Background: Little is known regarding the restoration of the specific immune response after combined antiretroviral therapy (cART) and anti-tuberculosis (TB) therapy introduction among TB-HIV patients. In this study, we examined the immune response of TB-HIV patients to Mycobacterium tuberculosis (Mtb) antigens to evaluate the response dynamics to different antigens over time. Moreover, we also evaluated the influence of two different doses of efavirenz and the factors associated with immune reconstitution. Methods: This is a longitudinal study nested in a clinical trial, where cART was initiated during the baseline visit (D0), which occurred 30 ± 10 days after the introduction of anti-TB therapy. Follow-up visits were performed at 30, 60, 90 and 180 days after cART initiation. The production of IFN-γ upon in vitro stimulation with Mtb antigens purified protein derivative (PPD), ESAT-6 and 38 kDa/CFP-10 using ELISpot was examined at baseline and follow-up visits. Results: Sixty-one patients, all ART-naïve, were selected and included in the immune reconstitution analysis; seven (11.5%) developed Immune Reconstitution Inflammatory Syndrome (IRIS). The Mtb specific immune response was higher for the PPD antigen followed by 38 kDa/CFP-10 and increased in the first 60 days after cART initiation. In multivariate analysis, the variables independently associated with increased IFN-γ production in response to PPD antigen were CD4+ T cell counts <200 cells/mm3 at baseline, age, site of tuberculosis, 800 mg efavirenz dose and follow-up CD4+ T cell counts. Moreover, the factors associated with the production of IFN-γ in response to 38 kDa/ CFP-10 were detectable HIV viral load (VL) and CD4+ T cell counts at follow-up visits of ≥200 cells/mm3. Conclusions: These findings highlight the differences in immune response according to the specificity of the Mtb antigen, which contributes to a better understanding of TB-HIV immunopathogenesis. IFN-γ production elicited by PD and 38 kDa/CFP-10 antigens have a greater magnitude compared to ESAT-6 and are associated with different factors. The low response to ESAT-6, even during immune restoration, suggests that this antigen is not adequate to assess the immune response of immunosuppressed TB-HIV patients.