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 |
|---|---|---|---|---|---|---|---|
| Qwen4 Maxqwen/qwen4-max | $1.65 in$4.95 out | $1.65list $1.50 | $4.95list $4.50 | no history yet | 1M | +10%$0.45 out | unmeasured |
| Gemini 4 Hydrogengoogle/gemini-4-hydrogenAlso:batchlatest | $1.65 in$8.25 out | $1.65list $1.50 | $8.25list $7.50 | no history yet | 1M | +10%$0.75 out | unmeasured |
| Gemini 4 Carbongoogle/gemini-4-carbonAlso:batchlatest | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| Claude Fable 5.2anthropic/claude-fable-5.2Also:batchlatest | $8.80 in$44.00 out | $8.80list $8.00 | $44.00list $40.00 | no history yet | 1M | +10%$4.00 out | unmeasured |
| GLM 5.3 FlashX Legalz-ai/glm-5.3-flashx-legal | $0.407 in$1.375 out | $0.407list $0.37 | $1.375list $1.25 | no history yet | 1M | +10%$0.125 out | unmeasured |
| GPT-6.1 Terra Proopenai/gpt-6.1-terra-proAlso:batch | $1.10 in$5.50 out | $1.10list $1.00 | $5.50list $5.00 | no history yet | 1M | +10%$0.50 out | unmeasured |
| GPT-6.1 Terraopenai/gpt-6.1-terraAlso:batchlatest | $1.10 in$5.50 out | $1.10list $1.00 | $5.50list $5.00 | no history yet | 1M | +10%$0.50 out | unmeasured |
| Kimi K3.1 Promoonshotai/kimi-k3.1-pro | $0.26433 in$9.24253 out | $0.26433list $0.2403 | $9.24253list $8.4023 | no history yet | 1M | +10%$0.84023 out | unmeasured |
| Gemini 4 Argongoogle/gemini-4-argonAlso:batch | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| Claude Haiku 5.5anthropic/claude-haiku-5.5Also:batchlatest | $0.11 in$0.55 out | $0.11list $0.10 | $0.55list $0.50 | no history yet | 1M | +10%$0.05 out | unmeasured |
| Nano Banana 2.1google/gemini-nano-banana-2.1 | $1.65 in$8.25 out | $1.65list $1.50 | $8.25list $7.50 | no history yet | 65k | +10%$0.75 out | unmeasured |
| Mistral Large 4mistralai/mistral-large-4-0 | $0.77 in$2.31 out | $0.77list $0.70 | $2.31list $2.10 | no history yet | 1M | +10%$0.21 out | unmeasured |
| GPT-6.1 Sol Proopenai/gpt-6.1-sol-proAlso:batch | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| GPT-6.1 Solopenai/gpt-6.1-solAlso:batchlatest | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| Claude Sonnet 5.5anthropic/claude-sonnet-5.5Also:batchlatest | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| GLM 5.3 Primez-ai/glm-5.3-prime | $3.08 in$9.68 out | $3.08list $2.80 | $9.68list $8.80 | no history yet | 1M | +10%$0.88 out | unmeasured |
| Qwen3.8 Max Primeqwen/qwen3.8-max-prime | $4.40 in$13.20 out | $4.40list $4.00 | $13.20list $12.00 | no history yet | 1M | +10%$1.20 out | unmeasured |
| GPT-6 Luna Proopenai/gpt-6-luna-proAlso:batch | $0.11 in$0.55 out | $0.11list $0.10 | $0.55list $0.50 | no history yet | 1M | +10%$0.05 out | unmeasured |
| GPT-6 Lunaopenai/gpt-6-lunaAlso:batchlatest | $0.11 in$0.55 out | $0.11list $0.10 | $0.55list $0.50 | no history yet | 1M | +10%$0.05 out | unmeasured |
| GPT-6 Sol Proopenai/gpt-6-sol-proAlso:batch | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| GPT-6 Solopenai/gpt-6-solAlso:batch | $2.20 in$11.00 out | $2.20list $2.00 | $11.00list $10.00 | no history yet | 1M | +10%$1.00 out | unmeasured |
