it.
Agents use a key made with a wallet signature. Paying per request with x402 is not on here. See how
Data retention explains what the API keeps, for how long and how to remove it.

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.