Model catalog
Every model the gateway can route to.
Filter by provider, quality tier, region, or vision support. Pick a row and the snippet panel below builds a ready-to-run request using that exact canonical model id — copy, paste, replace the API key, and you're dispatching.
Provider
Tier
Region
Vision
Showing 82 of 82 models
Want code snippets? → /docs/api| Model id | Tier | Region | Input $/M | Output $/M | Cache | Capabilities |
|---|---|---|---|---|---|---|
anthropic/claude-haiku-5-5 | cheap / fast | Global | $0.100 | $0.500 | −90% | visiontoolsstreaming |
anthropic/claude-haiku-4-5 | cheap / fast | Global | $1.00 | $5.00 | −90% | visiontoolsstreaming |
anthropic/claude-sonnet-5 | flagship | Global | $2.00 | $10.00 | −90% | visiontoolsstreaming |
anthropic/claude-sonnet-5-5 | flagship | Global | $2.00 | $10.00 | −95% | visiontoolsstreaming |
anthropic/claude-sonnet-4-6 | flagship | Global | $3.00 | $15.00 | −90% | visiontoolsstreaming |
anthropic/claude-opus-5-5 | premium reasoning | Global | $4.00 | $20.00 | −95% | visiontoolsstreaming |
anthropic/claude-opus-4-5 | premium reasoning | Global | $5.00 | $25.00 | −90% | visiontoolsstreaming |
anthropic/claude-opus-4-6 | premium reasoning | Global | $5.00 | $25.00 | −90% | visiontoolsstreaming |
anthropic/claude-opus-4-7 | premium reasoning | Global | $5.00 | $25.00 | −90% | visiontoolsstreaming |
anthropic/claude-opus-4-8 | premium reasoning | Global | $5.00 | $25.00 | −90% | visiontoolsstreaming |
anthropic/claude-opus-5 | premium reasoning | Global | $5.00 | $25.00 | −90% | visiontoolsstreaming |
anthropic/claude-fable-5 | premium reasoning | Global | $10.00 | $50.00 | −90% | visiontoolsstreaming |
anthropic/claude-fable-5-1 | premium reasoning | Global | $10.00 | $50.00 | −98% | visiontoolsstreaming |
bedrock/anthropic.claude-haiku-4-5 | cheap / fast | Global | $1.00 | $5.00 | −90% | visiontoolsstreaming |
bedrock/anthropic.claude-sonnet-4-5 | flagship | Global | $3.00 | $15.00 | −90% | visiontoolsstreaming |
deepseek/deepseek-v4-1-flash | flagship | Global | $0.150 | $0.600 | −98% | visiontoolsstreaming |
deepseek/deepseek-v4-pro | premium reasoning | Global | $0.660 | $1.98 | −97% | toolsstreaming |
doubao/doubao-seed-2.0-mini | cheap / fast | China | $0.028 | $0.278 | −50% | toolsstreaming |
doubao/doubao-seed-2.0-lite | cheap / fast | China | $0.083 | $0.500 | −50% | toolsstreaming |
doubao/doubao-seed-2.1-turbo | flagship | China | $0.417 | $2.08 | −50% | visiontoolsstreaming |
doubao/doubao-seed-2.0-pro | flagship | China | $0.444 | $2.22 | −50% | toolsstreaming |
doubao/doubao-seed-2.1-pro | flagship | China | $0.833 | $4.17 | −50% | visiontoolsstreaming |
glm/glm-4.6v-flashx | cheap / fast | China | $0.040 | $0.400 | −90% | visiontoolsstreaming |
glm/glm-4.7-flashx | cheap / fast | China | $0.070 | $0.400 | −86% | toolsstreaming |
glm/glm-5.3-flash | cheap / fast | China | $0.150 | $0.500 | −80% | toolsstreaming |
glm/glm-4.5-air | cheap / fast | China | $0.200 | $1.10 | −85% | toolsstreaming |
glm/glm-4.6v | flagship | China | $0.300 | $0.900 | −83% | visiontoolsstreaming |
glm/glm-5.3-flashx | cheap / fast | China | $0.370 | $1.25 | −80% | toolsstreaming |
glm/glm-4.5 | cheap / fast | China | $0.600 | $2.20 | −82% | toolsstreaming |
glm/glm-4.5v | flagship | China | $0.600 | $1.80 | −82% | visiontoolsstreaming |
glm/glm-4.6 | cheap / fast | China | $0.600 | $2.20 | −82% | toolsstreaming |
glm/glm-4.7 | cheap / fast | China | $0.600 | $2.20 | −82% | toolsstreaming |
glm/glm-5 | flagship | China | $1.00 | $3.20 | −80% | toolsstreaming |
glm/glm-4.5-airx | flagship | China | $1.10 | $4.50 | −80% | toolsstreaming |
glm/glm-5v-turbo | flagship | China | $1.20 | $4.00 | −80% | visiontoolsstreaming |
glm/glm-5.1 | flagship | China | $1.40 | $4.40 | −81% | toolsstreaming |
glm/glm-5.2 | flagship | China | $1.40 | $4.40 | −81% | toolsstreaming |
glm/glm-5.3 | flagship | China | $1.40 | $4.40 | −81% | toolsstreaming |
glm/glm-4.5-x | flagship | China | $2.20 | $8.90 | −80% | toolsstreaming |
google/gemini-3.1-flash-lite | cheap / fast | Global | $0.250 | $1.50 | −90% | visiontoolsstreaming |
google/gemini-3.5-flash-lite | cheap / fast | Global | $0.300 | $2.50 | −90% | visiontoolsstreaming |
