Qwen3.8 Flash-Next
NativeChatqwen/qwen3.8-flash-next$0.06851per 1M output tokens, network price
+11.60%24h
$0.203124h spent
1.2K24h requests
2sellers online
262.1Kcontext
258 ms · 42 tok/sfirst word · speed
TrustT4✓yes: Business verified✓yes: Model checked✕no: Prompt private
Native T4list price
| Time | Tier | Buyer | Seller | Checks | Used | Price / 1M out | Cost | Sale |
|---|---|---|---|---|---|---|---|---|
| – | acct…5dce | – | – | 130 output tokens | $0.06771 | $0.0000400 | sale_8f4259150181411b | |
| T4 | acct…67c5 | Trac Systems UG | ✓✓· | 222 output tokens | $0.06884 | $0.0000470 | sale_cf08e9f4ce19256a | |
| – | acct…5b50 | – | – | 159 output tokens | $0.06777 | $0.0000420 | sale_25c55a96a820eaf3 | |
| – | acct…6cdf | – | – | 271 output tokens | $0.06833 | $0.0000500 | sale_82ac1b7bafc1dba5 | |
| T4 | acct…53f2 | Trac Systems UG | ✓✓· | 96 output tokens | $0.06825 | $0.0000380 | sale_775b252aed188210 | |
| T4 | acct…3afb | Trac Systems UG | ✓✓· | 146 output tokens | $0.06922 | $0.0000420 | sale_191320d60aa2811f | |
| – | acct…7f58 | – | – | 81 output tokens | $0.06839 | $0.0000380 | sale_093beab5bbd148bc | |
| T4 | acct…7b55 | Trac Systems UG | ✓✓· | 189 output tokens | $0.06772 | $0.0000440 | sale_3250c1123c8dcdda | |
| T4 | acct…3d91 | Trac Systems UG | ✓✓· | 188 output tokens | $0.06764 | $0.0000450 | sale_811272459a67ba3e | |
| – | acct…ea43 | – | – | 37 output tokens | $0.08773 | $0.00000400 | sale_6d1ca5c724e1869a | |
| T4 | acct…854e | Trac Systems UG | ✓✓· | 477 output tokens | $0.06825 | $0.0000640 | sale_aae9888eedbc7758 | |
| – | acct…035e | – | – | 175 output tokens | $0.06764 | $0.0000430 | sale_2a4dc99fb92947f6 | |
| – | acct…250c | – | – | 81 output tokens | $0.06805 | $0.0000390 | sale_2c69d008922b60a4 | |
| – | acct…250c | – | – | 78 output tokens | $0.06823 | $0.0000390 | sale_438386510b2f66e8 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09228 | $0.000150 | sale_0de0a2df5e7c9b78 | |
| – | acct…250c | – | – | 84 output tokens | $0.09349 | $0.0000540 | sale_c424a2d24b0dbe50 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 21 output tokens | $0.09223 | $0.000140 | sale_c3b28090d709e2fe | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 79 output tokens | $0.09272 | $0.000149 | sale_30958ae34bedff79 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 79 output tokens | $0.09272 | $0.000149 | sale_d86a3c875876ed66 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 90 output tokens | $0.09253 | $0.000151 | sale_d427e5329e626c99 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 21 output tokens | $0.09223 | $0.000140 | sale_bfe9a297111ad708 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 90 output tokens | $0.09253 | $0.000151 | sale_6edcb462d889fd82 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09245 | $0.000150 | sale_1ee2a0579a91027e | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 87 output tokens | $0.09278 | $0.000151 | sale_60d5be1ca8c09e63 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 87 output tokens | $0.09278 | $0.000151 | sale_f6af63c4bc6ec0cd | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 87 output tokens | $0.09278 | $0.000151 | sale_bee8a581873321a5 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_8e10cd79932c6e8b | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_595746e7cf5210fe | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_e48fcccf6eac4606 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_262edc9fb3c75223 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_23eafbddcf79be6e | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_4a6b4592b7723791 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 82 output tokens | $0.09262 | $0.000150 | sale_cf6f89ff5ea2608f | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 79 output tokens | $0.09226 | $0.000149 | sale_fe2cf4606eebb33e | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 24 output tokens | $0.09279 | $0.000142 | sale_ea50280c6e4f723e | |
| – | acct…250c | – | – | 83 output tokens | $0.09350 | $0.0000540 | sale_bb04ee24e3109891 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 20 output tokens | $0.09258 | $0.000142 | sale_c3d119cbe5280819 | |
| T4 | acct…8a39 | Trac Systems UG | ✓✓· | 24 output tokens | $0.1085 | $0.000166 | sale_b6eeb962232b0ebe | |
| T4 | acct…5dce | Trac Systems UG | ✓✓· | 121 output tokens | $0.1083 | $0.0000630 | sale_4f92a1e781fbd332 | |
| T4 | acct…53f2 | Trac Systems UG | ✓✓· | 109 output tokens | $0.1088 | $0.0000620 | sale_67ffd4b4096f6ad9 | |
| – | acct…6cdf | – | – | 642 output tokens | $0.1088 | $0.000120 | sale_45e1773b10525c83 | |
| T4 | acct…67c5 | Trac Systems UG | ✓✓· | 136 output tokens | $0.1089 | $0.0000650 | sale_86b674fd35e83f0b | |
| – | acct…7f58 | – | – | 70 output tokens | $0.1083 | $0.0000590 | sale_616e5f4e23bcf9a0 | |
| – | acct…035e | – | – | 386 output tokens | $0.1087 | $0.0000920 | sale_db429702c99e6774 | |
| – | acct…5b50 | – | – | 353 output tokens | $0.1081 | $0.0000880 | sale_0020a47aac244540 | |
| – | acct…ea43 | – | – | 38 output tokens | $0.1288 | $0.00000600 | sale_edb90cd2ad063d2f | |
| T4 | acct…3d91 | Trac Systems UG | ✓✓· | 107 output tokens | $0.1095 | $0.0000640 | sale_f24c18505c895fdf | |
| T4 | acct…3afb | Trac Systems UG | ✓✓· | 128 output tokens | $0.1087 | $0.0000640 | sale_b081c445221a8935 | |
| T4 | acct…854e | Trac Systems UG | ✓✓· | 131 output tokens | $0.1082 | $0.0000640 | sale_c26a9f6d3059d4bf | |
| T4 | acct…7b55 | Trac Systems UG | ✓✓· | 277 output tokens | $0.1084 | $0.0000800 | sale_a0d35bacb42a108b |
| Tier | Seller | Checks | Status | Share of 7 days | Network price / 1M out | Context | Pays with | Requests | Avg. latency | Last seen |
|---|---|---|---|---|---|---|---|---|---|---|
| T4 | Trac Systems UG92293ede…d247 | ✓✓· | Online | 92.4% | $0.06763 | 262.1K | tap · tnk · usd | 71,508 | 11 s | Oct 29 |
| T4 | Trac Systems UG9cb9ddae…f317 | ✓✓· | Online | 6.9% | $0.06763 | 262.1K | tap · tnk · usd | 7,609 | 66 s | Oct 29 |
Performance
Measured from real, settled requests over the last 30 days. No synthetic benchmarks.
- Time to first token
- 258 ms
- median · 49,622 streams
- Request latency
- 3.8 s
- median · p95 49 s · 88,610 requests
- Throughput
- 42 tok/s
- 88549 requests
- Success rate
- 90.8%
- 97,564 finished requests, 30 days
This week: 486.1M tokens across 20151 requests.
Availability
Provider availability polled every minute by the platform itself, replayed hour by hour.
100% online over the last 3 days
3 days ago online down no dataNow
Usage per day
What actually ran on the platform, per day over the last 30 days. Settled usage from receipts; nothing synthetic.