| Claude Opus 5.5anthropic/claude-opus-5.5Also:batchlatest | $4.40 in$22.00 out | $4.40list $4.00 | $22.00list $20.00 | no history yet | 1M | +10%$2.00 out | unmeasured |
| Grok 4.7x-ai/grok-4.7Also:batchlatest | $2.20 in$6.60 out | $2.20list $2.00 | $6.60list $6.00 | no history yet | 500k | +10%$0.60 out | unmeasured |
| Qwen3.8 Omni Flashqwen/qwen3.8-omni-flash | $0.165 in$0.517 out | $0.165list $0.15 | $0.517list $0.47 | no history yet | 1M | +10%$0.047 out | unmeasured |
| GLM 5.3 FlashXz-ai/glm-5.3-flashx | $0.407 in$1.375 out | $0.407list $0.37 | $1.375list $1.25 | no history yet | 1M | +10%$0.125 out | unmeasured |
| DeepSeek V4.1 Flashdeepseek/deepseek-v4.1-flashAlso:10171017 batchlatestbatch | $0.154 in$0.462 out | $0.154list $0.14 | $0.462list $0.42 | no history yet | 1M | +10%$0.042 out | unmeasured |
| GPT-6 Astraopenai/gpt-6-astraAlso:latestbatch | $11.00 in$55.00 out | $11.00list $10.00 | $55.00list $50.00 | no history yet | 1M | +10%$5.00 out | unmeasured |
| GPT-6 Astra Proopenai/gpt-6-astra-proAlso:batch | $11.00 in$55.00 out | $11.00list $10.00 | $55.00list $50.00 | no history yet | 1M | +10%$5.00 out | unmeasured |
| Qwen3.8 Max (0902)qwen/qwen3.8-max-0902Also:batch | $2.20 in$6.60 out | $2.20list $2.00 | $6.60list $6.00 | no history yet | 1M | +10%$0.60 out | unmeasured |
| Gemini 3.8 Flashgoogle/gemini-3.8-flashAlso:batch | $0.825 in$4.125 out | $0.825list $0.75 | $4.125list $3.75 | no history yet | 1M | +10%$0.375 out | unmeasured |
| Claude Fable 5.1anthropic/claude-fable-5.1Also:batch | $11.00 in$55.00 out | $11.00list $10.00 | $55.00list $50.00 | no history yet | 1M | +10%$5.00 out | unmeasured |
| Qwen3.8 Flashqwen/qwen3.8-flash | $0.165 in$0.517 out | $0.165list $0.15 | $0.517list $0.47 | no history yet | 1M | +10%$0.047 out | unmeasured |
| GLM 5.3 Flashz-ai/glm-5.3-flashAlso:latestbatch | $0.04389 in$0.08624 out | $0.04389list $0.0399 | $0.08624list $0.0784 | no history yet | 1M | +10%$0.00784 out | unmeasured |
| DeepSeek V4 Flash Vision Expdeepseek/deepseek-v4-flash-vision-exp | $0.484 in$1.452 out | $0.484list $0.44 | $1.452list $1.32 | no history yet | 1M | +10%$0.132 out | unmeasured |
| GLM 5.3z-ai/glm-5.3Also:latestbatch | $0.07689 in$1.54 out | $0.07689list $0.0699 | $1.54list $1.40 | no history yet | 1M | +10%$0.14 out | unmeasured |
| Qwen3.8 27Bqwen/qwen3.8-27bAlso:batch | $0.165 in$2.0625 out | $0.165list $0.15 | $2.0625list $1.875 | no history yet | 1M | +10%$0.1875 out | unmeasured |
| Gemini 3.7 Flashgoogle/gemini-3.7-flashAlso:batch | $0.825 in$4.125 out | $0.825list $0.75 | $4.125list $3.75 | no history yet | 1M | +10%$0.375 out | unmeasured |
| Qwen3.8 2.4T A95Bqwen/qwen3.8-2.4t-a95b | $2.20 in$6.60 out | $2.20list $2.00 | $6.60list $6.00 | no history yet | 1M | +10%$0.60 out | unmeasured |
| Grok 4.6x-ai/grok-4.6Also:batch | $2.20 in$6.60 out | $2.20list $2.00 | $6.60list $6.00 | no history yet | 500k | +10%$0.60 out | unmeasured |
| Qwen3.7 Flashqwen/qwen3.7-flash | $0.033 in$0.143 out | $0.033list $0.03 | $0.143list $0.13 | no history yet | 1M | +10%$0.013 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.