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 |
|---|---|---|---|---|---|---|---|
| Qwen3 Coder Flashqwen/qwen3-coder-flash | $0.2145 in$1.0725 out | $0.2145list $0.195 | $1.0725list $0.975 | no history yet | 1M | +10%$0.0975 out | unmeasured |
| Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct | $0.099 in$1.21 out | $0.099list $0.09 | $1.21list $1.10 | no history yet | 262k | +10%$0.11 out | unmeasured |
| DeepSeek V3.1deepseek/deepseek-chat-v3.1 | $0.275 in$1.045 out | $0.275list $0.25 | $1.045list $0.95 | no history yet | 163k | +10%$0.095 out | unmeasured |
| Mistral Medium 3.1mistralai/mistral-medium-3.1 | $0.44 in$2.20 out | $0.44list $0.40 | $2.20list $2.00 | no history yet | 131k | +10%$0.20 out | unmeasured |
| GLM 4.5Vz-ai/glm-4.5v | $0.66 in$1.98 out | $0.66list $0.60 | $1.98list $1.80 | no history yet | 65k | +10%$0.18 out | unmeasured |
| gpt-oss-120bopenai/gpt-oss-120bAlso:batch | $0.165 in$0.66 out | $0.165list $0.15 | $0.66list $0.60 | no history yet | 131k | +10%$0.06 out | unmeasured |
| gpt-oss-20bopenai/gpt-oss-20bAlso:batch | $0.0825 in$0.33 out | $0.0825list $0.075 | $0.33list $0.30 | no history yet | 131k | +10%$0.03 out | unmeasured |
| Claude Opus 4.1anthropic/claude-opus-4.1 | $16.50 in$82.50 out | $16.50list $15.00 | $82.50list $75.00 | no history yet | 200k | +10%$7.50 out | unmeasured |
| Codestral 2508mistralai/codestral-2508 | $0.33 in$0.99 out | $0.33list $0.30 | $0.99list $0.90 | no history yet | 256k | +10%$0.09 out | unmeasured |
| Qwen3 Coder 30B A3B Instructqwen/qwen3-coder-30b-a3b-instruct | $0.165 in$0.66 out | $0.165list $0.15 | $0.66list $0.60 | no history yet | 262k | +10%$0.06 out | unmeasured |
| Qwen3 30B A3B Instruct 2507qwen/qwen3-30b-a3b-instruct-2507 | $0.11 in$0.33 out | $0.11list $0.10 | $0.33list $0.30 | no history yet | 262k | +10%$0.03 out | unmeasured |
| GLM 4.5z-ai/glm-4.5 | $0.66 in$2.42 out | $0.66list $0.60 | $2.42list $2.20 | no history yet | 131k | +10%$0.22 out | unmeasured |
| GLM 4.5 Airz-ai/glm-4.5-air | $0.143 in$0.935 out | $0.143list $0.13 | $0.935list $0.85 | no history yet | 131k | +10%$0.085 out | unmeasured |
| Qwen3 235B A22B Thinking 2507qwen/qwen3-235b-a22b-thinking-2507 | $0.495 in$3.85 out | $0.495list $0.45 | $3.85list $3.50 | no history yet | 128k | +10%$0.35 out | unmeasured |
| Qwen3 Coder 480B A35Bqwen/qwen3-coder | $0.33 in$1.10 out | $0.33list $0.30 | $1.10list $1.00 | no history yet | 262k | +10%$0.10 out | unmeasured |
| Gemini 2.5 Flash Litegoogle/gemini-2.5-flash-lite | $0.11 in$0.44 out | $0.11list $0.10 | $0.44list $0.40 | no history yet | 1M | +10%$0.04 out | unmeasured |
| Qwen3 235B A22B Instruct 2507qwen/qwen3-235b-a22b-2507 | $0.154 in$0.88 out | $0.154list $0.14 | $0.88list $0.80 | no history yet | 262k | +10%$0.08 out | unmeasured |
| Kimi K2 0711moonshotai/kimi-k2Also:0905 | $0.627 in$2.53 out | $0.627list $0.57 | $2.53list $2.30 | no history yet | 131k | +10%$0.23 out | unmeasured |
| Mistral Small 3.2 24Bmistralai/mistral-small-3.2-24b-instruct | $0.11 in$0.33 out | $0.11list $0.10 | $0.33list $0.30 | no history yet | 256k | +10%$0.03 out | unmeasured |
