Model specifications
- Context
- 524,288 tokens
- Maximum output
- 262,144 tokens
- Architecture
- text+image+audio->text
- Tokenizer
- Other
- Knowledge cutoff
- Not provided
- Moderated
- No
Complete pricing
Synchronized OpenRouter rates. Token prices are shown per one million tokens.
- Input
- $0.36 per 1M tokens
- Output
- $0.96 per 1M tokens
- Cache read
- $0.08 per 1M tokens
Model configuration
Reasoning
- Reasoning required
- No
- Default parameters
- high
- Capabilities
- max, high, medium, low, minimal, none
Quick start
Set OPENROUTER_API_KEY locally. Python requires requests; JavaScript runs in Node.js. Keep the key on the server.
This submits an asynchronous batch using the base model ID. A job ID confirms submission, not completion.
curl --fail-with-body https://openrouter.ai/api/beta/batches \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"endpoint":"/v1/chat/completions","model":"thinkingmachines/inkling-small","requests":[{"custom_id":"request-1","body":{"messages":[{"role":"user","content":"Hello!"}]}}]}'
# Replace JOB_ID with the returned id to check progress.
curl --fail-with-body "https://openrouter.ai/api/beta/batches/JOB_ID" \
-H "Authorization: Bearer $OPENROUTER_API_KEY"Input → Output
Yes · max · high · medium · low · minimal · none
Supported API parameters
frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyseedstoptemperaturetool_choicetoolstop_ktop_p1 Provider
Checked: November 7, 2026
Provider availability, latency, throughput and routing can change continuously. Open the source page for current operational data.
DeepInfra
fp8- Context
- 524K
- Maximum output
- 262K
- Input
- $0.36
- Output
- $0.96
- Cache read
- $0.08
- Cache write
- Not provided