Show as table
| Day | input tokens | output tokens | Requests |
|---|---|---|---|
| Oct 29 | 386,546 | 23,401 | 187 |
| Oct 28 | 5,649,216 | 410,021 | 1,461 |
| Oct 27 | 43,046,628 | 773,928 | 3,047 |
| Oct 26 | 68,144,427 | 1,099,953 | 3,649 |
| Oct 25 | 87,611,153 | 1,151,738 | 3,715 |
| Oct 24 | 93,272,734 | 1,261,728 | 3,342 |
| Oct 23 | 122,542,934 | 2,126,339 | 4,690 |
| Oct 22 | 62,697,142 | 1,718,136 | 3,581 |
| Oct 21 | 90,528,047 | 2,001,065 | 4,953 |
| Oct 20 | 29,632,837 | 884,414 | 3,219 |
| Oct 19 | 11,559,659 | 405,890 | 3,750 |
| Oct 18 | 17,462,386 | 676,296 | 2,430 |
| Oct 17 | 4,295,590 | 175,494 | 2,997 |
| Oct 16 | 11,089,229 | 787,159 | 3,008 |
| Oct 15 | 26,723,024 | 1,287,310 | 3,344 |
| Oct 14 | 29,123,457 | 1,964,842 | 4,803 |
| Oct 13 | 29,951,656 | 1,939,700 | 4,799 |
| Oct 12 | 10,720,440 | 802,646 | 3,053 |
| Oct 11 | 18,701,591 | 1,436,488 | 1,845 |
| Oct 10 | 8,357,560 | 895,082 | 741 |
| Oct 9 | 366,665 | 56,333 | 441 |
| Oct 8 | 9,598,911 | 858,659 | 2,137 |
| Oct 7 | 14,793,273 | 2,180,575 | 4,399 |
| Oct 6 | 8,735,164 | 1,556,536 | 3,067 |
| Oct 5 | 15,563,376 | 2,746,041 | 5,006 |
| Oct 4 | 40,475,594 | 4,894,070 | 7,717 |
| Oct 3 | 54,843,261 | 1,813,471 | 2,605 |
| Oct 2 | 60,116,815 | 2,484,142 | 2,391 |
| Oct 1 | 26,315,063 | 1,641,963 | 1,622 |
| Sep 30 | 120,169,238 | 4,334,420 | 3,766 |
API
The API is OpenAI-compatible and uses the same price and sellers as shown here.
curl https://api.openmayhem.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "qwen/qwen3.8-flash-next",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 2000
}'MCP
OpenMayhem runs its own MCP server, so Claude, Codex, Cursor and other AI apps can call this model and pay from your credit.
claude mcp add --transport http openmayhem \ https://mcp.openmayhem.ai/mcp \ --header "X-OpenMayhem-API-Key: $OPENMAYHEM_API_KEY"
Then ask your app, for example: "Use OpenMayhem Qwen3.8 Flash-Next to answer this." It calls chat with qwen/qwen3.8-flash-next. Apps that support sign-in connect without a key, and you approve spending limits once.
Full request reference
POST /v1/chat/completionsCHAT · openai_chat_completions +
Working request
curl https://api.openmayhem.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"model": "qwen/qwen3.8-flash-next",
"max_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh",
"thinking_mode": "enabled"
}'Parameters
| Parameter | Required | Type | Default | Allowed values | Limits and shape |
|---|---|---|---|---|---|
messages | Required | array | — | — | min items 1; max items 4096 [{"role":"user","content":"Hello"}] |
model | Required | string | — | Qwen/Qwen3.8-Flash-Next | — |
frequency_penalty | Optional | number | — | — | min -2; max 2 |
max_completion_tokens | Optional | integer | — | — | min 0; max 262144 |
max_tokens | Optional | integer | — | — | min 0; max 262144 |
metadata | Optional | object | — | — | JSON object; use the endpoint-specific schema shown in the examples |
min_p | Optional | number | — | — | min 0; max 0 |
presence_penalty | Optional | number | — | — | min -2; max 2 |
reasoning_effort | Optional | string | xhigh | low, medium, xhigh | — |
response_format | Optional | object | — | — | {"type":"json_object"} |
seed | Optional | integer | — | — | min 0; max 4294967295 |
stop | Optional | string | array | null | — | — | JSON array |
stream | Optional | boolean | false | — | — |
temperature | Optional | number | — | — | min 0; max 2 |
thinking_history | Optional | string | preserve | latest_only, preserve | — |
thinking_mode | Optional | string | enabled | disabled, enabled | — |
tool_choice | Optional | string | object | — | — | "auto" or an OpenAI tool-choice object |
tools | Optional | array | — | — | min items 1; max items 128 [{"type":"function","function":{"name":"get_time","description":"Get the current time","parameters":{"type":"object","properties":{}}}}] |
