Specifiche del modello
- Contesto
- 1.310.720 tokens
- Output massimo
- 131.072 tokens
- Architettura
- text+image+video->text
- Tokenizer
- Other
- Limite di conoscenza
- Non indicato
- Moderato
- No
Prezzi completi
Tariffe sincronizzate da OpenRouter, per milione di token.
- Input
- $0.075 per milione di token
- Output
- $0.25 per milione di token
- Lettura cache
- $0.015 per milione di token
Configurazione del modello
Parametri predefiniti
temperature- 1
top_p- 0.95
Ragionamento
- Ragionamento obbligatorio
- Sì
- Parametri predefiniti
- max
- Capacità e modalità
- max, high, low
Avvio rapido
Imposta OPENROUTER_API_KEY localmente. Python richiede requests; JavaScript viene eseguito in Node.js. Conserva la chiave sul server.
curl --fail-with-body https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"z-ai/glm-5.3-flash","messages":[{"role":"user","content":"Hello!"}]}'Input → Output
Sì · max · high · low
Parametri API supportati
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p24 provider
Verificato: 7 settembre 2026
Disponibilità, latenza, throughput e routing cambiano continuamente. Consulta la fonte per i dati correnti.
Relace
fp4- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.0713
- Output
- $0.2375
- Lettura cache
- $0.0143
- Scrittura cache
- Non indicato
GMICloud
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.075
- Output
- $0.25
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Novita
fp8- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.075
- Output
- $0.25
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
DeepInfra
fp4- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.075
- Output
- $0.25
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Z.AI
fp8- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.075
- Output
- $0.25
- Lettura cache
- $0.015
- Scrittura cache
- Non indicato
Wafer
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.1
- Output
- $0.35
- Lettura cache
- $0.02
- Scrittura cache
- Non indicato
StreamLake
fp8- Contesto
- 1.0M
- Output massimo
- 128K
- Input
- $0.135
- Output
- $0.45
- Lettura cache
- $0.027
- Scrittura cache
- Non indicato
Makora
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.14
- Output
- $0.47
- Lettura cache
- $0.024
- Scrittura cache
- Non indicato
Modal
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.4999
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
CoreWeave
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.05
- Scrittura cache
- Non indicato
Sail Research
fp8- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
NextBit
fp8- Contesto
- 1.0M
- Output massimo
- 128K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Fireworks
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Friendli
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
SiliconFlow
fp8- Contesto
- 1.0M
- Output massimo
- 262K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
DigitalOcean
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Together
Non indicato- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Reka
fp8- Contesto
- 262K
- Output massimo
- 236K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Parasail
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
BaseTen
fp8- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Venice
Non indicato- Contesto
- 1.0M
- Output massimo
- 131K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Io Net
fp8- Contesto
- 262K
- Output massimo
- 131K
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Cloudflare
Non indicato- Contesto
- 1.3M
- Output massimo
- 1.2M
- Input
- $0.15
- Output
- $0.5
- Lettura cache
- $0.03
- Scrittura cache
- Non indicato
Morph
fp8- Contesto
- 1.0M
- Output massimo
- 944K
- Input
- $0.388
- Output
- $1.358
- Lettura cache
- $0.0776
- Scrittura cache
- Non indicato