jishie

Qwen3 Max

cloudflare-ai-gateway/alibaba/qwen3-max · family qwen · in: text → out: text · price provider-declared (via models.dev). Capabilities: tools text.

$2.40
Blended $/1M (3:1)
$1.2
Input $/1M
$6
Output $/1M
$7.20
1M in + 1M out
—
Cache read $/1M
#5976 of 8,511
Cheapest rank
Provider
Cloudflare AI Gateway (cloudflare-ai-gateway)
Kind
text (outputs text)
Context
262,144 tokens
Max output
65,536 tokens
Capabilities
tools text

Same model, other providers

“Qwen3 Max” is offered by 13 providers — cheapest-effective first. Alibaba Coding Plan is the cheapest at $0.00 blended.

ProviderInputOutputBlendedContext
Alibaba Coding Planfreefree$0.00262k
Alibaba Coding Plan (China)freefree$0.00262k
Ofox$0.36$1.43$0.63256k
Merge Gateway$0.359$1.43$0.63262k
Alibaba (China)$0.359$1.43$0.63262k
OrcaRouter$0.359$1.43$0.63262k
AIHubMix$0.4508$2.7$1.01262k
Qiniu$0.8696$3.48$1.52262k
Cloudflare AI Gateway (this)$1.2$6$2.40262k
Deep Infra$1.2$6$2.40256k
LLMTR$1.2$6$2.40256k
Abacus$1.2$6$2.40131k
Alibaba$1.2$6$2.40262k

Call it

jishie indexes & prices models; it does not proxy inference.

Most providers are OpenAI-compatible — point base_url at Cloudflare AI Gateway and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"alibaba/qwen3-max","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):

← all Cloudflare AI Gateway models · model index · JSON