top_k | Optional | integer | — | — | min 1; max 1000000 |
top_p | Optional | number | — | — | min 0.000001; max 1 |
user | Optional | string | — | — | min length 1; max length 512 |
Input shapes
tools
{
"model": "qwen/qwen3.8-flash-next",
"tools": [
{
"type": "function",
"function": {
"name": "get_time",
"description": "Get the current time",
"parameters": {
"type": "object",
"properties": {}
}
}
}
]
}POST /v1/completionsCOMPLETIONS · openai_completions +
Working request
curl https://api.openmayhem.ai/v1/completions \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "qwen/qwen3.8-flash-next",
"prompt": "A lighthouse at dusk",
"max_tokens": 2000,
"stream": false
}'Parameters
| Parameter | Required | Type | Default | Allowed values | Limits and shape |
|---|---|---|---|---|---|
model | Required | string | — | Qwen/Qwen3.8-Flash-Next | — |
prompt | Required | string | — | — | min length 1; max length 32000 |
frequency_penalty | Optional | number | — | — | min -2; max 2 |
max_tokens | Optional | integer | — | — | min 0; max 262144 |
min_p | Optional | number | — | — | min 0; max 0 |
presence_penalty | Optional | number | — | — | min -2; max 2 |
reasoning_effort | Optional | string | xhigh | low, medium, xhigh | — |
seed | Optional | integer | — | — | min 0; max 4294967295 |
stop | Optional | string | array | null | — | — | JSON array |
stream | Optional | boolean | false | — | — |
temperature | Optional | number | — | — | min 0; max 2 |
thinking_history | Optional | string | preserve | latest_only, preserve | — |
thinking_mode | Optional | string | enabled | disabled, enabled | — |
top_k | Optional | integer | — | — | min 1; max 1000000 |
top_p | Optional | number | — | — | min 0.000001; max 1 |
user | Optional | string | — | — | min length 1; max length 512 |
POST /v1/responsesRESPONSES · openai_responses +
Working request
curl https://api.openmayhem.ai/v1/responses \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "qwen/qwen3.8-flash-next",
"input": "Hello",
"max_output_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh"
}'Parameters
| Parameter | Required | Type | Default | Allowed values | Limits and shape |
|---|---|---|---|---|---|
input | Required | string | array | — | — | JSON array |
model | Required | string | — | Qwen/Qwen3.8-Flash-Next | — |
max_output_tokens | Optional | integer | — | — | min 0; max 262144 |
metadata | Optional | object | — | — | JSON object; use the endpoint-specific schema shown in the examples |
min_p | Optional | number | — | — | min 0; max 0 |
reasoning_effort | Optional | string | xhigh | low, medium, xhigh | — |
stream | Optional | boolean | false | — | — |
temperature | Optional | number | — | — | min 0; max 2 |
text | Optional | object | — | — | JSON object; use the endpoint-specific schema shown in the examples |
thinking_history | Optional | string | preserve | latest_only, preserve | — |
thinking_mode | Optional | string | enabled | disabled, enabled | — |
tool_choice | Optional | string | object | — | — | "auto" or an OpenAI tool-choice object |
tools | Optional | array | — | — | min items 1; max items 128 [{"type":"function","function":{"name":"get_time","description":"Get the current time","parameters":{"type":"object","properties":{}}}}] |
top_k | Optional | integer | — | — | min 1; max 1000000 |
top_p | Optional | number | — | — | min 0.000001; max 1 |
user | Optional | string | — | — | min length 1; max length 512 |
Input shapes
tools
{
"model": "qwen/qwen3.8-flash-next",
"tools": [
{
"type": "function",
"function": {
"name": "get_time",
"description": "Get the current time",
"parameters": {
"type": "object",
"properties": {}
}
}
}
]
}POST /v1/chat/completionsCHAT · hf_multimodal_chat +
Working request
curl https://api.openmayhem.ai/v1/chat/completions \