google/gemini-3.6-flash | cheap / fast | Global | $0.750 | $3.75 | −90% | visiontoolsstreaming |
google/gemini-3.8-flash | cheap / fast | Global | $0.750 | $3.75 | −90% | visiontoolsstreaming |
google/gemini-4-argon | flagship | Global | $2.00 | $10.00 | −95% | visiontoolsstreaming |
groq/openai/gpt-oss-20b | cheap / fast | Global | $0.075 | $0.300 | −50% | toolsstreaming |
groq/openai/gpt-oss-120b | flagship | Global | $0.150 | $0.600 | −50% | toolsstreaming |
kimi/kimi-k2.6 | flagship | China | $0.950 | $4.00 | −83% | visiontoolsstreaming |
kimi/kimi-k2.7-code | cheap / fast | China | $0.950 | $4.00 | −80% | visiontoolsstreaming |
kimi/kimi-k2.7-code-highspeed | cheap / fast | China | $1.90 | $8.00 | −80% | visiontoolsstreaming |
kimi/kimi-k3.1-pro | flagship | China | $2.00 | $10.00 | −90% | toolsstreaming |
kimi/kimi-k3 | premium reasoning | China | $3.00 | $15.00 | −90% | toolsstreaming |
krutrim/openai/gpt-oss-20b | cheap / fast | India | $0.084 | $0.330 | — | toolsstreaming |
krutrim/openai/gpt-oss-120b | cheap / fast | India | $0.140 | $0.680 | — | toolsstreaming |
meta/muse-spark-1.1 | flagship | Global | $1.25 | $4.25 | −88% | toolsstreaming |
meta/muse-spark-1.2 | flagship | Global | $1.25 | $4.25 | −88% | toolsstreaming |
meta/muse-spark-1.3 | flagship | Global | $1.25 | $4.25 | −88% | toolsstreaming |
openai/gpt-6-luna | cheap / fast | Global | $0.100 | $0.500 | −90% | toolsstreaming |
openai/gpt-5.6-luna | cheap / fast | Global | $0.200 | $1.20 | −90% | visiontoolsstreaming |
openai/gpt-6.1-terra | flagship | Global | $1.00 | $5.00 | −95% | toolsstreaming |
openai/gpt-5.6-terra | flagship | Global | $2.00 | $12.00 | −90% | visiontoolsstreaming |
openai/gpt-6.1-sol | flagship | Global | $2.00 | $10.00 | −95% | toolsstreaming |
openai/gpt-5.6-sol | premium reasoning | Global | $4.00 | $20.00 | −90% | visiontoolsstreaming |
openai/gpt-6-astra | premium reasoning | Global | $10.00 | $50.00 | −90% | toolsstreaming |
qwen/qwen-vl-ocr | cheap / fast | China | $0.043 | $0.072 | — | visiontoolsstreaming |
qwen/qwen3.5-flash | cheap / fast | China | $0.100 | $0.400 | — | toolsstreaming |
qwen/qwen-mt-flash | cheap / fast | China | $0.101 | $0.280 | — | toolsstreaming |
qwen/qwen3.8-flash | cheap / fast | China | $0.150 | $0.470 | −60% | toolsstreaming |
qwen/qwen-mt-plus | flagship | China | $0.259 | $0.775 | — | toolsstreaming |
qwen/qwen-plus | cheap / fast | China | $0.400 | $1.20 | −50% | toolsstreaming |
qwen/qwen3.7-plus | cheap / fast | China | $0.400 | $1.60 | −78% | toolsstreaming |
qwen/qwen-max | flagship | China | $1.60 | $6.40 | −50% | toolsstreaming |
qwen/qwen3.8-max | flagship | China | $2.00 | $6.00 | −60% | toolsstreaming |
qwen/qwen3.7-max | flagship | China | $2.50 | $7.50 | −80% | toolsstreaming |
sarvam/sarvam-105b | flagship | India | $0.156 | $0.625 | −67% | toolsstreaming |
sarvam/sarvam-105b-conversations | flagship | India | $0.156 | $0.625 | −67% | toolsstreaming |
xai/grok-build-0-1 | cheap / fast | Global | $1.00 | $2.00 | −80% | toolsstreaming |
xai/grok-4-20-0309-non-reasoning | flagship | Global | $1.25 | $2.50 | −84% | toolsstreaming |
xai/grok-4-20-0309-reasoning | flagship | Global | $1.25 | $2.50 | −84% | toolsstreaming |
xai/grok-4-3 | flagship | Global | $1.25 | $2.50 | −84% | toolsstreaming |
xai/grok-4-5 | flagship | Global | $2.00 | $6.00 | −85% | toolsstreaming |
xai/grok-4-6 | flagship | Global | $2.00 | $6.00 | −75% | toolsstreaming |
xai/grok-4-7 | flagship | Global | $2.00 | $6.00 | −75% | toolsstreaming |
Pricing shown is upstream cost per 1M tokens in USD. On the BYOK subscription ($15 Starter / $25 Pro per month), you pay these rates directly to the provider on your own key — we add nothing per request. On pay-as-you-go credits, we front the provider at cost and add a 2% platform fee plus card processing at top-up; each call debits the exact upstream number. Cache hits are billed at $0 under either mode. See the pricing section and the terms for the full breakdown. Rates are refreshed daily from provider pricing pages and reflected in the catalog above.
See also: API reference · Integration guides · Home