GPT-OSS 120B vs Kimi K2.7 Code
Two open-weight chat models on the same endpoint and API key, so switching between them is a one-word change. Below: what each costs for three realistic workloads, how they differ, and measured speed.
Inference APIs prices are read live from the price list.
- Cost: GPT-OSS 120B is cheaper in all three workloads, by 79–82%.
- Speed (measured): GPT-OSS 120B 0.46 s to first token and 46 tok/s; Kimi K2.7 Code 0.87 s and 41 tok/s.
Side by side
| GPT-OSS 120B | Kimi K2.7 Code | |
|---|---|---|
| Served by | Inference APIs | Inference APIs |
| Model author | OpenAI | Moonshot AI |
| Model id | openai/gpt-oss-120b | moonshotai/Kimi-K2.7-Code |
| Input price | $0.20 / 1M tokens | $0.89 / 1M tokens |
| Output price | $0.80 / 1M tokens | $4.42 / 1M tokens |
| Context window | 131K tokens | 262K tokens |
| Capabilities | Chat, Reasoning, Tool calling, JSON mode | Chat, Reasoning, Coding, Tool calling |
| Weights | Open | Open |
| Status | Available | Available |
| Limits | No per-minute or per-day request or token caps; usage draws on a prepaid balance | No per-minute or per-day request or token caps; usage draws on a prepaid balance |
| Time to first token | 0.46 s | 0.87 s |
| Output speed | 45.8 tokens / s | 40.7 tokens / s |
What three workloads cost
List prices applied to the same work. The cheaper side of each row is in bold.
| Workload | GPT-OSS 120B | Kimi K2.7 Code | Difference |
|---|---|---|---|
| Chat assistant — 10,000 turns of 800 tokens in, 300 out | $4.00 | $20.38 | 80% |
| Long prompts or RAG — 10,000 requests of 8,000 in, 500 out | $20.00 | $93.30 | 79% |
| Generation-heavy — 10,000 requests of 500 in, 2,000 out | $17.00 | $92.85 | 82% |
GPT-OSS 120B is cheaper in all three workloads, by 79–82%. Reasoning models bill their thinking as output tokens, so real output counts run higher than the visible answer; treat the generation-heavy row as a floor for them.
When to choose which
- Time to first token matters: 0.46 s against 0.87 s in our measurement
- Cost is the deciding factor; it is cheaper in every workload above
- You are replacing llama-3.3-70b-versatile and want the model Groq itself recommends
- You build agents: tool calling, JSON-schema output and a visible reasoning trace are all verified on this endpoint
- You need full-precision weights; our upstream serves this model at FP4
- You need more than 131K tokens of context (it takes 262K)
- Coding agents: it is the coding-tuned model of Moonshot's Kimi family
- You need more than 131K tokens of context
Price, context and speed are measurable; answer quality on your task is not something a table can settle. Both take the same request, so the honest test is to run your own prompts through each in the playground.
Measured speed
Medians of three streamed runs on 2026-09-17, public endpoint, a prompt that asks for about 120 words. Time to first token is the first token of any kind, reasoning included; output speed counts every generated token from that point. Reasoning models then think before the visible answer starts: GPT-OSS 120B began answering after 1.38 s and Kimi K2.7 Code after 37.34 s at default settings, which you can shorten with the reasoning controls on each model page. Expect ±30% with time of day. Method and raw numbers: speed measurements.
Trying both
Same endpoint, same key. Change one string:
for MODEL in "openai/gpt-oss-120b" "moonshotai/Kimi-K2.7-Code"; do
curl -s https://api.inferenceapis.com/v1/chat/completions \
-H "Authorization: Bearer $INFERENCE_API_KEY" -H "Content-Type: application/json" \
-d "{\"model\": \"$MODEL\", \"max_tokens\": 500, \"messages\": [{\"role\": \"user\", \"content\": \"Summarise the plot of Hamlet in two sentences.\"}]}" \
| jq -r '.model, .choices[0].message.content, .usage'
doneFAQ
Which is cheaper, GPT-OSS 120B or Kimi K2.7 Code?
GPT-OSS 120B is cheaper in all three workloads, by 79–82%. The table above uses list prices: GPT-OSS 120B $0.20 / 1M tokens input, $0.80 / 1M tokens output; Kimi K2.7 Code $0.89 / 1M tokens input, $4.42 / 1M tokens output.
How do I switch between them?
They are on the same endpoint and key. Change the model field from openai/gpt-oss-120b to moonshotai/Kimi-K2.7-Code and nothing else.
Why does GPT-OSS 120B use more output tokens than the visible answer?
It is a reasoning model: it thinks before it answers and the thinking is billed as output tokens. Budget for that in output-heavy workloads, and set max_tokens to a few hundred or more so the answer is not cut off.
Spotted a price or limit that has changed? Tell us and we will re-check the provider page.