-H "Authorization: Bearer $OPENMAYHEM_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"model": "qwen/qwen3.8-flash-next",
"max_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh",
"thinking_mode": "enabled"
}'Parameters
| Parameter | Required | Type | Default | Allowed values | Limits and shape |
|---|---|---|---|---|---|
messages | Required | array | — | — | min items 1; max items 4096 [{"role":"user","content":"Hello"}] |
model | Required | string | — | Qwen/Qwen3.8-Flash-Next | — |
max_tokens | Optional | integer | — | — | min 0; max 262144 |
min_p | Optional | number | — | — | min 0; max 0 |
reasoning_effort | Optional | string | xhigh | low, medium, xhigh | — |
response_format | Optional | object | — | — | {"type":"json_object"} |
seed | Optional | integer | — | — | min 0; max 4294967295 |
stream | Optional | boolean | false | — | — |
temperature | Optional | number | — | — | min 0; max 2 |
thinking_history | Optional | string | preserve | latest_only, preserve | — |
thinking_mode | Optional | string | enabled | disabled, enabled | — |
tool_choice | Optional | string | object | — | — | "auto" or an OpenAI tool-choice object |
tools | Optional | array | — | — | min items 1; max items 128 [{"type":"function","function":{"name":"get_time","description":"Get the current time","parameters":{"type":"object","properties":{}}}}] |
top_k | Optional | integer | — | — | min 1; max 1000000 |
top_p | Optional | number | — | — | min 0.000001; max 1 |
Input shapes
tools
{
"model": "qwen/qwen3.8-flash-next",
"tools": [
{
"type": "function",
"function": {
"name": "get_time",
"description": "Get the current time",
"parameters": {
"type": "object",
"properties": {}
}
}
}
]
}Use this model through MCP
These calls use this model’s exact live request contract. First estimate the unchanged request, then pass the returned estimate ID and maximum cost to the paid tool. Read the complete MCP guide.
chatCHAT +
Send this object to estimate_request. Review the result, then send the next object to the named paid tool without changing request.
estimate_request · CHAT
{
"endpoint": "CHAT",
"model": "qwen/qwen3.8-flash-next",
"request": {
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh",
"thinking_mode": "enabled"
}
}chat
{
"model": "qwen/qwen3.8-flash-next",
"request": {
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh",
"thinking_mode": "enabled"
},
"estimate_id": "<estimate_id from estimate_request>",
"max_cost_usd": "<maximum_cost_usd from estimate_request>"
}create_responseRESPONSES +
Send this object to estimate_request. Review the result, then send the next object to the named paid tool without changing request.
estimate_request · RESPONSES
{
"endpoint": "RESPONSES",
"model": "qwen/qwen3.8-flash-next",
"request": {
"input": "Hello",
"max_output_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh"
}
}create_response
{
"model": "qwen/qwen3.8-flash-next",
"request": {
"input": "Hello",
"max_output_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh"
},
"estimate_id": "<estimate_id from estimate_request>",
"max_cost_usd": "<maximum_cost_usd from estimate_request>"
}chatCHAT +
Send this object to estimate_request. Review the result, then send the next object to the named paid tool without changing request.
estimate_request · CHAT
{
"endpoint": "CHAT",
"model": "qwen/qwen3.8-flash-next",
"request": {
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh",
"thinking_mode": "enabled"
}
}chat
{
"model": "qwen/qwen3.8-flash-next",
"request": {
"messages": [
{
"role": "user",
"content": "Hello"
}
],
"max_tokens": 2000,
"stream": false,
"reasoning_effort": "xhigh",
"thinking_mode": "enabled"
},
"estimate_id": "<estimate_id from estimate_request>",
"max_cost_usd": "<maximum_cost_usd from estimate_request>"
}Agent drop-ins
These configurations make this exact model the main model in each harness. Create an API key first and keep it in OPENMAYHEM_API_KEY.
