DeepInfra
deepinfra/fp8
Purchased through OpenRouter
$1.32
1M input + 1M output token subtotal
Input / output per 1M tokens: $0.36 / $0.96
Lowest reference rate in this group; verify output and access.
Use this endpoint
Create a provider API key and set the local environment variable OPENROUTER_API_KEY, then run the example below.
After submitting, use the official docs to check job status and retrieve results.
https://openrouter.ai/api/v1/batches
Base URL: https://openrouter.ai/api/v1 Catalog model: thinkingmachines/inkling-small:batch Request API model: thinkingmachines/inkling-small Protocol: openai Provider routing: deepinfra/fp8 API key env: OPENROUTER_API_KEY Docs: https://openrouter.ai/docs/batch-quickstart
curl "https://openrouter.ai/api/v1/batches" -H "Authorization: Bearer $OPENROUTER_API_KEY" -H "Content-Type: application/json" -d '{
"endpoint": "/v1/chat/completions",
"model": "thinkingmachines/inkling-small",
"provider": {
"only": [
"deepinfra/fp8"
],
"allow_fallbacks": false
},
"completion_window": "24h",
"requests": [
{
"custom_id": "example-1",
"body": {
"messages": [
{
"role": "user",
"content": "Read this support ticket and return a JSON object with \"summary\", \"urgency\" (low, medium, or high), and \"next_step\". Use null for missing details.\n\nTicket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo."
}
]
}
}
]
}'Use the OpenAI-compatible API at https://openrouter.ai/api/v1 with model "thinkingmachines/inkling-small". Use the asynchronous Batch API to obtain the batch rate. At the batch top level set provider.only to ["deepinfra/fp8"] and allow_fallbacks to false. Check the provider and billed cost in the result. Read the API key from the OPENROUTER_API_KEY environment variable; never hardcode it. Pricing observed on 2026-11-22: $0.36 / 1M input tokens, $0.96 / 1M output tokens, $0.08 / 1M cache read tokens. API integration docs: https://openrouter.ai/docs/batch-quickstart. Billing scope and conditions: Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.. Source: https://openrouter.ai/api/v1/models/thinkingmachines/inkling-small%3Abatch/endpoints.
Read this support ticket and return a JSON object with "summary", "urgency" (low, medium, or high), and "next_step". Use null for missing details. Ticket: I paid for the Pro plan yesterday, but my account still shows Free. My team needs access before tomorrow’s demo.
Input: $0.36 / 1M tokens Output: $0.96 / 1M tokens Cache read: $0.08 / 1M tokens Currency: USD Regions: global Unit source: api Checked: 2026-11-22T09:20:27.138Z Source: https://openrouter.ai/api/v1/models/thinkingmachines/inkling-small%3Abatch/endpoints
Source check: 2026-11-22 · valid no later than 2026-11-23 09:21 UTC
Billing evidence and sources
thinkingmachines/inkling-small:batch · deepinfra/fp8
Billing conditions
Served by DeepInfra through OpenRouter, not a direct-provider contract. Published rates for route deepinfra/fp8; fp8 quantization. Other fees, tier conditions and regional access must be checked before use.
- Cache read / 1M
- $0.08
- Cache write / 1M
- Not published
- Per request
- Not published
- Route
- deepinfra/fp8 · fp8
Declared parameters: frequency_penalty, include_reasoning, logit_bias, max_tokens, min_p, presence_penalty, reasoning, reasoning_effort, repetition_penalty, seed, stop, temperature, tool_choice, tools, top_k, top_p