| Gemini 2.5 Flashgoogle/gemini-2.5-flash | $0.33 in$2.75 out | $0.33list $0.30 | $2.75list $2.50 | no history yet | 1M | +10%$0.25 out | unmeasured |
| Gemini 2.5 Progoogle/gemini-2.5-pro | $1.375 in$11.00 out | $1.375list $1.25 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| o3 Proopenai/o3-pro | $22.00 in$88.00 out | $22.00list $20.00 | $88.00list $80.00 | no history yet | 200k | +10%$8.00 out | unmeasured |
| Gemini 2.5 Pro Preview 06-05google/gemini-2.5-pro-preview | $1.375 in$11.00 out | $1.375list $1.25 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| R1 0528deepseek/deepseek-r1-0528 | $0.55 in$2.365 out | $0.55list $0.50 | $2.365list $2.15 | no history yet | 163k | +10%$0.215 out | unmeasured |
| Mistral Medium 3mistralai/mistral-medium-3 | $0.44 in$2.20 out | $0.44list $0.40 | $2.20list $2.00 | no history yet | 131k | +10%$0.20 out | unmeasured |
| Qwen3 30B A3Bqwen/qwen3-30b-a3b | $0.132 in$0.55 out | $0.132list $0.12 | $0.55list $0.50 | no history yet | 40k | +10%$0.05 out | unmeasured |
| Qwen3 14Bqwen/qwen3-14b | $0.132 in$0.264 out | $0.132list $0.12 | $0.264list $0.24 | no history yet | 40k | +10%$0.024 out | unmeasured |
| Qwen3 32Bqwen/qwen3-32b | $0.088 in$0.308 out | $0.088list $0.08 | $0.308list $0.28 | no history yet | 131k | +10%$0.028 out | unmeasured |
| GPT-4.1 Nanoopenai/gpt-4.1-nano | $0.11 in$0.44 out | $0.11list $0.10 | $0.44list $0.40 | no history yet | 1M | +10%$0.04 out | unmeasured |
| Llama 4 Maverickmeta-llama/llama-4-maverick | $0.385 in$1.10 out | $0.385list $0.35 | $1.10list $1.00 | no history yet | 524k | +10%$0.10 out | unmeasured |
| Llama 4 Scoutmeta-llama/llama-4-scout | $0.11 in$0.33 out | $0.11list $0.10 | $0.33list $0.30 | no history yet | 327k | +10%$0.03 out | unmeasured |
| DeepSeek V3 0324deepseek/deepseek-chat-v3-0324 | $0.319 in$1.254 out | $0.319list $0.29 | $1.254list $1.14 | no history yet | 163k | +10%$0.114 out | unmeasured |
| Mistral Small 3.1 24Bmistralai/mistral-small-3.1-24b-instruct | $0.3861 in$0.6105 out | $0.3861list $0.351 | $0.6105list $0.555 | no history yet | 128k | +10%$0.0555 out | unmeasured |
| Gemma 3 12Bgoogle/gemma-3-12b-it | $0.055 in$0.165 out | $0.055list $0.05 | $0.165list $0.15 | no history yet | 131k | +10%$0.015 out | unmeasured |
| Gemma 3 27Bgoogle/gemma-3-27b-it | $0.088 in$0.385 out | $0.088list $0.08 | $0.385list $0.35 | no history yet | 131k | +10%$0.035 out | unmeasured |
| Sabamistralai/mistral-saba | $0.22 in$0.66 out | $0.22list $0.20 | $0.66list $0.60 | no history yet | 32k | +10%$0.06 out | unmeasured |
| Qwen-Plusqwen/qwen-plus | $0.286 in$0.858 out | $0.286list $0.26 | $0.858list $0.78 | no history yet | 1M | +10%$0.078 out | unmeasured |
| DeepSeek V3deepseek/deepseek-chat | $0.28314 in$1.13157 out | $0.28314list $0.2574 | $1.13157list $1.0287 | no history yet | 163k | +10%$0.10287 out | unmeasured |
| Llama 3.3 70B Instructmeta-llama/llama-3.3-70b-instruct | $0.781 in$0.781 out | $0.781list $0.71 | $0.781list $0.71 | no history yet | 131k | +10%$0.071 out | unmeasured |
| Qwen2.5 72B Instructqwen/qwen-2.5-72b-instruct | $0.396 in$0.44 out | $0.396list $0.36 | $0.44list $0.40 | no history yet | 32k | +10%$0.04 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.