OpenCode+
Save this as opencode.json in your project, export the key, then select openmayhem/model in /models.
opencode.json
{
"$schema": "https://opencode.ai/config.json",
"provider": {
"openmayhem": {
"npm": "@ai-sdk/openai-compatible",
"name": "OpenMayhem",
"options": {
"baseURL": "https://api.openmayhem.ai/v1",
"apiKey": "{env:OPENMAYHEM_API_KEY}"
},
"models": {
"qwen/qwen3.8-flash-next": {
"name": "Qwen3.8 Flash-Next",
"limit": {
"context": 262144,
"output": 32768
}
}
}
}
}
}Run
export OPENMAYHEM_API_KEY="replace-with-your-openmayhem-api-key"
opencode --model "openmayhem/qwen/qwen3.8-flash-next"Claude Code+
Claude Code speaks Anthropic Messages. Claude Code Router 2.0.0 translates it to this model's Chat Completions endpoint and removes Claude-only cache metadata.
~/.claude-code-router/config.json
{
"LOG": false,
"API_TIMEOUT_MS": 3600000,
"Providers": [
{
"name": "openmayhem",
"api_base_url": "https://api.openmayhem.ai/v1/chat/completions",
"api_key": "$OPENMAYHEM_API_KEY",
"models": [
"qwen/qwen3.8-flash-next"
],
"transformer": {
"use": [
"cleancache"
]
}
}
],
"Router": {
"default": "openmayhem,qwen/qwen3.8-flash-next",
"background": "openmayhem,qwen/qwen3.8-flash-next",
"think": "openmayhem,qwen/qwen3.8-flash-next",
"longContext": "openmayhem,qwen/qwen3.8-flash-next",
"longContextThreshold": 229376
}
}Run
npm install -g @anthropic-ai/claude-code @musistudio/claude-code-router@2.0.0
export OPENMAYHEM_API_KEY="replace-with-your-openmayhem-api-key"
export MAX_THINKING_TOKENS=0
export CLAUDE_CODE_MAX_CONTEXT_TOKENS=262144
export CLAUDE_CODE_DISABLE_UNKNOWN_MODEL_WINDOW_ENFORCEMENT=1
ccr start &
ccr code
ccr stopCodex CLI+
Codex 0.80.0 is the tested Chat Completions compatibility release for this model. The key stays in the environment; config.toml contains no secret.
~/.codex/config.toml
model = "qwen/qwen3.8-flash-next"
model_provider = "openmayhem"
model_context_window = 262144
[model_providers.openmayhem]
name = "OpenMayhem"
base_url = "https://api.openmayhem.ai/v1"
env_key = "OPENMAYHEM_API_KEY"
wire_api = "chat"
request_max_retries = 4
stream_max_retries = 5
stream_idle_timeout_ms = 3600000Run
export OPENMAYHEM_API_KEY="replace-with-your-openmayhem-api-key"
npx -y @openai/codex@0.80.0Hermes Agent+
Hermes uses OpenMayhem as a named custom provider over Chat Completions. The key stays in OPENMAYHEM_API_KEY and is not stored in YAML.
~/.hermes/config.yaml
providers:
openmayhem:
api: "https://api.openmayhem.ai/v1"
key_env: OPENMAYHEM_API_KEY
transport: chat_completions
default_model: "qwen/qwen3.8-flash-next"
models:
"qwen/qwen3.8-flash-next":
context_length: 262144
model:
default: "qwen/qwen3.8-flash-next"
provider: custom:openmayhem
api_mode: chat_completions
context_length: 262144
max_tokens: 32768Run
curl -fsSL https://raw.githubusercontent.com/NousResearch/hermes-agent/main/scripts/install.sh | bash
export OPENMAYHEM_API_KEY="replace-with-your-openmayhem-api-key"
hermes chatOpenClaw+
Merge this provider into openclaw.json. apiKey is an environment SecretRef, so the resolved key is not written to the file.
~/.openclaw/openclaw.json
{
"models": {
"mode": "merge",
"providers": {
"openmayhem": {
"baseUrl": "https://api.openmayhem.ai/v1",
"apiKey": "${OPENMAYHEM_API_KEY}",
"api": "openai-completions",
"authHeader": true,
"timeoutSeconds": 3600,
"models": [
{
"id": "qwen/qwen3.8-flash-next",
"name": "Qwen3.8 Flash-Next",
"reasoning": true,
"input": [
"text",
"image"
],
"contextWindow": 262144,
"contextTokens": 229376,
"maxTokens": 32768,
"compat": {
"supportsTools": true,
"supportsReasoningEffort": true,
"supportedReasoningEfforts": [
"low",
"medium",
"xhigh"
],
"supportsTemperature": true
}
}
]
}
}
},
"agents": {
"defaults": {
"model": {
"primary": "openmayhem/qwen/qwen3.8-flash-next"
}
}
}
}Run
export OPENMAYHEM_API_KEY="replace-with-your-openmayhem-api-key"
openclaw agent --local --model "openmayhem/qwen/qwen3.8-flash-next" --message "Hello"About this model
Qwen's multimodal mixture-of-experts reasoning model for long-context chat, visual understanding, tool use, and structured output.
- Family
- qwen3.8
How it is served
- Registered tiers
- T4
- Live tiers
- T4
- Quantizations
- nvfp4
- Live routes
- 2
- Live providers
- 2
- Prompt processing
- Provider-visible
- Context capacity
- 262.1K
- Concurrent requests
- 2
Routing providers
92293ede…d2479cb9ddae…f317
Accepted request parameters
From the network's signed model contract; anything else is rejected before a provider runs.
frequency_penaltyinputmax_completion_tokensmax_output_tokensmax_tokensmessagesmetadatamin_pmodelpresence_penaltypromptreasoning_effortresponse_formatseedstopstreamtemperaturetextthinking_historythinking_modetool_choicetoolstop_ktop_puserPrice versions
| Version | From | Until |
|---|---|---|
| v1328 | 2026-10-29 03:53 UTC | current |
| v1327 | 2026-10-29 02:52 UTC | 2026-10-29 03:53 UTC |
| v1326 | 2026-10-29 01:52 UTC | 2026-10-29 02:52 UTC |
| v1325 | 2026-10-29 00:52 UTC | 2026-10-29 01:52 UTC |
| v1324 | 2026-10-28 23:51 UTC | 2026-10-29 00:52 UTC |
| v1323 | 2026-10-28 22:52 UTC | 2026-10-28 23:51 UTC |
| v1322 | 2026-10-28 21:52 UTC | 2026-10-28 22:52 UTC |
| v1321 | 2026-10-28 20:51 UTC | 2026-10-28 21:52 UTC |
| v1320 | 2026-10-28 19:52 UTC | 2026-10-28 20:51 UTC |
| v1318 | 2026-10-28 18:52 UTC | 2026-10-28 19:52 UTC |
| v1317 | 2026-10-28 17:51 UTC | 2026-10-28 18:52 UTC |
| v1316 | 2026-10-28 16:53 UTC | 2026-10-28 17:51 UTC |
Questions and answers
What does Qwen3.8 Flash-Next cost on OpenMayhem?
Qwen3.8 Flash-Next currently costs $0.0200384 / M input · $0.0676298 / M output. There is no subscription: you buy credit and every request settles against a signed receipt for exactly what it used. Prices are versioned, and the full price history is published on this page.
Is Qwen3.8 Flash-Next available right now?
Yes. 2 providers serving Qwen3.8 Flash-Next right now, and it was online 100% of the last 3 days as measured by our own polling.
How do I use Qwen3.8 Flash-Next?
Send an OpenAI-compatible request to https://api.openmayhem.ai/v1/chat/completions with "model": "qwen/qwen3.8-flash-next" and your API key. Existing OpenAI SDKs work by changing the base URL. Create an account to get a key and starting credit.
Who serves Qwen3.8 Flash-Next?
Independent providers on the OpenMayhem network run the model on their own hardware. Over the last 30 days, 2 providers served it; the providers table on this page is attributed from signed receipts, not self-reporting.
Are my prompts stored?
OpenMayhem does not persist prompt or completion text. Requests are proxied to the serving provider and only billing metadata is retained: usage counts, the price applied, and the provider's signed receipt. The provider that serves a request necessarily processes its content.